From 0afb39942098b421dbfbfa44f675c060378fdd61 Mon Sep 17 00:00:00 2001 From: Hugh Murray Date: Thu, 21 May 2026 15:55:43 +0100 Subject: [PATCH 01/22] Rename Atlas Search to MongoDB Search across all files --- .../scripts/seed-db.js | 4 ++-- apps/graph_rag_demo/README.md | 2 +- apps/local-bot/README.md | 6 +++--- apps/lyric-semantic-search/README.md | 2 +- apps/minimal-ts-agent/README.md | 6 +++--- apps/minimal-ts-agent/src/app/layout.tsx | 2 +- apps/minimal-ts-agent/src/app/page.tsx | 2 +- apps/mongo-mp/scripts/seed-db.js | 2 +- apps/mongostory/README.md | 4 ++-- apps/springai-terraform-rag/README.md | 4 ++-- .../backend/setup_indexes.py | 4 ++-- apps/voice-memory-demo/README.md | 8 ++++---- apps/voice-memory-demo/src/lib/mongodb.ts | 4 ++-- .../README.md | 4 ++-- .../src/server/tools.py | 4 ++-- misc/low-code/BuildShip.md | 2 +- ...ion_of_nomic_emebddings_with_mongodb.ipynb | 2 +- ...city_retention_with_mongodb_voyageai.ipynb | 8 ++++---- ...spatialqueries_vectorsearch_spritzes.ipynb | 4 ++-- .../langchain_parent_document_retrieval.ipynb | 4 ++-- ...rieval_strategies_mongodb_llamaindex.ipynb | 2 +- ...tegies_mongodb_llamaindex_togetherai.ipynb | 2 +- ...lity_with_mongodb_atlas_vector_store.ipynb | 8 ++++---- ...tion_From_RAG_to_Agents_with_MongoDB.ipynb | 2 +- ...gentic_chatbot_with_langgraph_claude.ipynb | 2 +- ...rking_memory_with_tavily_and_mongodb.ipynb | 4 ++-- ...b_as_a_toolbox_for_llamaindex_agents.ipynb | 4 ++-- ...nai_rag_hybrid_agentic_sports_scores.ipynb | 4 ++-- .../agents/smolagents_hf_with_mongodb.ipynb | 8 ++++---- .../agents/video_intelligence_agent.ipynb | 6 +++--- ..._hero_with_genai_with_mongodb_openai.ipynb | 10 +++++----- notebooks/performance_guidance/README.md | 8 ++++---- ...atabase_architecture_mongodb_elastic.ipynb | 8 ++++---- ...rformance_guidance_mongondb_pgvector.ipynb | 20 +++++++++---------- notebooks/rag/README.md | 2 +- .../SwigMenu_Playwright_OpenAI_MongoDB.ipynb | 8 ++++---- ...ner_PlaywrightLlamaIndexVectorSearch.ipynb | 20 +++++++++---------- ...ngodb_openai_langchain_POLM_AI_Stack.ipynb | 2 +- ...eepseek_r1_rag_pipeline_with_mongodb.ipynb | 2 +- ...rying_mongodb_unstructured_langgraph.ipynb | 6 +++--- partners/README.md | 2 +- ...allucination_detection_and_reduction.ipynb | 2 +- ...anagement_for_International_Shipping.ipynb | 2 +- ...agentic_knowledge_discovery_notebook.ipynb | 4 ++-- 44 files changed, 108 insertions(+), 108 deletions(-) diff --git a/apps/RT-voice-ts-store-agent/scripts/seed-db.js b/apps/RT-voice-ts-store-agent/scripts/seed-db.js index f152d100..4c4844cc 100644 --- a/apps/RT-voice-ts-store-agent/scripts/seed-db.js +++ b/apps/RT-voice-ts-store-agent/scripts/seed-db.js @@ -5,7 +5,7 @@ * * This script loads product data from a JSON file, computes embeddings for each document * using the Vercel AI SDK, seeds (upserts) each document into the "products" collection in the - * "ai_shop" database, and then creates both an Atlas Search index and a vector search index. + * "ai_shop" database, and then creates both an MongoDB Search index and a vector search index. * * It uses a dedicated MongoDB client instance created with custom appName settings. * @@ -90,7 +90,7 @@ async function createSearchIndex(client) { } }] }); - console.log("Successfully created Atlas Search index on 'products' collection"); + console.log("Successfully created MongoDB Search index on 'products' collection"); } catch (e) { console.error("Failed to create search index:", e); } diff --git a/apps/graph_rag_demo/README.md b/apps/graph_rag_demo/README.md index ab0bbae2..dbb90955 100644 --- a/apps/graph_rag_demo/README.md +++ b/apps/graph_rag_demo/README.md @@ -43,7 +43,7 @@ This guide explores how to leverage MongoDB's capabilities to create and manipul } ] } ``` - After this create an Atlas Search Index on the knowledge_graph collection. [Please refer this document](https://www.mongodb.com/docs/compass/current/indexes/create-search-index/). Please name the Atlas Search Index as default + After this create an MongoDB Search Index on the knowledge_graph collection. [Please refer this document](https://www.mongodb.com/docs/compass/current/indexes/create-search-index/). Please name the MongoDB Search Index as default diff --git a/apps/local-bot/README.md b/apps/local-bot/README.md index c6ab48f9..68516e88 100644 --- a/apps/local-bot/README.md +++ b/apps/local-bot/README.md @@ -1,6 +1,6 @@ # Step-by-Step Guide: Building a Local Chatbot with Streamlit, LangChain, Ollama, and MongoDB Atlas -In this tutorial, we'll set up a local chatbot using **Streamlit**, **LangChain**, **Ollama**, and **MongoDB Atlas Search**. This bot will leverage MongoDB's powerful Atlas Search capabilities alongside local LLMs (Large Language Models) via Ollama, allowing you to enhance user queries with context from chat history. +In this tutorial, we'll set up a local chatbot using **Streamlit**, **LangChain**, **Ollama**, and **MongoDB MongoDB Search**. This bot will leverage MongoDB's powerful MongoDB Search capabilities alongside local LLMs (Large Language Models) via Ollama, allowing you to enhance user queries with context from chat history. ## Prerequisites Before starting, make sure you have the following installed: @@ -40,7 +40,7 @@ Here’s a quick rundown of the tools we’re using in this project: * *[Streamlit](https://streamlit.io)*: A Python library for easily creating data-based web applications. We'll use it to create a local chatbot interface. * *[LangChain](https://langchain.com)*: A framework that simplifies working with LLMs and document processing. It will assist processing user queries and generate responses. * *[Ollama](https://ollama.com)*: A solution for deploying LLMs locally without external API dependency. It to host our models. -* *[MongoDB Atlas Search](https://www.mongodb.com/products/platform/atlas-search)*: Adds a powerful, flexible vector search functionality to our app. It will store user queries and responses in MongoDB. +* *[MongoDB MongoDB Search](https://www.mongodb.com/products/platform/atlas-search)*: Adds a powerful, flexible vector search functionality to our app. It will store user queries and responses in MongoDB. ### Setting Up `requirements.txt` @@ -268,7 +268,7 @@ At this point, you can start prompting with inputs like “Who started AT&T?” ## Conclusion and Next Steps -In this tutorial, we built a local chatbot setup using MongoDB Atlas Search and local LLMs via Ollama, integrated through Streamlit. This project forms a robust foundation for further development and deployment. +In this tutorial, we built a local chatbot setup using MongoDB MongoDB Search and local LLMs via Ollama, integrated through Streamlit. This project forms a robust foundation for further development and deployment. Possible Extensions: diff --git a/apps/lyric-semantic-search/README.md b/apps/lyric-semantic-search/README.md index 9fcd47b4..02108c0e 100644 --- a/apps/lyric-semantic-search/README.md +++ b/apps/lyric-semantic-search/README.md @@ -3,7 +3,7 @@ This repo is support the [Building a Semantic Search Service With Spring AI and Spring AI is an application framework from [Spring](https://spring.io/) that allows you to combine various AI services and plugins with your applications. With support for many chat, text-to-image, and embedding models, you can get your AI powered Java application set up for a variety of AI use cases. -With Spring AI, MongoDB Atlas is supported as a vector database, all with [Atlas Vector Search](https://www.mongodb.com/products/platform/atlas-vector-search) to power your semantic search and implement your RAG applications. To learn more about RAG and other key concepts in AI, check out the [MongoDB AI integration docs](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/#std-label-ai-key-concepts). +With Spring AI, MongoDB Atlas is supported as a vector database, all with [MongoDB Vector Search](https://www.mongodb.com/products/platform/atlas-vector-search) to power your semantic search and implement your RAG applications. To learn more about RAG and other key concepts in AI, check out the [MongoDB AI integration docs](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/#std-label-ai-key-concepts). In this tutorial, we’ll go through what you need to get started with Spring AI and MongoDB. Adding documents to your database with the vectorised content (embeddings), and searching this content with semantic search. The full code for this tutorial is available in this [Github repository](https://github.com/timotheekelly/lyric-semantic-search). diff --git a/apps/minimal-ts-agent/README.md b/apps/minimal-ts-agent/README.md index 4039b1b4..0dfa8ae3 100644 --- a/apps/minimal-ts-agent/README.md +++ b/apps/minimal-ts-agent/README.md @@ -1,6 +1,6 @@ # RAG Agent Demo — How to Create an AI Agent with Minimal Coding -Companion project for the **"How to Create an AI Agent with Minimal Coding"** video. This demo builds a fully functional RAG (Retrieval-Augmented Generation) agent that answers questions about the MongoDB Brand Book using MongoDB Atlas Vector Search, Voyage AI embeddings, and the Vercel AI SDK's `ToolLoopAgent`. +Companion project for the **"How to Create an AI Agent with Minimal Coding"** video. This demo builds a fully functional RAG (Retrieval-Augmented Generation) agent that answers questions about the MongoDB Brand Book using MongoDB MongoDB Vector Search, Voyage AI embeddings, and the Vercel AI SDK's `ToolLoopAgent`. ## What It Does @@ -23,7 +23,7 @@ flowchart TD D -->|Reasoning step| E{Need more context?} E -->|Yes| F[searchDocumentation tool] F -->|Embed query| G[Voyage AI] - G -->|Query vector| H[MongoDB Atlas Vector Search] + G -->|Query vector| H[MongoDB MongoDB Vector Search] H -->|Top 5 results| D E -->|No| I[Generate final response] I -->|Stream| B @@ -92,7 +92,7 @@ VOYAGE_AI_API_KEY=your-voyage-ai-api-key npx ts-node scripts/ingest.ts ``` -This embeds 14 brand book sections with Voyage AI, inserts them into the `brand_demo.brand_book` collection, and automatically creates the Atlas Vector Search index. The index may take a minute to become ready after creation. +This embeds 14 brand book sections with Voyage AI, inserts them into the `brand_demo.brand_book` collection, and automatically creates the MongoDB Vector Search index. The index may take a minute to become ready after creation. ### 4. Run the app diff --git a/apps/minimal-ts-agent/src/app/layout.tsx b/apps/minimal-ts-agent/src/app/layout.tsx index d68262bf..f5c1de7b 100644 --- a/apps/minimal-ts-agent/src/app/layout.tsx +++ b/apps/minimal-ts-agent/src/app/layout.tsx @@ -15,7 +15,7 @@ const geistMono = Geist_Mono({ export const metadata: Metadata = { title: "MongoDB RAG Agent — Brand Book Expert", description: - "A fully autonomous RAG agent powered by Vercel AI SDK ToolLoopAgent and MongoDB Atlas Vector Search", + "A fully autonomous RAG agent powered by Vercel AI SDK ToolLoopAgent and MongoDB MongoDB Vector Search", }; export default function RootLayout({ diff --git a/apps/minimal-ts-agent/src/app/page.tsx b/apps/minimal-ts-agent/src/app/page.tsx index aa6d9fa2..0fe75e1d 100644 --- a/apps/minimal-ts-agent/src/app/page.tsx +++ b/apps/minimal-ts-agent/src/app/page.tsx @@ -64,7 +64,7 @@ export default function ChatPage() {

MongoDB Brand Expert

- RAG Agent powered by ToolLoopAgent + Atlas Vector Search + RAG Agent powered by ToolLoopAgent + MongoDB Vector Search

diff --git a/apps/mongo-mp/scripts/seed-db.js b/apps/mongo-mp/scripts/seed-db.js index 4103fe34..80c65e59 100644 --- a/apps/mongo-mp/scripts/seed-db.js +++ b/apps/mongo-mp/scripts/seed-db.js @@ -78,7 +78,7 @@ async function createSearchIndex(client) { }] }); - console.log("Successfully created Atlas Search index"); + console.log("Successfully created MongoDB Search index"); } catch (e) { console.error('Failed to create search index:', e); } diff --git a/apps/mongostory/README.md b/apps/mongostory/README.md index 42d5d512..15b7069b 100644 --- a/apps/mongostory/README.md +++ b/apps/mongostory/README.md @@ -40,7 +40,7 @@ MongoStory is a cloud-native platform designed to empower content creators, edit ### Backend - **API Routes**: Next.js API routes for server-side functionality - **Database**: MongoDB for flexible document storage -- **Vector Search**: MongoDB Atlas Vector Search for semantic content operations +- **Vector Search**: MongoDB MongoDB Vector Search for semantic content operations - **AI Integration**: Integration with AI models via AI SDK - xAI (Grok) ### AI Integration @@ -60,7 +60,7 @@ MongoStory leverages MongoDB's document model for flexible content storage and i - `clusters`: AI-generated content clusters - `socialMediaPosts`: Generated social media content -- **Vector Search**: Uses MongoDB Atlas Vector Search for semantic operations: +- **Vector Search**: Uses MongoDB MongoDB Vector Search for semantic operations: - Content similarity detection - Semantic search functionality - Automatic content clustering diff --git a/apps/springai-terraform-rag/README.md b/apps/springai-terraform-rag/README.md index e7608aaf..bd0b8c62 100644 --- a/apps/springai-terraform-rag/README.md +++ b/apps/springai-terraform-rag/README.md @@ -1,6 +1,6 @@ # MongoDB Atlas + Terraform Spring Boot RAG Application -This repository demonstrates how to build a **Retrieval-Augmented Generation (RAG)** application using **Spring Boot**, **OpenAI embeddings**, and **MongoDB Atlas Vector Search**. The infrastructure is automated using **Terraform** to provision and manage MongoDB Atlas resources. +This repository demonstrates how to build a **Retrieval-Augmented Generation (RAG)** application using **Spring Boot**, **OpenAI embeddings**, and **MongoDB MongoDB Vector Search**. The infrastructure is automated using **Terraform** to provision and manage MongoDB Atlas resources. ## Overview @@ -85,6 +85,6 @@ To run this project, you'll need: ## Technologies Used - **Spring Boot**: Java-based framework for building REST APIs. -- **MongoDB Atlas**: An integrated suite of data services (including Atlas Vector Search) centered around a cloud database designed to accelerate and simplify how you build with data. Build faster and build smarter with a developer data platform that helps solve your data challenges. Click [here](https://www.mongodb.com/products/platform/atlas-database) to learn more. +- **MongoDB Atlas**: An integrated suite of data services (including MongoDB Vector Search) centered around a cloud database designed to accelerate and simplify how you build with data. Build faster and build smarter with a developer data platform that helps solve your data challenges. Click [here](https://www.mongodb.com/products/platform/atlas-database) to learn more. - **OpenAI**: Generates embeddings for semantic searches. - **Terraform**: Automates infrastructure management for MongoDB Atlas. diff --git a/apps/video-intelligence/backend/setup_indexes.py b/apps/video-intelligence/backend/setup_indexes.py index bac31ed9..2b84eb87 100755 --- a/apps/video-intelligence/backend/setup_indexes.py +++ b/apps/video-intelligence/backend/setup_indexes.py @@ -1,6 +1,6 @@ #!/usr/bin/env python3 """ -MongoDB Atlas Search Index Setup Script +MongoDB MongoDB Search Index Setup Script Creates the required vector search and text search indexes for the Video Intelligence app. """ @@ -18,7 +18,7 @@ def setup_indexes(): # Get embedding dimensions from environment variable EMBEDDING_DIM_SIZE = int(os.getenv("EMBEDDING_DIM_SIZE", "1024")) print(f"Using embedding dimensions: {EMBEDDING_DIM_SIZE}") - print("🔧 Setting up MongoDB Atlas Search Indexes") + print("🔧 Setting up MongoDB MongoDB Search Indexes") print("=" * 50) # Load environment variables diff --git a/apps/voice-memory-demo/README.md b/apps/voice-memory-demo/README.md index cf347870..5fbf9618 100644 --- a/apps/voice-memory-demo/README.md +++ b/apps/voice-memory-demo/README.md @@ -64,13 +64,13 @@ Open [http://localhost:3000](http://localhost:3000) in your browser. ### 4. Create MongoDB Indexes -For hybrid search (vector + text) with `$rankFusion` (require latest Atlas version cluster), the code creates on startup two Atlas Search indexes on the `memories` collection: +For hybrid search (vector + text) with `$rankFusion` (require latest Atlas version cluster), the code creates on startup two MongoDB Search indexes on the `memories` collection: #### Vector Search Index **Index Name:** `memory_vector_index` -Optional: In Atlas UI: **Search Indexes** → **Create Search Index** → **Atlas Vector Search** +Optional: In Atlas UI: **Search Indexes** → **Create Search Index** → **MongoDB Vector Search** ```json { @@ -97,11 +97,11 @@ Optional: In Atlas UI: **Search Indexes** → **Create Search Index** → **Atla } ``` -#### Atlas Search Index (Text) +#### MongoDB Search Index (Text) **Index Name:** `memory_text_index` -Optional: In Atlas UI: **Search Indexes** → **Create Search Index** → **Atlas Search** +Optional: In Atlas UI: **Search Indexes** → **Create Search Index** → **MongoDB Search** ```json { diff --git a/apps/voice-memory-demo/src/lib/mongodb.ts b/apps/voice-memory-demo/src/lib/mongodb.ts index c11eff22..1303554d 100644 --- a/apps/voice-memory-demo/src/lib/mongodb.ts +++ b/apps/voice-memory-demo/src/lib/mongodb.ts @@ -39,7 +39,7 @@ const VECTOR_INDEX_DEFINITION = { }, }; -// Atlas Search (text) index definition +// MongoDB Search (text) index definition const TEXT_INDEX_DEFINITION = { name: 'memory_text_index', type: 'search' as const, @@ -70,7 +70,7 @@ const TEXT_INDEX_DEFINITION = { }; /** - * Ensures Atlas Search indexes exist on the memories collection. + * Ensures MongoDB Search indexes exist on the memories collection. * Creates them if they don't exist. * Note: Indexes take 1-5 minutes to build after creation. */ diff --git a/apps/voice-openai-mongo-rentals-agent/README.md b/apps/voice-openai-mongo-rentals-agent/README.md index a42b4f20..d4c6a96f 100644 --- a/apps/voice-openai-mongo-rentals-agent/README.md +++ b/apps/voice-openai-mongo-rentals-agent/README.md @@ -1,4 +1,4 @@ -# Voice Agent with MongoDB Atlas Vector Search +# Voice Agent with MongoDB MongoDB Vector Search Thumbnail @@ -112,7 +112,7 @@ print("All records ingested successfully!") bookings = db['bookings'] -## Create Atlas Search index +## Create MongoDB Search index db.create_collection("bookings") search_index_model = SearchIndexModel( diff --git a/apps/voice-openai-mongo-rentals-agent/src/server/tools.py b/apps/voice-openai-mongo-rentals-agent/src/server/tools.py index 72c3d480..ce6b5fed 100644 --- a/apps/voice-openai-mongo-rentals-agent/src/server/tools.py +++ b/apps/voice-openai-mongo-rentals-agent/src/server/tools.py @@ -37,7 +37,7 @@ class Booking(BaseModel): @tool def rentlas_search_tool(query: str, k: int = 5): """ - Perform a vector similarity search using MongoDB Atlas Vector Search to find rentals. + Perform a vector similarity search using MongoDB MongoDB Vector Search to find rentals. Args: query (str): The search query string. @@ -48,7 +48,7 @@ def rentlas_search_tool(query: str, k: int = 5): and score is the similarity score (lower is more similar). Note: - Uses MongoDB Atlas Vector Search for semantic search capabilities. + Uses MongoDB MongoDB Vector Search for semantic search capabilities. """ vector_store = MongoDBAtlasVectorSearch.from_connection_string( connection_string=os.environ["MONGODB_ATLAS_URI"], diff --git a/misc/low-code/BuildShip.md b/misc/low-code/BuildShip.md index e76b77ec..f315e7f7 100644 --- a/misc/low-code/BuildShip.md +++ b/misc/low-code/BuildShip.md @@ -63,7 +63,7 @@ This workflow serves as a versatile template for creating various types of AI ag ### Extend MongoDB Integration - Implement complex aggregation pipelines for advanced queries -- Add MongoDB Atlas Search for full-text search capabilities +- Add MongoDB MongoDB Search for full-text search capabilities - Utilize MongoDB Change Streams for real-time updates - Incorporate MongoDB Charts for data visualization diff --git a/notebooks/advanced_techniques/automatic_quantization_of_nomic_emebddings_with_mongodb.ipynb b/notebooks/advanced_techniques/automatic_quantization_of_nomic_emebddings_with_mongodb.ipynb index 5ce3debd..41ca17df 100644 --- a/notebooks/advanced_techniques/automatic_quantization_of_nomic_emebddings_with_mongodb.ipynb +++ b/notebooks/advanced_techniques/automatic_quantization_of_nomic_emebddings_with_mongodb.ipynb @@ -1186,7 +1186,7 @@ "Cost Reduction and Resource Efficiency: Efficient data storage and retrieval reduce the need for excessive computational resources, leading to cost savings.\n", "By examining the trade-offs between retrieval accuracy and performance across different embedding formats (float32, int8, and binary), we showcased how MongoDB's capabilities, such as vector indexing and automatic quantization, can streamline data storage, retrieval, and analysis. \n", "\n", - "From this tutorial, we’ve explored Atlas Vector Search native capabilities for scalar quantization as well as binary quantization with rescoring. Our implementation showed that automatic quantization increases scalability and cost savings by reducing the storage and computational resources for efficient processing of vectors. In most cases, automatic quantization reduces the RAM for mongot by 3.75x for scalar and by 24x for binary; the vector values shrink by 4x and 32x, respectively, but the Hierarchical Navigable Small Worlds graph itself does not shrink.\n", + "From this tutorial, we’ve explored MongoDB Vector Search native capabilities for scalar quantization as well as binary quantization with rescoring. Our implementation showed that automatic quantization increases scalability and cost savings by reducing the storage and computational resources for efficient processing of vectors. In most cases, automatic quantization reduces the RAM for mongot by 3.75x for scalar and by 24x for binary; the vector values shrink by 4x and 32x, respectively, but the Hierarchical Navigable Small Worlds graph itself does not shrink.\n", "\n", "We recommend automatic quantization if you have a large number of full-fidelity vectors, typically over 10M vectors. After quantization, you index reduced representation vectors without compromising the accuracy of your retrieval.\n", "To further explore quantization techniques and their applications, refer to resources like [Ingesting Quantized Vectors with Cohere](https://www.mongodb.com/developer/products/atlas/ingesting_quantized_vectors_with_cohere/). An [additional notebook](https://github.com/mongodb-developer/GenAI-Showcase/blob/main/notebooks/advanced_techniques/advanced_evaluation_of_quantized_vectors_using_cohere_mongodb_beir.ipynb) for comparing retrieval accuracy between quantized and non-quantized vectors is also available to deepen your understanding of these methods." diff --git a/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb b/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb index 35038294..c89c46c4 100644 --- a/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb +++ b/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb @@ -41,7 +41,7 @@ "- Binary Quantization: A technique used to reduce the precision of a vector by converting it to a lower precision.\n", "- Representational Capacity Retention: The ability of a vector to retain the information of the original vector.\n", "\n", - "In this guide, we demonstrate how to leverage MongoDB Atlas Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. \n", + "In this guide, we demonstrate how to leverage MongoDB MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. \n", "\n", "By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", "\n", @@ -593,7 +593,7 @@ "\n", "Benefits\n", "The BinData vector format requires about three times less disk space in your cluster compared to arrays of elements. \n", - "It allows you to index your vectors with alternate types such as int1 or int8 vectors, reducing the memory needed to build the Atlas Vector Search index for your collection. \n", + "It allows you to index your vectors with alternate types such as int1 or int8 vectors, reducing the memory needed to build the MongoDB Vector Search index for your collection. \n", "It reduces the RAM for mongot by 3.75x for scalar and by 24x for binary; the vector values shrink by 4x and 32x respectively, but the Hierarchical Navigable Small Worlds graph itself doesn't shrink.\n", "\n", "In this notebook, we will convert the embeddings to the BSON binData vector format by using the `bson.binary` module.\n", @@ -1321,7 +1321,7 @@ " \"wiki_id\": 1,\n", " \"url\": 1,\n", " \"score\": {\n", - " # Atlas Vector Search assigns a score, in a fixed range from 0 to 1 (\n", + " # MongoDB Vector Search assigns a score, in a fixed range from 0 to 1 (\n", " # where 0 indicates low similarity and 1 indicates high similarity), to every document that it returns.\n", " # This is the score of the vector search operation score = (1 + cosine(v1,v2)) / 2.\n", " \"$meta\": \"vectorSearchScore\"\n", @@ -4211,7 +4211,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "In this guide, we demonstrate how to leverage MongoDB Atlas Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", + "In this guide, we demonstrate how to leverage MongoDB MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", "\n", "These techniques not only cut operational costs but also improve throughput, allowing you to handle larger workloads or more complex queries. \n", "\n", diff --git a/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb b/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb index 62fd3f27..5b0d16b5 100644 --- a/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb +++ b/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb @@ -458,9 +458,9 @@ "## Which one comes first, Vector Search or Geospatial Queries?\n", "Both of these need to be the first stage in their aggregation pipelines, so instead of making one pipeline we are going to do a little loophole. We will do two pipelines. But how will we decide which?!\n", "\n", - "When I'm using Google Maps to figure out where to go, I normally first search for what I'm looking for and then I see how far away it is from where I currently am and pick the closest location to me. So let's keep that mindset in place and start off with MongoDB Atlas Vector Search for this tutorial. But, I understand intuitively some of you might prefer to search via all nearby locations and then utilize Vector Search, so I'll highlight that method of searching for your spritz's as well.\n", + "When I'm using Google Maps to figure out where to go, I normally first search for what I'm looking for and then I see how far away it is from where I currently am and pick the closest location to me. So let's keep that mindset in place and start off with MongoDB MongoDB Vector Search for this tutorial. But, I understand intuitively some of you might prefer to search via all nearby locations and then utilize Vector Search, so I'll highlight that method of searching for your spritz's as well.\n", "\n", - "## MongoDB Atlas Vector Search\n", + "## MongoDB MongoDB Vector Search\n", "We have a couple steps here. Our first step is to create a Vector Search Index. Do this inside of MongoDB Atlas by following this documentation. Please keep in mind that your index is NOT run in your script, it lives in your cluster. You'll know it's ready to go when the button turns green and it's activated." ] }, diff --git a/notebooks/advanced_techniques/langchain_parent_document_retrieval.ipynb b/notebooks/advanced_techniques/langchain_parent_document_retrieval.ipynb index e51ad28d..80dee015 100644 --- a/notebooks/advanced_techniques/langchain_parent_document_retrieval.ipynb +++ b/notebooks/advanced_techniques/langchain_parent_document_retrieval.ipynb @@ -351,7 +351,7 @@ { "data": { "text/plain": [ - "Document(metadata={'contentType': None, 'pageDescription': None, 'productName': 'MongoDB Atlas', 'tags': ['atlas', 'docs'], 'version': None, 'updated': {'$date': '2024-05-20T17:30:49.148Z'}, 'url': 'https://mongodb.com/docs/atlas/access-tracking/', 'title': 'View Database Access History'}, page_content='# View Database Access History\\n\\n- This feature is not available for `M0` free clusters, `M2`, and `M5` clusters. To learn more, see Atlas M0 (Free Cluster), M2, and M5 Limits.\\n\\n- This feature is not supported on Serverless instances at this time. To learn more, see Serverless Instance Limitations.\\n\\n## Overview\\n\\nAtlas parses the MongoDB database logs to collect a list of authentication requests made against your clusters through the following methods:\\n\\n- `mongosh`\\n\\n- Compass\\n\\n- Drivers\\n\\nAuthentication requests made with API Keys through the Atlas Administration API are not logged.\\n\\nAtlas logs the following information for each authentication request within the last 7 days:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nField\\n\\n\\nDescription\\n\\n
\\nTimestamp\\n\\n\\nThe date and time of the authentication request.\\n\\n
\\nUsername\\n\\n\\nThe username associated with the database user who made the authentication request.\\n\\nFor LDAP usernames, the UI displays the resolved LDAP name. Hover over the name to see the full LDAP username.\\n\\n
\\nIP Address\\n\\n\\nThe IP address of the machine that sent the authentication request.\\n\\n
\\nHost\\n\\n\\nThe target server that processed the authentication request.\\n\\n
\\nAuthentication Source\\n\\n\\nThe database that the authentication request was made against. `admin` is the authentication source for SCRAM-SHA users and `$external` for LDAP users.\\n\\n
\\nAuthentication Result\\n\\n\\nThe success or failure of the authentication request. A reason code is displayed for the failed authentication requests.\\n\\n
Authentication requests are pre-sorted by descending timestamp with 25 entries per page.\\n\\n### Logging Limitations\\n\\nIf a cluster experiences an activity spike and generates an extremely large quantity of log messages, Atlas may stop collecting and storing new logs for a period of time.\\n\\nLog analysis rate limits apply only to the Performance Advisor UI, the Query Insights UI, the Access Tracking UI, and the Atlas Search Query Analytics UI. Downloadable log files are always complete.\\n\\nIf authentication requests occur during a period when logs are not collected, they will not appear in the database access history.\\n\\n## Required Access\\n\\nTo view database access history, you must have `Project Owner` or `Organization Owner` access to Atlas.\\n\\n## Procedure\\n\\n\\n\\n\\n\\nTo return the access logs for a cluster using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas accessLogs list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas accessLogs list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nTo view the database access history using the API, see Access Tracking.\\n\\n\\n\\n\\n\\nUse the following procedure to view your database access history using the Atlas UI:\\n\\n### Navigate to the Clusters page for your project.\\n\\n- If it is not already displayed, select the organization that contains your desired project from the Organizations menu in the navigation bar.\\n\\n- If it is not already displayed, select your desired project from the Projects menu in the navigation bar.\\n\\n- If the Clusters page is not already displayed, click Database in the sidebar.\\n\\n### View the cluster\\'s database access history.\\n\\n- On the cluster card, click .\\n\\n- Select View Database Access History.\\n\\nor\\n\\n- Click the cluster name.\\n\\n- Click .\\n\\n- Select View Database Access History.\\n\\n\\n\\n\\n\\n')" + "Document(metadata={'contentType': None, 'pageDescription': None, 'productName': 'MongoDB Atlas', 'tags': ['atlas', 'docs'], 'version': None, 'updated': {'$date': '2024-05-20T17:30:49.148Z'}, 'url': 'https://mongodb.com/docs/atlas/access-tracking/', 'title': 'View Database Access History'}, page_content='# View Database Access History\\n\\n- This feature is not available for `M0` free clusters, `M2`, and `M5` clusters. To learn more, see Atlas M0 (Free Cluster), M2, and M5 Limits.\\n\\n- This feature is not supported on Serverless instances at this time. To learn more, see Serverless Instance Limitations.\\n\\n## Overview\\n\\nAtlas parses the MongoDB database logs to collect a list of authentication requests made against your clusters through the following methods:\\n\\n- `mongosh`\\n\\n- Compass\\n\\n- Drivers\\n\\nAuthentication requests made with API Keys through the Atlas Administration API are not logged.\\n\\nAtlas logs the following information for each authentication request within the last 7 days:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nField\\n\\n\\nDescription\\n\\n
\\nTimestamp\\n\\n\\nThe date and time of the authentication request.\\n\\n
\\nUsername\\n\\n\\nThe username associated with the database user who made the authentication request.\\n\\nFor LDAP usernames, the UI displays the resolved LDAP name. Hover over the name to see the full LDAP username.\\n\\n
\\nIP Address\\n\\n\\nThe IP address of the machine that sent the authentication request.\\n\\n
\\nHost\\n\\n\\nThe target server that processed the authentication request.\\n\\n
\\nAuthentication Source\\n\\n\\nThe database that the authentication request was made against. `admin` is the authentication source for SCRAM-SHA users and `$external` for LDAP users.\\n\\n
\\nAuthentication Result\\n\\n\\nThe success or failure of the authentication request. A reason code is displayed for the failed authentication requests.\\n\\n
Authentication requests are pre-sorted by descending timestamp with 25 entries per page.\\n\\n### Logging Limitations\\n\\nIf a cluster experiences an activity spike and generates an extremely large quantity of log messages, Atlas may stop collecting and storing new logs for a period of time.\\n\\nLog analysis rate limits apply only to the Performance Advisor UI, the Query Insights UI, the Access Tracking UI, and the MongoDB Search Query Analytics UI. Downloadable log files are always complete.\\n\\nIf authentication requests occur during a period when logs are not collected, they will not appear in the database access history.\\n\\n## Required Access\\n\\nTo view database access history, you must have `Project Owner` or `Organization Owner` access to Atlas.\\n\\n## Procedure\\n\\n\\n\\n\\n\\nTo return the access logs for a cluster using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas accessLogs list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas accessLogs list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nTo view the database access history using the API, see Access Tracking.\\n\\n\\n\\n\\n\\nUse the following procedure to view your database access history using the Atlas UI:\\n\\n### Navigate to the Clusters page for your project.\\n\\n- If it is not already displayed, select the organization that contains your desired project from the Organizations menu in the navigation bar.\\n\\n- If it is not already displayed, select your desired project from the Projects menu in the navigation bar.\\n\\n- If the Clusters page is not already displayed, click Database in the sidebar.\\n\\n### View the cluster\\'s database access history.\\n\\n- On the cluster card, click .\\n\\n- Select View Database Access History.\\n\\nor\\n\\n- Click the cluster name.\\n\\n- Click .\\n\\n- Select View Database Access History.\\n\\n\\n\\n\\n\\n')" ] }, "execution_count": 11, @@ -944,7 +944,7 @@ "Node agent:\n", "{'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_sifH0mrhbpesQie4BTnQytNk', 'function': {'arguments': '{\"user_query\":\"How do I improve slow queries in MongoDB?\"}', 'name': 'get_info_about_mongodb'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 165, 'total_tokens': 192, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-11-20', 'system_fingerprint': 'fp_d924043139', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-bc1db263-f4f5-40ba-a6ba-b18a3585e095-0', tool_calls=[{'name': 'get_info_about_mongodb', 'args': {'user_query': 'How do I improve slow queries in MongoDB?'}, 'id': 'call_sifH0mrhbpesQie4BTnQytNk', 'type': 'tool_call'}], usage_metadata={'input_tokens': 165, 'output_tokens': 27, 'total_tokens': 192, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}\n", "Node tools:\n", - "{'messages': [ToolMessage(content='# Monitor and Improve Slow Queries\\n\\n*Only available on M10+ clusters and serverless instances*\\n\\nThe Performance Advisor monitors queries that MongoDB considers slow and suggests new indexes to improve query performance. The threshold for slow queries varies based on the average time of operations on your cluster to provide recommendations pertinent to your workload.\\n\\nRecommended indexes are accompanied by sample queries, grouped by query shape, that were run against a collection that would benefit from the suggested index. The Performance Advisor doesn\\'t negatively affect the performance of your Atlas clusters.\\n\\nYou can also monitor collection-level query latency with Namespace Insights and query performance with the Query Profiler.\\n\\nIf the slow query log contains consecutive `$match` stages in the aggregation pipeline, the two stages can coalesce into the first `$match` stage and result in a single `$match` stage. As a result, the query shape in the Performance Advisor might differ from the actual query you ran.\\n\\n## Common Reasons for Slow Queries\\n\\nIf a query is slow, common reasons include:\\n\\n- The query is unsupported by your current indexes.\\n\\n- Some documents in your collection have large array fields that are costly to search and index.\\n\\n- One query retrieves information from multiple collections with $lookup.\\n\\n## Required Access\\n\\nTo view collections with slow queries and see suggested indexes, you must have `Project Read Only` access or higher to the project.\\n\\nTo view field values in a sample query in the Performance Advisor, you must have `Project Data Access Read/Write` access or higher to the project.\\n\\nTo enable or disable the Atlas-managed slow operation threshold, you must have `Project Owner` access to the project. Users with `Organization Owner` access must add themselves to the project as a `Project Owner`.\\n\\n## Configure the Slow Query Threshold\\n\\nBy default, Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster. However, you can opt out of this feature and instead use a fixed slow query threshold of 100 milliseconds. You can disable the Atlas-managed slow operation threshold with the Atlas CLI, Atlas Administration API, or Atlas UI.\\n\\nAtlas clusters with Atlas Search enabled don\\'t support the Atlas-managed slow query operation threshold.\\n\\nFor `M0`, `M2`, `M5` clusters and serverless instances, Atlas disables the Atlas-managed slow query operation threshold by default and you can\\'t enable it.\\n\\n### Disable the Atlas-Managed Slow Operation Threshold\\n\\nBy default, Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster. If you disable the Atlas-managed slow query threshold, it no longer dynamically adjusts. MongoDB defaults the fixed slow query threshold to 100 milliseconds. We don\\'t recommend that you set the fixed slow query threshold lower than 100 milliseconds.\\n\\nTo disable the Atlas-managed slow operation threshold and use a fixed threshold of 100 milliseconds:\\n\\n\\n\\n\\n\\nTo disable the Atlas-managed slow operation threshold for your project using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowOperationThreshold disable [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowOperationThreshold disable.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nSee Disable Managed Slow Operation Threshold.\\n\\n\\n\\n\\n\\nIn the Project Settings for the current project, toggle Managed Slow Operations to Off.\\n\\n\\n\\n\\n\\n### Enable the Atlas-Managed Slow Operation Threshold\\n\\nAtlas enables the Atlas-managed slow operation threshold by default. To re-enable the Atlas-managed slow operation threshold that you previously disabled:\\n\\n\\n\\n\\n\\nTo enable the Atlas-managed slow operation threshold for your project using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowOperationThreshold enable [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowOperationThreshold enable.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nSee Enable Managed Slow Operation Threshold.\\n\\n\\n\\n\\n\\nIn the Project Settings for the current project, toggle Managed Slow Operations to On.\\n\\n\\n\\n\\n\\n## Index Considerations\\n\\nIndexes improve read performance, but a large number of indexes can negatively impact write performance since indexes must be updated during writes. If your collection already has several indexes, consider this tradeoff of read and write performance when deciding whether to create new indexes. Examine whether a query for such a collection can be modified to take advantage of existing indexes, as well as whether a query occurs often enough to justify the cost of a new index.\\n\\n## Access Performance Advisor\\n\\n\\n\\n\\n\\n### View Collections with Slow Queries\\n\\nTo return up to 20 namespaces in `.` format for collections experiencing slow queries using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor namespaces list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor namespaces list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n### View Slow Query Logs\\n\\nTo return query log line items for slow queries that the Performance Advisor and Query Profiler identify using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowQueryLogs list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowQueryLogs list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n### View Suggested Indexes\\n\\nTo return suggested indexes for collections experiencing slow queries using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor suggestedIndexes list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor suggestedIndexes list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nTo access the Performance Advisor using the Atlas UI:\\n\\n\\n\\n\\n\\n### Click Database.\\n\\n### Click the replica set where the collection resides.\\n\\nIf the replica set resides in a sharded cluster, first click the sharded cluster containing the replica set.\\n\\n### Click Performance Advisor.\\n\\n### Select a collection from the Collections dropdown.\\n\\n### Select a time period from the Time Range dropdown.\\n\\n\\n\\n\\n\\n### Click Database.\\n\\n### Click the serverless instance.\\n\\n### Click Performance Advisor.\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nThe Performance Advisor displays up to 20 query shapes across all collections in the cluster and suggested indexes for those shapes. The Performance Advisor ranks the indexes according to their Impact, which indicates High or Medium based on the total wasted bytes read. To learn more about index ranking, see Review Index Ranking.\\n\\n## Index Suggestions\\n\\nThe Performance Advisor ranks the indexes that it suggests according to their Impact, which indicates High or Medium based on the total wasted bytes read. To learn more about how the Performance Advisor ranks indexes, see Review Index Ranking.\\n\\nTo learn how to create indexes that the Performance Advisor suggests, see Create Suggested Indexes.\\n\\n### Index Metrics\\n\\nEach index that the Performance Advisor suggests contains the following metrics. These metrics apply specifically to queries which would be improved by the index:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nExecution Count\\n\\n\\nNumber of queries executed per hour which would be improved.\\n\\n
\\nAverage Execution Time\\n\\n\\nCurrent average execution time in milliseconds for affected queries.\\n\\n
\\nAverage Query Targeting\\n\\n\\nAverage number of documents read per document returned by affected queries. A higher query targeting score indicates a greater degree of inefficiency. For more information on query targeting, see Query Targeting.\\n\\n
\\nIn Memory Sort\\n\\n\\nCurrent number of affected queries per hour that needed to be sorted in memory.\\n\\n
\\nAverage Docs Scanned\\n\\n\\nAverage number of documents scanned.\\n\\n
\\nAverage Docs Returned\\n\\n\\nAverage number of documents returned.\\n\\n
\\nAverage Object Size\\n\\n\\nAverage object size.\\n\\n
\\n\\n### Sample Queries\\n\\nFor each suggested index, the Performance Advisor shows the most commonly executed query shapes that the index would improve. For each query shape, the Performance Advisor displays the following metrics:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nExecution Count\\n\\n\\nNumber of queries executed per hour which match the query shape.\\n\\n
\\nAverage Execution Time\\n\\n\\nAverage execution time in milliseconds for queries which match the query shape.\\n\\n
\\nAverage Query Targeting\\n\\n\\nAverage number of documents read for every document returned by matching queries. A higher query targeting score indicates a greater degree of inefficiency. For more information on query targeting, see Query Targeting.\\n\\n
\\nAverage Docs Scanned\\n\\n\\nAverage number of documents scanned.\\n\\n
\\nAverage Docs Returned\\n\\n\\nAverage number of documents returned.\\n\\n
The Performance Advisor also shows each executed sample query that matches the query shape, with specific metrics for that query.\\n\\n### Query Targeting\\n\\nEach index suggestion includes an Average Query Targeting score indicating how many documents were read for every document returned for the index\\'s corresponding query shapes. A score of 1 represents very efficient query shapes because every document read matched the query and was returned with the query results. All suggested indexes represent an opportunity to improve query performance.\\n\\n### Filter Index Suggestions\\n\\nBy default, the Performance Advisor suggests indexes for all clusters in the deployment. To only show suggested indexes from a specific collection, use the Collection dropdown at the top of the Performance Advisor.\\n\\nYou can also adjust the time range the Performance Advisor takes into account when suggesting indexes by using the Time Range dropdown at the top of the Performance Advisor.\\n\\n### Limitations of Index Suggestions\\n\\n#### Timestamp Format\\n\\nThe Performance Advisor can\\'t suggest indexes for MongoDB databases configured to use the `ctime` timestamp format. As a workaround, set the timestamp format for such databases to either `iso8601-utc` or `iso8601-local`. To learn more about timestamp formats, see mongod --timeStampFormat.\\n\\n#### Log Size\\n\\nThe Performance Advisor analyzes up to 200,000 of your cluster\\'s most recent log lines.\\n\\n#### Log Quantity\\n\\nIf a cluster experiences an activity spike and generates an extremely large quantity of log messages, Atlas may stop collecting and storing new logs for a period of time.\\n\\nLog analysis rate limits apply only to the Performance Advisor UI, the Query Insights UI, the Access Tracking UI, and the Atlas Search Query Analytics UI. Downloadable log files are always complete.\\n\\n#### Time-Series Collections\\n\\nThe Performance Advisor doesn\\'t provide performance suggestions for time-series collections.\\n\\n#### User Feedback\\n\\nThe Performance Advisor includes a user feedback button for Index Suggestions. Atlas hides this button for serverless instances.\\n\\n## Create Suggested Indexes\\n\\nYou can create indexes suggested by the Performance Advisor directly within the Performance Advisor itself. When you create indexes, keep the ratio of reads to writes on the target collection in mind. Indexes come with a performance cost, but are more than worth the cost for frequent queries on large data sets. To learn more about indexing strategies, see Indexing Strategies.\\n\\n### Behavior and Limitations\\n\\n- You can\\'t create indexes through the Performance Advisor if Data Explorer is disabled for your project. You can still view the Performance Advisor recommendations, but you must create those indexes from `mongosh`.\\n\\n- You can only create one index at a time through the Performance Advisor. If you want to create more simultaneously, you can do so using the Atlas UI, a driver, or the shell\\n\\n- Atlas always creates indexes for entire clusters. If you create an index while viewing the Performance Advisor for a single shard in a sharded cluster, Atlas creates that index for the entire sharded cluster.\\n\\n### Procedure\\n\\nTo create a suggested index:\\n\\n#### For the index you want to create, click Create Index.\\n\\nThe Performance Advisor opens the Create Index dialog and prepopulates the Fields based on the index you selected.\\n\\n#### *(Optional)* Specify the index options.\\n\\n```javascript\\n{ : , ... }\\n```\\n\\nThe following options document specifies the `unique` option and the `name` for the index:\\n\\n```javascript\\n{ unique: true, name: \"myUniqueIndex\" }\\n```\\n\\n#### *(Optional)* Set the Collation options.\\n\\nUse collation to specify language-specific rules for string comparison, such as rules for lettercase and accent marks. The collation document contains a `locale` field which indicates the ICU Locale code, and may contain other fields to define collation behavior.\\n\\nThe following collation option document specifies a locale value of `fr` for a French language collation:\\n\\n```json\\n{ \"locale\": \"fr\" }\\n```\\n\\nTo review the list of locales that MongoDB collation supports, see the list of languages and locales. To learn more about collation options, including which are enabled by default for each locale, see Collation in the MongoDB manual.\\n\\n#### *(Optional)* Enable building indexes in a rolling fashion.\\n\\nRolling index builds succeed only when they meet certain conditions. To ensure your index build succeeds, avoid the following design patterns that commonly trigger a restart loop:\\n\\n- Index key exceeds the index key limit\\n\\n- Index name already exists\\n\\n- Index on more than one array field\\n\\n- Index on collection that has the maximum number of text indexes\\n\\n- Text index on collection that has the maximum number of text indexes\\n\\nthe Atlas UI doesn\\'t support building indexes with a rolling build for `M0` free clusters and `M2/M5` shared clusters. You can\\'t build indexes with a rolling build for serverless instances.\\n\\nFor workloads which cannot tolerate performance decrease due to index builds, consider building indexes in a rolling fashion.\\n\\nTo maintain cluster availability:\\n\\n- Atlas removes one node from the cluster at a time starting with a secondary.\\n\\n- More than one node can go down at a time, but Atlas always keeps a majority of the nodes online.\\n\\nAtlas automatically cancels rolling index builds that don\\'t succeed on all nodes. When a rolling index build completes on some nodes, but fails on others, Atlas cancels the build and removes the index from any nodes that it was successfully built on.\\n\\nIn the event of a rolling index build cancellation, Atlas generates an activity feed event and sends a notification email to the project owner with the following information:\\n\\n- Name of the cluster on which the rolling index build failed\\n\\n- Namespace on which the rolling index build failed\\n\\n- Project that contains the cluster and namespace\\n\\n- Organization that contains the project\\n\\n- Link to the activity feed event\\n\\nTo learn more about rebuilding indexes, see Build Indexes on Replica Sets.\\n\\nUnique\\nindex options are incompatible with building indexes in a rolling fashion. If you specify `unique` in the Options pane, Atlas rejects your configuration with an error message.\\n\\n#### Click Review.\\n\\n#### In the Confirm Operation dialog, confirm your index.\\n\\nWhen an index build completes, Atlas generates an activity feed event and sends a notification email to the project owner with the following information:\\n\\n- Completion date of the index build\\n\\n- Name of the cluster on which the index build completed\\n\\n- Namespace on which the index build completed\\n\\n- Project containing the cluster and namespace\\n\\n- Organization containing the project\\n\\n- Link to the activity feed event\\n\\n\\n\\n# Fix Query Issues\\n\\n`Query Targeting` alerts often indicate inefficient queries.\\n\\n## Alert Conditions\\n\\nYou can configure the following alert conditions in the project-level alert settings page to trigger alerts.\\n\\n`Query Targeting: Scanned Objects / Returned` alerts are triggered when the average number of documents scanned relative to the average number of documents returned server-wide across all operations during a sampling period exceeds a defined threshold. The default alert uses a 1000:1 threshold.\\n\\nIdeally, the ratio of scanned documents to returned documents should be close to 1. A high ratio negatively impacts query performance.\\n\\n`Query Targeting: Scanned / Returned` occurs if the number of index keys examined to fulfill a query relative to the actual number of returned documents meets or exceeds a user-defined threshold. This alert is not enabled by default.\\n\\nThe following mongod log entry shows statistics generated from an inefficient query:\\n\\n```json\\n COMMAND \\nplanSummary: COLLSCAN keysExamined:0\\ndocsExamined: 10000 cursorExhausted:1 numYields:234\\nnreturned:4 protocol:op_query 358ms\\n```\\n\\nThis query scanned 10,000 documents and returned only 4 for a ratio of 2500, which is highly inefficient. No index keys were examined, so MongoDB scanned all documents in the collection, known as a collection scan.\\n\\n## Common Triggers\\n\\nThe query targeting alert typically occurs when there is no index to support a query or queries or when an existing index only partially supports a query or queries.\\n\\nThe change streams cursors that the Atlas Search process (`mongot`) uses to keep Atlas Search indexes updated can contribute to the query targeting ratio and trigger query targeting alerts if the ratio is high.\\n\\n## Fix the Immediate Problem\\n\\nAdd one or more indexes to better serve the inefficient queries.\\n\\nThe Performance Advisor provides the easiest and quickest way to create an index. The Performance Advisor monitors queries that MongoDB considers slow and recommends indexes to improve performance. Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster.\\n\\nClick Create Index on a slow query for instructions on how to create the recommended index.\\n\\nIt is possible to receive a Query Targeting alert for an inefficient query without receiving index suggestions from the Performance Advisor if the query exceeds the slow query threshold and the ratio of scanned to returned documents is greater than the threshold specified in the alert.\\n\\nIn addition, you can use the following resources to determine which query generated the alert:\\n\\n- The Real-Time Performance Panel monitors and displays current network traffic and database operations on machines hosting MongoDB in your Atlas clusters.\\n\\n- The MongoDB logs maintain an account of activity, including queries, for each `mongod` instance in your Atlas clusters.\\n\\n- The cursor.explain() command for `mongosh` provides performance details for all queries.\\n\\n- Namespace Insights monitors collection-level query latency.\\n\\n- The Atlas Query Profiler records operations that Atlas considers slow when compared to average execution time for all operations on your cluster.\\n\\n## Implement a Long-Term Solution\\n\\nRefer to the following for more information on query performance:\\n\\n- MongoDB Indexing Strategies\\n\\n- Query Optimization\\n\\n- Analyze Query Plan\\n\\n## Monitor Your Progress\\n\\nAtlas provides the following methods to visualize query targeting:\\n\\n- Query Targeting metrics, which highlight high ratios of objects scanned to objects returned.\\n\\n- Namespace Insights, which monitors collection-level query latency.\\n\\n- The Query Profiler, which describes specific inefficient queries executed on the cluster.\\n\\n### Query Targeting Metrics\\n\\nYou can view historical metrics to help you visualize the query performance of your cluster. To view Query Targeting metrics in the Atlas UI:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. On the Metrics page, click the Add Chart dropdown menu and select Query Targeting.\\n\\nThe Query Targeting chart displays the following metrics for queries executed on the server:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nScanned Objects / Returned\\n\\n\\nIndicates the average number of documents examined relative to the average number of returned documents.\\n\\n
\\nScanned / Returned\\n\\n\\nIndicates the number of index keys examined to fulfill a query relative to the actual number of returned documents.\\n\\n
The change streams cursors that the Atlas Search process (`mongot`) uses to keep Atlas Search indexes updated can contribute to the query targeting ratio and trigger query targeting alerts if the ratio is high.\\n\\nIf either of these metrics exceed the user-defined threshold, Atlas generates the corresponding `Query Targeting: Scanned Objects / Returned` or `Query Targeting: Scanned / Returned` alert.\\n\\nYou can also view Query Targeting ratios of operations in real-time using the Real-Time Performance Panel.\\n\\n### Namespace Insights\\n\\nNamespace Insights monitors collection-level query latency. You can view query latency metrics and statistics for certain hosts and operation types. Manage pinned namespaces and choose up to five namespaces to show in the corresponding query latency charts.\\n\\nTo access Namespace Insights:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. Click the Query Insights tab.\\n\\n4. Click the Namespace Insights tab.\\n\\n### Query Profiler\\n\\nThe Query Profiler contains several metrics you can use to pinpoint specific inefficient queries. You can visualize up to the past 24 hours of query operations. The Query Profiler can show the Examined : Returned Ratio (index keys examined to documents returned) of logged queries, which might help you identify the queries that triggered a `Query Targeting: Scanned / Returned` alert. The chart shows the number of index keys examined to fulfill a query relative to the actual number of returned documents.\\n\\nThe default\\n`Query Targeting: Scanned Objects / Returned` alert ratio differs slightly. The ratio of the average number of documents scanned to the average number of documents returned during a sampling period triggers this alert.\\n\\nAtlas might not log the individual operations that contribute to the Query Targeting ratios due to automatically set thresholds. However, you can still use the Query Profiler and Query Targeting metrics to analyze and optimize query performance.\\n\\nTo access the Query Profiler:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. Click the Query Insights tab.\\n\\n4. Click the Query Profiler tab.\\n\\n\\n\\n# Analyze Slow Queries\\n\\nAtlas provides several tools to help analyze slow queries executed on your clusters. See the following sections for descriptions of each tool. To optimize your query performance, review the best practices for query performance.\\n\\n## Performance Advisor\\n\\nThe Performance Advisor monitors queries that MongoDB considers slow and suggests new indexes to improve query performance.\\n\\nYou can use the Performance Advisor to review the following information:\\n\\n- Index Ranking\\n\\n- Drop Index Recommendations\\n\\n## Namespace Insights\\n\\nMonitor collection-level query latency with Namespace Insights. You can view query latency metrics and statistics for certain hosts and operation types. Manage pinned namespaces and choose up to five namespaces to show in the corresponding query latency charts.\\n\\n## Query Profiler\\n\\nThe Query Profiler displays slow-running operations and their key performance statistics. You can explore a sample of historical queries for up to the last 24 hours without additional cost or performance overhead. Before you enable the Query Profiler, see Considerations.\\n\\n## Real-Time Performance Panel (RTPP)\\n\\nThe Real-Time Performance Panel identifies relevant database operations, evaluates query execution times, and shows the ratio of documents scanned to documents returned during query execution. RTPP (Real-Time Performance Panel) is enabled by default.\\n\\nTo enable or disable Real-Time Performance Panel for a project, you must have the `Project Owner` role for the project.\\n\\n## Best Practices for Query Performance\\n\\nTo optimize query performance, review the following best practices:\\n\\n- Create queries that your current indexes support to reduce the time needed to search for your results.\\n\\n- Avoid creating documents with large array fields that require a lot of processing to search and index.\\n\\n- Optimize your indexes and remove unused or inefficent indexes. Too many indexes can negatively impact write performance.\\n\\n- Consider the suggested indexes from the Performance Advisor with the highest Impact scores and lowest Average Query Targeting scores.\\n\\n- Create the indexes that the Performance Advisor suggests when they align with your Indexing Strategies.\\n\\n- The Performance Advisor cannot suggest indexes for MongoDB databases configured to use the ctime timestamp format. As a workaround, set the timestamp format for such databases to either iso8601-utc or iso8601-local.\\n\\n- Perform rolling index builds to reduce the performance impact of building indexes on replica sets and sharded clusters.\\n\\n- Drop unused, redundant, and hidden indexes to improve write performance and free storage space.\\n\\n', name='get_info_about_mongodb', id='58b5fb08-1776-49d8-a6f6-956431f77388', tool_call_id='call_sifH0mrhbpesQie4BTnQytNk')]}\n", + "{'messages': [ToolMessage(content='# Monitor and Improve Slow Queries\\n\\n*Only available on M10+ clusters and serverless instances*\\n\\nThe Performance Advisor monitors queries that MongoDB considers slow and suggests new indexes to improve query performance. The threshold for slow queries varies based on the average time of operations on your cluster to provide recommendations pertinent to your workload.\\n\\nRecommended indexes are accompanied by sample queries, grouped by query shape, that were run against a collection that would benefit from the suggested index. The Performance Advisor doesn\\'t negatively affect the performance of your Atlas clusters.\\n\\nYou can also monitor collection-level query latency with Namespace Insights and query performance with the Query Profiler.\\n\\nIf the slow query log contains consecutive `$match` stages in the aggregation pipeline, the two stages can coalesce into the first `$match` stage and result in a single `$match` stage. As a result, the query shape in the Performance Advisor might differ from the actual query you ran.\\n\\n## Common Reasons for Slow Queries\\n\\nIf a query is slow, common reasons include:\\n\\n- The query is unsupported by your current indexes.\\n\\n- Some documents in your collection have large array fields that are costly to search and index.\\n\\n- One query retrieves information from multiple collections with $lookup.\\n\\n## Required Access\\n\\nTo view collections with slow queries and see suggested indexes, you must have `Project Read Only` access or higher to the project.\\n\\nTo view field values in a sample query in the Performance Advisor, you must have `Project Data Access Read/Write` access or higher to the project.\\n\\nTo enable or disable the Atlas-managed slow operation threshold, you must have `Project Owner` access to the project. Users with `Organization Owner` access must add themselves to the project as a `Project Owner`.\\n\\n## Configure the Slow Query Threshold\\n\\nBy default, Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster. However, you can opt out of this feature and instead use a fixed slow query threshold of 100 milliseconds. You can disable the Atlas-managed slow operation threshold with the Atlas CLI, Atlas Administration API, or Atlas UI.\\n\\nAtlas clusters with MongoDB Search enabled don\\'t support the Atlas-managed slow query operation threshold.\\n\\nFor `M0`, `M2`, `M5` clusters and serverless instances, Atlas disables the Atlas-managed slow query operation threshold by default and you can\\'t enable it.\\n\\n### Disable the Atlas-Managed Slow Operation Threshold\\n\\nBy default, Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster. If you disable the Atlas-managed slow query threshold, it no longer dynamically adjusts. MongoDB defaults the fixed slow query threshold to 100 milliseconds. We don\\'t recommend that you set the fixed slow query threshold lower than 100 milliseconds.\\n\\nTo disable the Atlas-managed slow operation threshold and use a fixed threshold of 100 milliseconds:\\n\\n\\n\\n\\n\\nTo disable the Atlas-managed slow operation threshold for your project using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowOperationThreshold disable [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowOperationThreshold disable.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nSee Disable Managed Slow Operation Threshold.\\n\\n\\n\\n\\n\\nIn the Project Settings for the current project, toggle Managed Slow Operations to Off.\\n\\n\\n\\n\\n\\n### Enable the Atlas-Managed Slow Operation Threshold\\n\\nAtlas enables the Atlas-managed slow operation threshold by default. To re-enable the Atlas-managed slow operation threshold that you previously disabled:\\n\\n\\n\\n\\n\\nTo enable the Atlas-managed slow operation threshold for your project using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowOperationThreshold enable [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowOperationThreshold enable.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nSee Enable Managed Slow Operation Threshold.\\n\\n\\n\\n\\n\\nIn the Project Settings for the current project, toggle Managed Slow Operations to On.\\n\\n\\n\\n\\n\\n## Index Considerations\\n\\nIndexes improve read performance, but a large number of indexes can negatively impact write performance since indexes must be updated during writes. If your collection already has several indexes, consider this tradeoff of read and write performance when deciding whether to create new indexes. Examine whether a query for such a collection can be modified to take advantage of existing indexes, as well as whether a query occurs often enough to justify the cost of a new index.\\n\\n## Access Performance Advisor\\n\\n\\n\\n\\n\\n### View Collections with Slow Queries\\n\\nTo return up to 20 namespaces in `.` format for collections experiencing slow queries using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor namespaces list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor namespaces list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n### View Slow Query Logs\\n\\nTo return query log line items for slow queries that the Performance Advisor and Query Profiler identify using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor slowQueryLogs list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor slowQueryLogs list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n### View Suggested Indexes\\n\\nTo return suggested indexes for collections experiencing slow queries using the Atlas CLI, run the following command:\\n\\n```sh\\n\\natlas performanceAdvisor suggestedIndexes list [options]\\n\\n```\\n\\nTo learn more about the command syntax and parameters, see the Atlas CLI documentation for atlas performanceAdvisor suggestedIndexes list.\\n\\n- Install the Atlas CLI\\n\\n- Connect to the Atlas CLI\\n\\n\\n\\n\\n\\nTo access the Performance Advisor using the Atlas UI:\\n\\n\\n\\n\\n\\n### Click Database.\\n\\n### Click the replica set where the collection resides.\\n\\nIf the replica set resides in a sharded cluster, first click the sharded cluster containing the replica set.\\n\\n### Click Performance Advisor.\\n\\n### Select a collection from the Collections dropdown.\\n\\n### Select a time period from the Time Range dropdown.\\n\\n\\n\\n\\n\\n### Click Database.\\n\\n### Click the serverless instance.\\n\\n### Click Performance Advisor.\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nThe Performance Advisor displays up to 20 query shapes across all collections in the cluster and suggested indexes for those shapes. The Performance Advisor ranks the indexes according to their Impact, which indicates High or Medium based on the total wasted bytes read. To learn more about index ranking, see Review Index Ranking.\\n\\n## Index Suggestions\\n\\nThe Performance Advisor ranks the indexes that it suggests according to their Impact, which indicates High or Medium based on the total wasted bytes read. To learn more about how the Performance Advisor ranks indexes, see Review Index Ranking.\\n\\nTo learn how to create indexes that the Performance Advisor suggests, see Create Suggested Indexes.\\n\\n### Index Metrics\\n\\nEach index that the Performance Advisor suggests contains the following metrics. These metrics apply specifically to queries which would be improved by the index:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nExecution Count\\n\\n\\nNumber of queries executed per hour which would be improved.\\n\\n
\\nAverage Execution Time\\n\\n\\nCurrent average execution time in milliseconds for affected queries.\\n\\n
\\nAverage Query Targeting\\n\\n\\nAverage number of documents read per document returned by affected queries. A higher query targeting score indicates a greater degree of inefficiency. For more information on query targeting, see Query Targeting.\\n\\n
\\nIn Memory Sort\\n\\n\\nCurrent number of affected queries per hour that needed to be sorted in memory.\\n\\n
\\nAverage Docs Scanned\\n\\n\\nAverage number of documents scanned.\\n\\n
\\nAverage Docs Returned\\n\\n\\nAverage number of documents returned.\\n\\n
\\nAverage Object Size\\n\\n\\nAverage object size.\\n\\n
\\n\\n### Sample Queries\\n\\nFor each suggested index, the Performance Advisor shows the most commonly executed query shapes that the index would improve. For each query shape, the Performance Advisor displays the following metrics:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nExecution Count\\n\\n\\nNumber of queries executed per hour which match the query shape.\\n\\n
\\nAverage Execution Time\\n\\n\\nAverage execution time in milliseconds for queries which match the query shape.\\n\\n
\\nAverage Query Targeting\\n\\n\\nAverage number of documents read for every document returned by matching queries. A higher query targeting score indicates a greater degree of inefficiency. For more information on query targeting, see Query Targeting.\\n\\n
\\nAverage Docs Scanned\\n\\n\\nAverage number of documents scanned.\\n\\n
\\nAverage Docs Returned\\n\\n\\nAverage number of documents returned.\\n\\n
The Performance Advisor also shows each executed sample query that matches the query shape, with specific metrics for that query.\\n\\n### Query Targeting\\n\\nEach index suggestion includes an Average Query Targeting score indicating how many documents were read for every document returned for the index\\'s corresponding query shapes. A score of 1 represents very efficient query shapes because every document read matched the query and was returned with the query results. All suggested indexes represent an opportunity to improve query performance.\\n\\n### Filter Index Suggestions\\n\\nBy default, the Performance Advisor suggests indexes for all clusters in the deployment. To only show suggested indexes from a specific collection, use the Collection dropdown at the top of the Performance Advisor.\\n\\nYou can also adjust the time range the Performance Advisor takes into account when suggesting indexes by using the Time Range dropdown at the top of the Performance Advisor.\\n\\n### Limitations of Index Suggestions\\n\\n#### Timestamp Format\\n\\nThe Performance Advisor can\\'t suggest indexes for MongoDB databases configured to use the `ctime` timestamp format. As a workaround, set the timestamp format for such databases to either `iso8601-utc` or `iso8601-local`. To learn more about timestamp formats, see mongod --timeStampFormat.\\n\\n#### Log Size\\n\\nThe Performance Advisor analyzes up to 200,000 of your cluster\\'s most recent log lines.\\n\\n#### Log Quantity\\n\\nIf a cluster experiences an activity spike and generates an extremely large quantity of log messages, Atlas may stop collecting and storing new logs for a period of time.\\n\\nLog analysis rate limits apply only to the Performance Advisor UI, the Query Insights UI, the Access Tracking UI, and the MongoDB Search Query Analytics UI. Downloadable log files are always complete.\\n\\n#### Time-Series Collections\\n\\nThe Performance Advisor doesn\\'t provide performance suggestions for time-series collections.\\n\\n#### User Feedback\\n\\nThe Performance Advisor includes a user feedback button for Index Suggestions. Atlas hides this button for serverless instances.\\n\\n## Create Suggested Indexes\\n\\nYou can create indexes suggested by the Performance Advisor directly within the Performance Advisor itself. When you create indexes, keep the ratio of reads to writes on the target collection in mind. Indexes come with a performance cost, but are more than worth the cost for frequent queries on large data sets. To learn more about indexing strategies, see Indexing Strategies.\\n\\n### Behavior and Limitations\\n\\n- You can\\'t create indexes through the Performance Advisor if Data Explorer is disabled for your project. You can still view the Performance Advisor recommendations, but you must create those indexes from `mongosh`.\\n\\n- You can only create one index at a time through the Performance Advisor. If you want to create more simultaneously, you can do so using the Atlas UI, a driver, or the shell\\n\\n- Atlas always creates indexes for entire clusters. If you create an index while viewing the Performance Advisor for a single shard in a sharded cluster, Atlas creates that index for the entire sharded cluster.\\n\\n### Procedure\\n\\nTo create a suggested index:\\n\\n#### For the index you want to create, click Create Index.\\n\\nThe Performance Advisor opens the Create Index dialog and prepopulates the Fields based on the index you selected.\\n\\n#### *(Optional)* Specify the index options.\\n\\n```javascript\\n{ : , ... }\\n```\\n\\nThe following options document specifies the `unique` option and the `name` for the index:\\n\\n```javascript\\n{ unique: true, name: \"myUniqueIndex\" }\\n```\\n\\n#### *(Optional)* Set the Collation options.\\n\\nUse collation to specify language-specific rules for string comparison, such as rules for lettercase and accent marks. The collation document contains a `locale` field which indicates the ICU Locale code, and may contain other fields to define collation behavior.\\n\\nThe following collation option document specifies a locale value of `fr` for a French language collation:\\n\\n```json\\n{ \"locale\": \"fr\" }\\n```\\n\\nTo review the list of locales that MongoDB collation supports, see the list of languages and locales. To learn more about collation options, including which are enabled by default for each locale, see Collation in the MongoDB manual.\\n\\n#### *(Optional)* Enable building indexes in a rolling fashion.\\n\\nRolling index builds succeed only when they meet certain conditions. To ensure your index build succeeds, avoid the following design patterns that commonly trigger a restart loop:\\n\\n- Index key exceeds the index key limit\\n\\n- Index name already exists\\n\\n- Index on more than one array field\\n\\n- Index on collection that has the maximum number of text indexes\\n\\n- Text index on collection that has the maximum number of text indexes\\n\\nthe Atlas UI doesn\\'t support building indexes with a rolling build for `M0` free clusters and `M2/M5` shared clusters. You can\\'t build indexes with a rolling build for serverless instances.\\n\\nFor workloads which cannot tolerate performance decrease due to index builds, consider building indexes in a rolling fashion.\\n\\nTo maintain cluster availability:\\n\\n- Atlas removes one node from the cluster at a time starting with a secondary.\\n\\n- More than one node can go down at a time, but Atlas always keeps a majority of the nodes online.\\n\\nAtlas automatically cancels rolling index builds that don\\'t succeed on all nodes. When a rolling index build completes on some nodes, but fails on others, Atlas cancels the build and removes the index from any nodes that it was successfully built on.\\n\\nIn the event of a rolling index build cancellation, Atlas generates an activity feed event and sends a notification email to the project owner with the following information:\\n\\n- Name of the cluster on which the rolling index build failed\\n\\n- Namespace on which the rolling index build failed\\n\\n- Project that contains the cluster and namespace\\n\\n- Organization that contains the project\\n\\n- Link to the activity feed event\\n\\nTo learn more about rebuilding indexes, see Build Indexes on Replica Sets.\\n\\nUnique\\nindex options are incompatible with building indexes in a rolling fashion. If you specify `unique` in the Options pane, Atlas rejects your configuration with an error message.\\n\\n#### Click Review.\\n\\n#### In the Confirm Operation dialog, confirm your index.\\n\\nWhen an index build completes, Atlas generates an activity feed event and sends a notification email to the project owner with the following information:\\n\\n- Completion date of the index build\\n\\n- Name of the cluster on which the index build completed\\n\\n- Namespace on which the index build completed\\n\\n- Project containing the cluster and namespace\\n\\n- Organization containing the project\\n\\n- Link to the activity feed event\\n\\n\\n\\n# Fix Query Issues\\n\\n`Query Targeting` alerts often indicate inefficient queries.\\n\\n## Alert Conditions\\n\\nYou can configure the following alert conditions in the project-level alert settings page to trigger alerts.\\n\\n`Query Targeting: Scanned Objects / Returned` alerts are triggered when the average number of documents scanned relative to the average number of documents returned server-wide across all operations during a sampling period exceeds a defined threshold. The default alert uses a 1000:1 threshold.\\n\\nIdeally, the ratio of scanned documents to returned documents should be close to 1. A high ratio negatively impacts query performance.\\n\\n`Query Targeting: Scanned / Returned` occurs if the number of index keys examined to fulfill a query relative to the actual number of returned documents meets or exceeds a user-defined threshold. This alert is not enabled by default.\\n\\nThe following mongod log entry shows statistics generated from an inefficient query:\\n\\n```json\\n COMMAND \\nplanSummary: COLLSCAN keysExamined:0\\ndocsExamined: 10000 cursorExhausted:1 numYields:234\\nnreturned:4 protocol:op_query 358ms\\n```\\n\\nThis query scanned 10,000 documents and returned only 4 for a ratio of 2500, which is highly inefficient. No index keys were examined, so MongoDB scanned all documents in the collection, known as a collection scan.\\n\\n## Common Triggers\\n\\nThe query targeting alert typically occurs when there is no index to support a query or queries or when an existing index only partially supports a query or queries.\\n\\nThe change streams cursors that the MongoDB Search process (`mongot`) uses to keep MongoDB Search indexes updated can contribute to the query targeting ratio and trigger query targeting alerts if the ratio is high.\\n\\n## Fix the Immediate Problem\\n\\nAdd one or more indexes to better serve the inefficient queries.\\n\\nThe Performance Advisor provides the easiest and quickest way to create an index. The Performance Advisor monitors queries that MongoDB considers slow and recommends indexes to improve performance. Atlas dynamically adjusts your slow query threshold based on the execution time of operations across your cluster.\\n\\nClick Create Index on a slow query for instructions on how to create the recommended index.\\n\\nIt is possible to receive a Query Targeting alert for an inefficient query without receiving index suggestions from the Performance Advisor if the query exceeds the slow query threshold and the ratio of scanned to returned documents is greater than the threshold specified in the alert.\\n\\nIn addition, you can use the following resources to determine which query generated the alert:\\n\\n- The Real-Time Performance Panel monitors and displays current network traffic and database operations on machines hosting MongoDB in your Atlas clusters.\\n\\n- The MongoDB logs maintain an account of activity, including queries, for each `mongod` instance in your Atlas clusters.\\n\\n- The cursor.explain() command for `mongosh` provides performance details for all queries.\\n\\n- Namespace Insights monitors collection-level query latency.\\n\\n- The Atlas Query Profiler records operations that Atlas considers slow when compared to average execution time for all operations on your cluster.\\n\\n## Implement a Long-Term Solution\\n\\nRefer to the following for more information on query performance:\\n\\n- MongoDB Indexing Strategies\\n\\n- Query Optimization\\n\\n- Analyze Query Plan\\n\\n## Monitor Your Progress\\n\\nAtlas provides the following methods to visualize query targeting:\\n\\n- Query Targeting metrics, which highlight high ratios of objects scanned to objects returned.\\n\\n- Namespace Insights, which monitors collection-level query latency.\\n\\n- The Query Profiler, which describes specific inefficient queries executed on the cluster.\\n\\n### Query Targeting Metrics\\n\\nYou can view historical metrics to help you visualize the query performance of your cluster. To view Query Targeting metrics in the Atlas UI:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. On the Metrics page, click the Add Chart dropdown menu and select Query Targeting.\\n\\nThe Query Targeting chart displays the following metrics for queries executed on the server:\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n
\\nMetric\\n\\n\\nDescription\\n\\n
\\nScanned Objects / Returned\\n\\n\\nIndicates the average number of documents examined relative to the average number of returned documents.\\n\\n
\\nScanned / Returned\\n\\n\\nIndicates the number of index keys examined to fulfill a query relative to the actual number of returned documents.\\n\\n
The change streams cursors that the MongoDB Search process (`mongot`) uses to keep MongoDB Search indexes updated can contribute to the query targeting ratio and trigger query targeting alerts if the ratio is high.\\n\\nIf either of these metrics exceed the user-defined threshold, Atlas generates the corresponding `Query Targeting: Scanned Objects / Returned` or `Query Targeting: Scanned / Returned` alert.\\n\\nYou can also view Query Targeting ratios of operations in real-time using the Real-Time Performance Panel.\\n\\n### Namespace Insights\\n\\nNamespace Insights monitors collection-level query latency. You can view query latency metrics and statistics for certain hosts and operation types. Manage pinned namespaces and choose up to five namespaces to show in the corresponding query latency charts.\\n\\nTo access Namespace Insights:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. Click the Query Insights tab.\\n\\n4. Click the Namespace Insights tab.\\n\\n### Query Profiler\\n\\nThe Query Profiler contains several metrics you can use to pinpoint specific inefficient queries. You can visualize up to the past 24 hours of query operations. The Query Profiler can show the Examined : Returned Ratio (index keys examined to documents returned) of logged queries, which might help you identify the queries that triggered a `Query Targeting: Scanned / Returned` alert. The chart shows the number of index keys examined to fulfill a query relative to the actual number of returned documents.\\n\\nThe default\\n`Query Targeting: Scanned Objects / Returned` alert ratio differs slightly. The ratio of the average number of documents scanned to the average number of documents returned during a sampling period triggers this alert.\\n\\nAtlas might not log the individual operations that contribute to the Query Targeting ratios due to automatically set thresholds. However, you can still use the Query Profiler and Query Targeting metrics to analyze and optimize query performance.\\n\\nTo access the Query Profiler:\\n\\n1. Click Database in the top-left corner of Atlas.\\n\\n2. Click View Monitoring on the dashboard for the cluster.\\n\\n3. Click the Query Insights tab.\\n\\n4. Click the Query Profiler tab.\\n\\n\\n\\n# Analyze Slow Queries\\n\\nAtlas provides several tools to help analyze slow queries executed on your clusters. See the following sections for descriptions of each tool. To optimize your query performance, review the best practices for query performance.\\n\\n## Performance Advisor\\n\\nThe Performance Advisor monitors queries that MongoDB considers slow and suggests new indexes to improve query performance.\\n\\nYou can use the Performance Advisor to review the following information:\\n\\n- Index Ranking\\n\\n- Drop Index Recommendations\\n\\n## Namespace Insights\\n\\nMonitor collection-level query latency with Namespace Insights. You can view query latency metrics and statistics for certain hosts and operation types. Manage pinned namespaces and choose up to five namespaces to show in the corresponding query latency charts.\\n\\n## Query Profiler\\n\\nThe Query Profiler displays slow-running operations and their key performance statistics. You can explore a sample of historical queries for up to the last 24 hours without additional cost or performance overhead. Before you enable the Query Profiler, see Considerations.\\n\\n## Real-Time Performance Panel (RTPP)\\n\\nThe Real-Time Performance Panel identifies relevant database operations, evaluates query execution times, and shows the ratio of documents scanned to documents returned during query execution. RTPP (Real-Time Performance Panel) is enabled by default.\\n\\nTo enable or disable Real-Time Performance Panel for a project, you must have the `Project Owner` role for the project.\\n\\n## Best Practices for Query Performance\\n\\nTo optimize query performance, review the following best practices:\\n\\n- Create queries that your current indexes support to reduce the time needed to search for your results.\\n\\n- Avoid creating documents with large array fields that require a lot of processing to search and index.\\n\\n- Optimize your indexes and remove unused or inefficent indexes. Too many indexes can negatively impact write performance.\\n\\n- Consider the suggested indexes from the Performance Advisor with the highest Impact scores and lowest Average Query Targeting scores.\\n\\n- Create the indexes that the Performance Advisor suggests when they align with your Indexing Strategies.\\n\\n- The Performance Advisor cannot suggest indexes for MongoDB databases configured to use the ctime timestamp format. As a workaround, set the timestamp format for such databases to either iso8601-utc or iso8601-local.\\n\\n- Perform rolling index builds to reduce the performance impact of building indexes on replica sets and sharded clusters.\\n\\n- Drop unused, redundant, and hidden indexes to improve write performance and free storage space.\\n\\n', name='get_info_about_mongodb', id='58b5fb08-1776-49d8-a6f6-956431f77388', tool_call_id='call_sifH0mrhbpesQie4BTnQytNk')]}\n", "Node agent:\n", "{'messages': [AIMessage(content=\"To improve slow queries in MongoDB, you can follow these steps:\\n\\n### 1. **Analyze the Problem**\\n - Use the **Performance Advisor** to monitor slow queries and get index recommendations.\\n - Check the **Query Profiler** to identify slow-running operations and their key performance statistics.\\n - Use **Namespace Insights** to monitor collection-level query latency.\\n - Analyze the **Real-Time Performance Panel (RTPP)** for real-time query execution metrics.\\n\\n### 2. **Common Causes of Slow Queries**\\n - Queries are not supported by existing indexes.\\n - Large array fields in documents that are costly to search and index.\\n - Queries involving multiple collections using `$lookup`.\\n\\n### 3. **Fix Immediate Issues**\\n - **Add Indexes**: Create indexes to support inefficient queries. The Performance Advisor provides suggestions for indexes with high impact.\\n - **Optimize Queries**: Ensure queries are designed to utilize existing indexes effectively.\\n - **Avoid Collection Scans**: If a query scans all documents in a collection (COLLSCAN), it indicates the need for an index.\\n\\n### 4. **Long-Term Solutions**\\n - **Optimize Indexes**: Remove unused or redundant indexes to improve write performance.\\n - **Monitor Query Targeting**: Keep the ratio of documents scanned to documents returned close to 1.\\n - **Avoid Large Arrays**: Minimize the use of large array fields in documents.\\n\\n### 5. **Best Practices**\\n - Use the **Query Targeting Metrics** to identify inefficiencies.\\n - Perform **rolling index builds** to minimize performance impact on replica sets and sharded clusters.\\n - Drop unused or hidden indexes to free up storage and improve write performance.\\n\\n### 6. **Tools for Monitoring and Optimization**\\n - **Performance Advisor**: Suggests indexes and provides query insights.\\n - **Query Profiler**: Displays slow-running queries and their statistics.\\n - **Namespace Insights**: Monitors query latency at the collection level.\\n - **Real-Time Performance Panel**: Provides real-time metrics for query execution.\\n\\nBy following these steps and utilizing MongoDB's built-in tools, you can significantly improve the performance of slow queries.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 451, 'prompt_tokens': 5355, 'total_tokens': 5806, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-11-20', 'system_fingerprint': 'fp_d924043139', 'finish_reason': 'stop', 'logprobs': None}, id='run-ad3b553a-e5e6-4c9e-9246-d6e0f7286abb-0', usage_metadata={'input_tokens': 5355, 'output_tokens': 451, 'total_tokens': 5806, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}\n", "---FINAL ANSWER---\n", diff --git a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb index 8b6a65f8..ebf9d143 100644 --- a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb +++ b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb @@ -531,7 +531,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Step 5: Create Atlas Search indexes" + "## Step 5: Create MongoDB Search indexes" ] }, { diff --git a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb index 22e7992f..5e2a6cf1 100644 --- a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb +++ b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb @@ -332,7 +332,7 @@ "id": "I0vBccQaj-o6" }, "source": [ - "### Create Atlas Search Index" + "### Create MongoDB Search Index" ] }, { diff --git a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb index cc4128a8..aad21719 100644 --- a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb +++ b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb @@ -667,7 +667,7 @@ "source": [ "# Prepare MongoDB Atlas vector store\n", "\n", - "Run the following code to create the Atlas Vector Search index and insert some vectorised employee records for our database." + "Run the following code to create the MongoDB Vector Search index and insert some vectorised employee records for our database." ] }, { @@ -5446,9 +5446,9 @@ "id": "EVb8Ia6LCv3B" }, "source": [ - "### MongoDB Atlas Vector Search with Gemini 2.0\n", + "### MongoDB MongoDB Vector Search with Gemini 2.0\n", "\n", - "A vector similarity search implementation that leverages MongoDB Atlas Vector Search and Google's Gemini 2.0 embeddings to perform semantic document searches, returning the k-most similar documents based on query embedding comparison." + "A vector similarity search implementation that leverages MongoDB MongoDB Vector Search and Google's Gemini 2.0 embeddings to perform semantic document searches, returning the k-most similar documents based on query embedding comparison." ] }, { @@ -5477,7 +5477,7 @@ " )\n", "def atlas_search(query: str, k: int = 5):\n", " \"\"\"\n", - " Perform a vector similarity search using MongoDB Atlas Vector Search.\n", + " Perform a vector similarity search using MongoDB MongoDB Vector Search.\n", " \"\"\"\n", " try:\n", "\n", diff --git a/notebooks/agents/Pragmatic_LLM_Application_Introduction_From_RAG_to_Agents_with_MongoDB.ipynb b/notebooks/agents/Pragmatic_LLM_Application_Introduction_From_RAG_to_Agents_with_MongoDB.ipynb index 94c9c744..8f162f3b 100644 --- a/notebooks/agents/Pragmatic_LLM_Application_Introduction_From_RAG_to_Agents_with_MongoDB.ipynb +++ b/notebooks/agents/Pragmatic_LLM_Application_Introduction_From_RAG_to_Agents_with_MongoDB.ipynb @@ -1612,7 +1612,7 @@ "source": [ "## 1.4 Vector Index Creation\n", "\n", - "- [Create an Atlas Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", + "- [Create an MongoDB Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", "\n", "- If you are following this notebook ensure that you are creating a vector search index for the right database(demo_company_employees) and collection(employees_records)\n", "\n", diff --git a/notebooks/agents/hr_agentic_chatbot_with_langgraph_claude.ipynb b/notebooks/agents/hr_agentic_chatbot_with_langgraph_claude.ipynb index f1348227..aa655650 100644 --- a/notebooks/agents/hr_agentic_chatbot_with_langgraph_claude.ipynb +++ b/notebooks/agents/hr_agentic_chatbot_with_langgraph_claude.ipynb @@ -1544,7 +1544,7 @@ "source": [ "1.4 Vector Index Creation\n", "\n", - "- [Create an Atlas Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", + "- [Create an MongoDB Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", "\n", "- If you are following this notebook ensure that you are creating a vector search index for the right database(demo_company_employees) and collection(employees_records)\n", "\n", diff --git a/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb b/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb index 70824a08..c08162a6 100644 --- a/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb +++ b/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb @@ -1936,7 +1936,7 @@ "source": [ "Retrieving data from MongoDB involves leveraging both traditional queries and vector search. For traditional queries, the pymongo library provides methods like `find_one()` and `find()` to retrieve documents based on specific criteria.\n", "\n", - "MongoDB Atlas Vector Search is used for semantic-based retrieval. This feature allows for efficient similarity searches using the pre-calculated product embeddings. The system can retrieve products that are semantically similar to the query by querying the' embedding' field with a target embedding.\n", + "MongoDB MongoDB Vector Search is used for semantic-based retrieval. This feature allows for efficient similarity searches using the pre-calculated product embeddings. The system can retrieve products that are semantically similar to the query by querying the' embedding' field with a target embedding.\n", "\n", "This approach significantly enhances the AI sales assistant's ability to understand user intent and offer relevant product suggestions. Variables like `embedding_field_name` and `vector_search_index_name` are used to configure and interact with the vector search index within MongoDB, ensuring efficient retrieval of similar products.\n" ] @@ -1960,7 +1960,7 @@ "source": [ "# The field containing the text embeddings on each document\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB Atlas Vector Search index name\n", + "# MongoDB MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, diff --git a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb index ba5e382a..035d43db 100644 --- a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb +++ b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb @@ -23,7 +23,7 @@ "**Key Features:**\n", "\n", "* **MongoDB as a Tool Registry:** Instead of hardcoding tool definitions within the agent, this application stores tool metadata (name, description, parameters) directly in a MongoDB collection.\n", - "* **MongoDB Atlas Vector Search for Tool Discovery:** LlamaIndex uses the vector embeddings of tool descriptions stored in MongoDB to perform semantic searches based on user queries. This allows the agent to dynamically discover and select the most relevant tools for a given task.\n", + "* **MongoDB MongoDB Vector Search for Tool Discovery:** LlamaIndex uses the vector embeddings of tool descriptions stored in MongoDB to perform semantic searches based on user queries. This allows the agent to dynamically discover and select the most relevant tools for a given task.\n", "* **LlamaIndex Agent with Function Calling:** The LlamaIndex agent is configured to use the retrieved tool definitions from MongoDB to enable function calling. This means the agent can understand the user's intent and execute the appropriate Python function (tool) stored in the application.\n", "* **Data Storage in MongoDB:** Besides tool definitions, the application also uses separate MongoDB collections to store operational data like customer orders, return requests, and policy documents.\n", "* **Integration with External Services:** The tools defined and managed in MongoDB can interact with external services (e.g., fetching real-time data, processing requests) or perform operations on the data stored within MongoDB itself (e.g., looking up order details, creating return requests).\n", @@ -48,7 +48,7 @@ "- `llama-index-core`: The core LlamaIndex library.\n", "- `llama-index-llms-openai`: LlamaIndex integration with OpenAI LLMs.\n", "- `llama-index-embeddings-voyageai`: LlamaIndex integration with VoyageAI embeddings.\n", - "- `llama-index-vector-stores-mongodb`: LlamaIndex integration with MongoDB Atlas Vector Search.\n", + "- `llama-index-vector-stores-mongodb`: LlamaIndex integration with MongoDB MongoDB Vector Search.\n", "- `llama-index-readers-file`: LlamaIndex file readers." ] }, diff --git a/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb b/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb index 8d8e91b0..81a6b027 100644 --- a/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb +++ b/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb @@ -6,9 +6,9 @@ "id": "Pff8TULfBfmW" }, "source": [ - "# MongoDB Atlas Vector Search with VoyageAI Embeddings for Sports Scores and Stories\n", + "# MongoDB MongoDB Vector Search with VoyageAI Embeddings for Sports Scores and Stories\n", "\n", - "This notebook demonstrates how to use VoyageAI embeddings with MongoDB Atlas Vector Search for retrieving relevant sports scores and stories based on user queries." + "This notebook demonstrates how to use VoyageAI embeddings with MongoDB MongoDB Vector Search for retrieving relevant sports scores and stories based on user queries." ] }, { diff --git a/notebooks/agents/smolagents_hf_with_mongodb.ipynb b/notebooks/agents/smolagents_hf_with_mongodb.ipynb index 80bc9693..489111c5 100644 --- a/notebooks/agents/smolagents_hf_with_mongodb.ipynb +++ b/notebooks/agents/smolagents_hf_with_mongodb.ipynb @@ -1273,9 +1273,9 @@ "id": "YL83jmaPB-iu" }, "source": [ - "## Vector Search based RAG with Atlas Search\n", + "## Vector Search based RAG with MongoDB Search\n", "\n", - "Vector search allows us to find relevant documents based on the semantic meaning of the query rather than just keyword matching. In this section, we demonstrate how to build a Retrieval-Augmented Generation (RAG) agent that leverages MongoDB Atlas Search's vector search capabilities.\n", + "Vector search allows us to find relevant documents based on the semantic meaning of the query rather than just keyword matching. In this section, we demonstrate how to build a Retrieval-Augmented Generation (RAG) agent that leverages MongoDB MongoDB Search's vector search capabilities.\n", "\n", "The RAG agent uses the `vector_search_rentals` tool to find relevant documents based on the query's embeddings. This approach enhances the search results by considering the context and meaning of the query, providing more accurate and relevant results.\n", "\n", @@ -1390,7 +1390,7 @@ " response = embedding(model=\"text-embedding-3-small\", input=[query])\n", " query_embedding = response[\"data\"][0][\"embedding\"]\n", "\n", - " # Perform vector search using Atlas Search\n", + " # Perform vector search using MongoDB Search\n", " pipeline = [\n", " {\n", " \"$vectorSearch\": {\n", @@ -2432,7 +2432,7 @@ "\n", "* **Robust Tool Design:** The tools now incorporate error handling, providing more informative feedback to the user in case of issues. The exclusion of embedding fields from queries enhances performance and readability of results.\n", "* **Enhanced Query Handling:** The inclusion of an initial projection stage in the aggregation pipeline, specifically designed to remove embedding fields (`text_embeddings` and `image_embeddings`) prior to other stages, ensures more efficient query execution and smaller response sizes. The use of `json.loads()` ensures that the pipeline string received from the LLM is correctly parsed.\n", - "Atlas Search excels at finding relevant documents quickly, thanks to its vector search capabilities. This is particularly beneficial for large datasets where traditional keyword search may be insufficient.\n", + "MongoDB Search excels at finding relevant documents quickly, thanks to its vector search capabilities. This is particularly beneficial for large datasets where traditional keyword search may be insufficient.\n", "* **Improved User Experience:** Clearer tool documentation and example usage further enhance the user's ability to interact with the agent and interpret results.\n", "* **Practical Application:** The demonstration showcases a practical application for analyzing data within a MongoDB Atlas database using an LLM-powered agent.\n", "\n", diff --git a/notebooks/agents/video_intelligence_agent.ipynb b/notebooks/agents/video_intelligence_agent.ipynb index 6c109bda..6eeae8c1 100644 --- a/notebooks/agents/video_intelligence_agent.ipynb +++ b/notebooks/agents/video_intelligence_agent.ipynb @@ -1163,7 +1163,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "The code below is a helper wraps MongoDB Atlas Search index creation: \n", + "The code below is a helper wraps MongoDB MongoDB Search index creation: \n", "- given a collection, an index-definition dict, and a name, \n", "- it builds a SearchIndexModel, calls create_search_index, \n", "- and returns the result—printing success or catching errors and returning None.\n" @@ -1369,7 +1369,7 @@ "\n", "By tuning `numCandidates` and `limit`, you can balance throughput, resource usage, and retrieval fidelity for your specific dataset.\n", "\n", - "[1]: https://www.mongodb.com/docs/drivers/rust/v3.1/fundamentals/aggregation/vector-search/ \"Atlas Vector Search - Rust Driver v3.1 - MongoDB Docs\"\n", + "[1]: https://www.mongodb.com/docs/drivers/rust/v3.1/fundamentals/aggregation/vector-search/ \"MongoDB Vector Search - Rust Driver v3.1 - MongoDB Docs\"\n", "[2]: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-stage/ \"Run Vector Search Queries - Atlas - MongoDB Docs\"\n" ] }, @@ -1615,7 +1615,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "**`hybrid_search`** combines semantic vector search and traditional text search in MongoDB using the `$rankFusion` operator. It first converts the `user_query` into an embedding via `get_voyage_embedding`, then defines two sub-pipelines—one using `$vectorSearch` on the specified `vector_search_index_name`, the other using Atlas Search’s `$search` on `text_search_index_name`. These pipelines each retrieve up to 20 candidates, which are then merged and re-ranked according to specified weights, producing a unified list of the top-`top_n` results enriched with detailed scoring information.\n", + "**`hybrid_search`** combines semantic vector search and traditional text search in MongoDB using the `$rankFusion` operator. It first converts the `user_query` into an embedding via `get_voyage_embedding`, then defines two sub-pipelines—one using `$vectorSearch` on the specified `vector_search_index_name`, the other using MongoDB Search’s `$search` on `text_search_index_name`. These pipelines each retrieve up to 20 candidates, which are then merged and re-ranked according to specified weights, producing a unified list of the top-`top_n` results enriched with detailed scoring information.\n", "\n", "The `$rankFusion` stage supports key parameters for fine-tuning relevance blending:\n", "\n", diff --git a/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb b/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb index 9006ac1d..b78c586a 100644 --- a/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb +++ b/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb @@ -688,7 +688,7 @@ "A vector search index organizes high-dimensional embeddings for efficient similarity searches. Without it, finding similar vectors would require exhaustive comparisons against every vector in your database—becoming impractical at scale. These indexes enable fast semantic searches by organizing vectors based on their geometric relationships, essential for RAG, recommendation systems, and semantic search.\n", "\n", "#### Understanding HNSW (Hierarchical Navigable Small Worlds)\n", - "HNSW is MongoDB Atlas Vector Search's algorithm of choice for approximate nearest neighbor searches:\n", + "HNSW is MongoDB MongoDB Vector Search's algorithm of choice for approximate nearest neighbor searches:\n", "- Creates a multi-layered graph connecting vectors to their nearest neighbors\n", "- Enables logarithmic search complexity through a hierarchical approach\n", "- Balances speed and accuracy via configurable parameters\n", @@ -1035,7 +1035,7 @@ " paths = [paths]\n", "\n", " # Define the text search stage using MongoDB's $search operator.\n", - " # This is part of Atlas Search and provides more powerful text search capabilities\n", + " # This is part of MongoDB Search and provides more powerful text search capabilities\n", " # than MongoDB's standard text index.\n", " text_search_stage = {\n", " \"$search\": {\n", @@ -1264,7 +1264,7 @@ "### Step 10: Define Hybrid Search Function\n", "\n", "\n", - "The `hybrid_search_with_mongodb` function conducts a hybrid search on a MongoDB Atlas collection that combines a vector search and a full-text search using Atlas Search.\n", + "The `hybrid_search_with_mongodb` function conducts a hybrid search on a MongoDB Atlas collection that combines a vector search and a full-text search using MongoDB Search.\n", "\n", "In the MongoDB hybrid search function, there are two weights:\n", "\n", @@ -1338,7 +1338,7 @@ "):\n", " \"\"\"\n", " Conduct a hybrid search on a MongoDB Atlas collection that combines a vector search\n", - " and a full-text search using Atlas Search.\n", + " and a full-text search using MongoDB Search.\n", "\n", " Args:\n", " user_query (str): The user's query string.\n", @@ -1419,7 +1419,7 @@ " \"$unionWith\": {\n", " \"coll\": collection_name, # Collection to search\n", " \"pipeline\": [\n", - " # Perform full text search using Atlas Search\n", + " # Perform full text search using MongoDB Search\n", " {\n", " \"$search\": {\n", " \"index\": text_search_index_name, # Name of the text search index\n", diff --git a/notebooks/performance_guidance/README.md b/notebooks/performance_guidance/README.md index 860d4cd6..0fc0b79a 100644 --- a/notebooks/performance_guidance/README.md +++ b/notebooks/performance_guidance/README.md @@ -1,8 +1,8 @@ -Performance guidance showing how MongoDB Atlas Vector Search compares against other vector databases. +Performance guidance showing how MongoDB MongoDB Vector Search compares against other vector databases. -Jupyter Notebooks comparing MongoDB Atlas Vector Search with other vector databases and search engines. +Jupyter Notebooks comparing MongoDB MongoDB Vector Search with other vector databases and search engines. | Title | Notebook | |-------|-------| -| Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB Atlas Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb) | -| AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB Atlas Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb) | +| Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb) | +| AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb) | diff --git a/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb b/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb index 622cf095..c29d7f83 100644 --- a/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb +++ b/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb @@ -6,7 +6,7 @@ "id": "0ioUyhIh4VMe" }, "source": [ - "# Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB Atlas Vector Search\n", + "# Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB MongoDB Vector Search\n", "\n", "\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb)\n", @@ -1049,7 +1049,7 @@ "id": "KZTYPIn34VMi" }, "source": [ - "## Part 3: Search with MongoDB Atlas Vector Search" + "## Part 3: Search with MongoDB MongoDB Vector Search" ] }, { @@ -1094,7 +1094,7 @@ "### Step 2: Installing MongoDB via Atlas CLI\n", "\n", "The Atlas CLI is a command line interface built specifically for MongoDB Atlas.\n", - "Interact with your Atlas database deployments and Atlas Search from the terminal with short, intuitive commands, so you can accomplish complex database management tasks in seconds.\n", + "Interact with your Atlas database deployments and MongoDB Search from the terminal with short, intuitive commands, so you can accomplish complex database management tasks in seconds.\n", "\n", "You can follow the instructions [here](https://www.mongodb.com/docs/atlas/cli/current/install-atlas-cli/#complete-the-prerequisites-3) to install the Atlas CLI using docker(other options are available) and get a local MongoDB database instance running.\n", "\n", @@ -1496,7 +1496,7 @@ "\n", "Benefits\n", "The BinData vector format requires about three times less disk space in your cluster compared to arrays of elements.\n", - "It allows you to index your vectors with alternate types such as int1 or int8 vectors, reducing the memory needed to build the Atlas Vector Search index for your collection.\n", + "It allows you to index your vectors with alternate types such as int1 or int8 vectors, reducing the memory needed to build the MongoDB Vector Search index for your collection.\n", "It reduces the RAM for mongot by 3.75x for scalar and by 24x for binary; the vector values shrink by 4x and 32x respectively, but the Hierarchical Navigable Small Worlds graph itself doesn't shrink.\n", "\n", "In this notebook, we will convert the embeddings to the BSON binData vector format by using the `bson.binary` module.\n", diff --git a/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb b/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb index 523f0bbe..42b9a58d 100644 --- a/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb +++ b/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB Atlas Vector Search\n", + "# AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB MongoDB Vector Search\n", "\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb)\n", "-----\n", @@ -35,14 +35,14 @@ "- PostgreSQL with pgvector:\n", " - How to set up a PostgreSQL database with the pgvector extension.\n", " - How to run text, vector, and hybrid searches on PostgreSQL.\n", - "- MongoDB Atlas Vector Search:\n", + "- MongoDB MongoDB Vector Search:\n", " - How to set up a MongoDB Atlas database with native Vector Search capabilities.\n", " - How to execute text, vector, and hybrid searches on MongoDB Atlas.\n", "- AI Workload Overview:\n", " - This notebook showcases a standard AI workload involving vector embeddings and the retrieval of semantically similar documents. \n", " - The system leverages two different vector search solutions:\n", " - PostgreSQL with pgvector: A powerful extension that integrates vector search capabilities directly into PostgreSQL.\n", - " - MongoDB Atlas Vector Search: A native vector search feature built into MongoDB, optimized for modern, document-based applications.\n", + " - MongoDB MongoDB Vector Search: A native vector search feature built into MongoDB, optimized for modern, document-based applications.\n", "- AI Workload Metrics:\n", " - Latency: The time it takes to retrieve the top n results\n", " - Throughput: The number of queries processed per second\n", @@ -1345,9 +1345,9 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "An Atlas Search index is a data structure that categorizes data in an easily searchable format. It is a mapping between terms and the documents that contain those terms. Atlas Search indexes enable faster retrieval of documents using certain identifiers. You must configure an Atlas Search index to query data in your Atlas cluster using Atlas Search.\n", + "An MongoDB Search index is a data structure that categorizes data in an easily searchable format. It is a mapping between terms and the documents that contain those terms. MongoDB Search indexes enable faster retrieval of documents using certain identifiers. You must configure an MongoDB Search index to query data in your Atlas cluster using MongoDB Search.\n", "\n", - "You can create an Atlas Search index on a single field or on multiple fields. We recommend that you index the fields that you regularly use to sort or filter your data in order to quickly retrieve the documents that contain the relevant data at query-time.\n", + "You can create an MongoDB Search index on a single field or on multiple fields. We recommend that you index the fields that you regularly use to sort or filter your data in order to quickly retrieve the documents that contain the relevant data at query-time.\n", "\n" ] }, @@ -1681,7 +1681,7 @@ "source": [ "### Step 9: Define Hybrid Search Function\n", "\n", - "The `hybrid_search_with_mongodb` function conducts a hybrid search on a MongoDB Atlas collection that combines a vector search and a full-text search using Atlas Search.\n", + "The `hybrid_search_with_mongodb` function conducts a hybrid search on a MongoDB Atlas collection that combines a vector search and a full-text search using MongoDB Search.\n", "\n", "In the MongoDB hybrid search function, there are two weights:\n", "\n", @@ -1753,7 +1753,7 @@ "):\n", " \"\"\"\n", " Conduct a hybrid search on a MongoDB Atlas collection that combines a vector search\n", - " and a full-text search using Atlas Search.\n", + " and a full-text search using MongoDB Search.\n", "\n", " Args:\n", " user_query (str): The user's query string.\n", @@ -2774,7 +2774,7 @@ "\n", "This notebook implements and benchmarks a standard AI workload that involves vector embeddings and the retreival of semantically similar documents from a database. The system uses two different vector databases:\n", "- PostgreSQL with pgvector: A vector database extension for PostgreSQL that enables vector search on the database.\n", - "- MongoDB Atlas Vector Search: A vector search feature for MongoDB Database that enables vector search on the database.\n" + "- MongoDB MongoDB Vector Search: A vector search feature for MongoDB Database that enables vector search on the database.\n" ] }, { @@ -4151,7 +4151,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Part 3: Semantic Search with MongoDB Atlas Vector Search" + "## Part 3: Semantic Search with MongoDB MongoDB Vector Search" ] }, { @@ -4179,7 +4179,7 @@ "### Step 2: Installing MongoDB via Atlas CLI\n", "\n", "The Atlas CLI is a command line interface built specifically for MongoDB Atlas. \n", - "Interact with your Atlas database deployments and Atlas Search from the terminal with short, intuitive commands, so you can accomplish complex database management tasks in seconds.\n", + "Interact with your Atlas database deployments and MongoDB Search from the terminal with short, intuitive commands, so you can accomplish complex database management tasks in seconds.\n", "\n", "You can follow the instructions [here](https://www.mongodb.com/docs/atlas/cli/current/install-atlas-cli/#complete-the-prerequisites-3) to install the Atlas CLI using docker(other options are available) and get a local MongoDB database instance running.\n", "\n", diff --git a/notebooks/rag/README.md b/notebooks/rag/README.md index 9c450cf7..a34cdca5 100644 --- a/notebooks/rag/README.md +++ b/notebooks/rag/README.md @@ -1,4 +1,4 @@ -Jupyter Notebooks demonstrating various Retrieval Augmented Generation (RAG) implementations using LLM providers, frameworks and MongoDB Atlas Vector Search. +Jupyter Notebooks demonstrating various Retrieval Augmented Generation (RAG) implementations using LLM providers, frameworks and MongoDB MongoDB Vector Search. | Title | Stack | Notebook | |-------|-------|----------| diff --git a/notebooks/rag/SwigMenu_Playwright_OpenAI_MongoDB.ipynb b/notebooks/rag/SwigMenu_Playwright_OpenAI_MongoDB.ipynb index 7df39db4..df062126 100644 --- a/notebooks/rag/SwigMenu_Playwright_OpenAI_MongoDB.ipynb +++ b/notebooks/rag/SwigMenu_Playwright_OpenAI_MongoDB.ipynb @@ -27,7 +27,7 @@ "source": [ "## Overview\n", "\n", - "In this tutorial we are going to scrape the popular Utah \"dirty\" soda website, Swig, using Playwright, then we are going to feed in our drinks into OpenAI using a prompt and their structured outputs to understand which drinks from their menu are best for various seasons with reasonings, and then save this information into MongoDB Atlas so we can use Atlas Search to find specific drinks based on the fall season and ingredients we are craving." + "In this tutorial we are going to scrape the popular Utah \"dirty\" soda website, Swig, using Playwright, then we are going to feed in our drinks into OpenAI using a prompt and their structured outputs to understand which drinks from their menu are best for various seasons with reasonings, and then save this information into MongoDB Atlas so we can use MongoDB Search to find specific drinks based on the fall season and ingredients we are craving." ] }, { @@ -906,7 +906,7 @@ "id": "rp_xZtC4DSXp" }, "source": [ - "Now that our drinks with their reasonings are printed out nicely, let's upload them into MongoDB Atlas so we can use Atlas Search and take a look at drinks based off their ingredients!" + "Now that our drinks with their reasonings are printed out nicely, let's upload them into MongoDB Atlas so we can use MongoDB Search and take a look at drinks based off their ingredients!" ] }, { @@ -915,7 +915,7 @@ "id": "uObYzbmu_Mjd" }, "source": [ - "## Step 3: Store into MongoDB and use Atlas Search" + "## Step 3: Store into MongoDB and use MongoDB Search" ] }, { @@ -1030,7 +1030,7 @@ "id": "wFUitWvnFb4Z" }, "source": [ - "Create an Atlas Search index on your collection\n", + "Create an MongoDB Search index on your collection\n", "and create an aggregation pipeline. We are using the operator $search.\n", "\n", "Do NOT run this part in your notebook. This is done in the Atlas UI.\n", diff --git a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb index 216ec262..cf1b73a0 100644 --- a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb +++ b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb @@ -30,7 +30,7 @@ "\n", "What's Covered\n", "\n", - "* Building a Trader Joe’s AI party planner using Playwright, LlamaIndex, and MongoDB Atlas Vector Search\n", + "* Building a Trader Joe’s AI party planner using Playwright, LlamaIndex, and MongoDB MongoDB Vector Search\n", "* Scraping Trader Joe’s fall items with Playwright and formatting them for chatbot use\n", "* Setting up and embedding product data in MongoDB Atlas Vector Store for semantic search\n", "* Creating a Retrieval-Augmented Generation (RAG) chatbot to answer party planning questions\n", @@ -421,7 +421,7 @@ "id": "qG9xp4g5SQ-7" }, "source": [ - "Now, let’s go ahead and save our products into a `.txt` file so we can use it later in our tutorial when we are using our LlamaIndex and Atlas Vector Search integration. Go ahead and name the file whatever you like, for sake of tracking I’m naming mine: `tj_fall_faves_oct30.txt`." + "Now, let’s go ahead and save our products into a `.txt` file so we can use it later in our tutorial when we are using our LlamaIndex and MongoDB Vector Search integration. Go ahead and name the file whatever you like, for sake of tracking I’m naming mine: `tj_fall_faves_oct30.txt`." ] }, { @@ -473,7 +473,7 @@ "id": "LMuoPlEwi2bq" }, "source": [ - "## Part 2: LlamaIndex and Atlas Vector Search Integration" + "## Part 2: LlamaIndex and MongoDB Vector Search Integration" ] }, { @@ -482,9 +482,9 @@ "id": "qTkfhJ_3SaNY" }, "source": [ - "This is the quickstart we are using in order to be successful with this part of the tutorial: https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/llamaindex/#:~:text=You%20can%20integrate%20Atlas%20Vector,RAG). We will be going over how to use Atlas Vector Search with LlamaIndex to build a RAG application with chat capabilities!\n", + "This is the quickstart we are using in order to be successful with this part of the tutorial: https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/llamaindex/#:~:text=You%20can%20integrate%20Atlas%20Vector,RAG). We will be going over how to use MongoDB Vector Search with LlamaIndex to build a RAG application with chat capabilities!\n", "\n", - "This section will cover in detail how to set up the environment, store our custom data that we previously scraped on Atlas, create an Atlas Vector Search index on top of our data, and to finish up we will implement RAG and will use Atlas Vector Search to answer questions from our unique data store.\n", + "This section will cover in detail how to set up the environment, store our custom data that we previously scraped on Atlas, create an MongoDB Vector Search index on top of our data, and to finish up we will implement RAG and will use MongoDB Vector Search to answer questions from our unique data store.\n", "\n", "\n", "Let’s first use `pip` to install all our necessary libraries. We will need to include `llama-index`, `llama-index-vector-stores-mongodb`, and `llama-index-embeddings-openai`.\n" @@ -775,7 +775,7 @@ "source": [ "Once this cell has run you can go ahead and view your data with the embeddings inside of your Atlas cluster.\n", "\n", - "In order to allow for vector search queries on our created vector store, we need to create an Atlas Vector Search index on our tj_products.fall_faves collection. We can do this either through the [Atlas UI](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/) or directly from our notebook:\n" + "In order to allow for vector search queries on our created vector store, we need to create an MongoDB Vector Search index on our tj_products.fall_faves collection. We can do this either through the [Atlas UI](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/) or directly from our notebook:\n" ] }, { @@ -834,7 +834,7 @@ "id": "F398Wr-aTLUJ" }, "source": [ - "You’ll be able to see this index once it’s up and running under your “Atlas Search” tab in your Atlas UI. Once it’s done, we can start querying our data and we can do some basic RAG." + "You’ll be able to see this index once it’s up and running under your “MongoDB Search” tab in your Atlas UI. Once it’s done, we can start querying our data and we can do some basic RAG." ] }, { @@ -852,9 +852,9 @@ "id": "v3rIQipnTPHB" }, "source": [ - "With our Atlas Vector Search index up and running we are ready to have some fun and bring our AI Party Planner to life! We are going to continue with this dream team where we will use Atlas Vector Search to get our documents and LlamaIndex’s query engine to actually answer our questions based on our documents.\n", + "With our MongoDB Vector Search index up and running we are ready to have some fun and bring our AI Party Planner to life! We are going to continue with this dream team where we will use MongoDB Vector Search to get our documents and LlamaIndex’s query engine to actually answer our questions based on our documents.\n", "\n", - "To do this, we will need to have Atlas Vector Search become a [vector index retriever](https://docs.llamaindex.ai/en/stable/api_reference/retrievers/vector/) and we will need to initialize a `RetrieverQueryEngine` to handle queries by passing each question through our vector retrieval system. This combination will allow us to ask any questions we want in natural language, and it will match us with the most accurate documents." + "To do this, we will need to have MongoDB Vector Search become a [vector index retriever](https://docs.llamaindex.ai/en/stable/api_reference/retrievers/vector/) and we will need to initialize a `RetrieverQueryEngine` to handle queries by passing each question through our vector retrieval system. This combination will allow us to ask any questions we want in natural language, and it will match us with the most accurate documents." ] }, { @@ -877,7 +877,7 @@ } ], "source": [ - "# Instantiate Atlas Vector Search as a retriever\n", + "# Instantiate MongoDB Vector Search as a retriever\n", "vector_store_retriever = VectorIndexRetriever(\n", " index=vector_store_index, similarity_top_k=5\n", ")\n", diff --git a/notebooks/rag/chat_with_pdf_mongodb_openai_langchain_POLM_AI_Stack.ipynb b/notebooks/rag/chat_with_pdf_mongodb_openai_langchain_POLM_AI_Stack.ipynb index a3ad12e7..5b783cb1 100644 --- a/notebooks/rag/chat_with_pdf_mongodb_openai_langchain_POLM_AI_Stack.ipynb +++ b/notebooks/rag/chat_with_pdf_mongodb_openai_langchain_POLM_AI_Stack.ipynb @@ -17,7 +17,7 @@ "\n", "## Vector Index Creation\n", "\n", - "- [Create an Atlas Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", + "- [Create an MongoDB Vector Search Index](https://www.mongodb.com/docs/compass/current/indexes/create-vector-search-index/)\n", "\n", "- If you are following this notebook ensure that you are creating a vector search index for the right database(anthropic_demo) and collection(research)\n", "\n", diff --git a/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb b/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb index 2f82a84b..3e80bb2d 100644 --- a/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb +++ b/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb @@ -908,7 +908,7 @@ "source": [ "# The field containing the text embeddings on each document within the shipping_data collection\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB Atlas Vector Search index name\n", + "# MongoDB MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, diff --git a/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb b/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb index 5a6e51c8..b3137cbe 100644 --- a/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb +++ b/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb @@ -621,7 +621,7 @@ "Next, let's add the graph nodes. Nodes in LangGraph are functions or tools that your system has access to in order to complete the task. Each node updates one or more attributes in the graph state with its return value after it executes. Our assistant has four nodes:\n", "1. **Metadata Extractor**: Extract metadata from a natural language query\n", "2. **Filter Generator**: Generate a MongoDB Query API filter definition\n", - "3. **MongoDB Atlas Vector Search**: Retrieve documents from MongoDB using semantic search\n", + "3. **MongoDB MongoDB Vector Search**: Retrieve documents from MongoDB using semantic search\n", "4. **Answer Generator**: Generate an answer to the user question\n", "\n", "\n" @@ -823,7 +823,7 @@ "id": "U1nFUwqbtGtS" }, "source": [ - "### MongoDB Atlas Vector Search" + "### MongoDB MongoDB Vector Search" ] }, { @@ -886,7 +886,7 @@ "source": [ "def vector_search(state: Dict) -> Dict:\n", " \"\"\"\n", - " Get relevant information using MongoDB Atlas Vector Search\n", + " Get relevant information using MongoDB MongoDB Vector Search\n", "\n", " Args:\n", " state (Dict): The current graph state\n", diff --git a/partners/README.md b/partners/README.md index a54aa534..a8934ccf 100644 --- a/partners/README.md +++ b/partners/README.md @@ -1,6 +1,6 @@ # MongoDB Gen AI Partners Showcase -This directory contains collaborative AI projects and showcases developed in partnership with leading AI and technology companies. These partnerships demonstrate real-world applications of MongoDB's AI capabilities across various industries and use cases, showcasing how MongoDB's vector search, Atlas Search, and other AI-powered features can be integrated with cutting-edge AI platforms and frameworks. +This directory contains collaborative AI projects and showcases developed in partnership with leading AI and technology companies. These partnerships demonstrate real-world applications of MongoDB's AI capabilities across various industries and use cases, showcasing how MongoDB's vector search, MongoDB Search, and other AI-powered features can be integrated with cutting-edge AI platforms and frameworks. Each partner brings their unique expertise and technology stack to create comprehensive solutions that address specific industry challenges. From regulatory compliance and supply chain management to AI safety and knowledge discovery, these collaborations highlight the versatility and power of MongoDB's AI ecosystem. diff --git a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb index c2780976..4ca4d92f 100644 --- a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb +++ b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb @@ -1410,7 +1410,7 @@ " 'functions\\n'\n", " '- 👤 **Persona System**: Create consistent, specialized agent '\n", " 'personalities\\n'\n", - " '- 📊 **Vector Search**: MongoDB Atlas Vector Search for efficient '\n", + " '- 📊 **Vector Search**: MongoDB MongoDB Vector Search for efficient '\n", " 'retrieval\\n'\n", " '\\n'\n", " '## Key Features\\n'\n", diff --git a/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb b/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb index d2a93cb3..b0e5fc7b 100644 --- a/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb +++ b/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb @@ -1393,7 +1393,7 @@ "source": [ "# The field containing the text embeddings on each document within the shipping_data collection\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB Atlas Vector Search index name\n", + "# MongoDB MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, diff --git a/partners/langchain/agentic_knowledge_discovery_notebook.ipynb b/partners/langchain/agentic_knowledge_discovery_notebook.ipynb index ddc7bee5..be3a48f7 100644 --- a/partners/langchain/agentic_knowledge_discovery_notebook.ipynb +++ b/partners/langchain/agentic_knowledge_discovery_notebook.ipynb @@ -35,7 +35,7 @@ "* **Mobilizing knowledge resources**: Retrieving relevant technical procedures, best practices, and previous incident documentation.\n", "* **Orchestrating coordinated response**: Generating comprehensive response plans with prioritized action items, team assignments, and communication protocols.\n", "\n", - "Built on `MongoDB Atlas Vector Search` for high-performance semantic search and document retrieval, `LangChain` and `LangGraph` for agentic workflow orchestration, this approach delivers an intelligent emergency response system that dramatically reduces incident resolution time and business impact.\n" + "Built on `MongoDB MongoDB Vector Search` for high-performance semantic search and document retrieval, `LangChain` and `LangGraph` for agentic workflow orchestration, this approach delivers an intelligent emergency response system that dramatically reduces incident resolution time and business impact.\n" ] }, { @@ -124,7 +124,7 @@ "\n", "**Key Components:**\n", "\n", - "- MongoDB Atlas Vector Search: Dense vector indexing for semantic relevance.\n", + "- MongoDB MongoDB Vector Search: Dense vector indexing for semantic relevance.\n", "\n", "- Voyage AI: State of the art embedding models and rerankers\n", "\n", From f7f70f5a61430af4d9f14fec38a19f7dcdc26e15 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:04:18 +0100 Subject: [PATCH 02/22] Update README.md --- apps/local-bot/README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/apps/local-bot/README.md b/apps/local-bot/README.md index 68516e88..dee5de3e 100644 --- a/apps/local-bot/README.md +++ b/apps/local-bot/README.md @@ -1,6 +1,6 @@ # Step-by-Step Guide: Building a Local Chatbot with Streamlit, LangChain, Ollama, and MongoDB Atlas -In this tutorial, we'll set up a local chatbot using **Streamlit**, **LangChain**, **Ollama**, and **MongoDB MongoDB Search**. This bot will leverage MongoDB's powerful MongoDB Search capabilities alongside local LLMs (Large Language Models) via Ollama, allowing you to enhance user queries with context from chat history. +In this tutorial, we'll set up a local chatbot using **Streamlit**, **LangChain**, **Ollama**, and **MongoDB Search**. This bot will leverage MongoDB's powerful MongoDB Search capabilities alongside local LLMs (Large Language Models) via Ollama, allowing you to enhance user queries with context from chat history. ## Prerequisites Before starting, make sure you have the following installed: @@ -40,7 +40,7 @@ Here’s a quick rundown of the tools we’re using in this project: * *[Streamlit](https://streamlit.io)*: A Python library for easily creating data-based web applications. We'll use it to create a local chatbot interface. * *[LangChain](https://langchain.com)*: A framework that simplifies working with LLMs and document processing. It will assist processing user queries and generate responses. * *[Ollama](https://ollama.com)*: A solution for deploying LLMs locally without external API dependency. It to host our models. -* *[MongoDB MongoDB Search](https://www.mongodb.com/products/platform/atlas-search)*: Adds a powerful, flexible vector search functionality to our app. It will store user queries and responses in MongoDB. +* *[MongoDB Search](https://www.mongodb.com/products/platform/atlas-search)*: Adds a powerful, flexible vector search functionality to our app. It will store user queries and responses in MongoDB. ### Setting Up `requirements.txt` @@ -268,7 +268,7 @@ At this point, you can start prompting with inputs like “Who started AT&T?” ## Conclusion and Next Steps -In this tutorial, we built a local chatbot setup using MongoDB MongoDB Search and local LLMs via Ollama, integrated through Streamlit. This project forms a robust foundation for further development and deployment. +In this tutorial, we built a local chatbot setup using MongoDB Search and local LLMs via Ollama, integrated through Streamlit. This project forms a robust foundation for further development and deployment. Possible Extensions: From 74981fd3f7f376d58ff4163ced78e9f7ec7a88a5 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:05:12 +0100 Subject: [PATCH 03/22] Update layout.tsx --- apps/minimal-ts-agent/src/app/layout.tsx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/minimal-ts-agent/src/app/layout.tsx b/apps/minimal-ts-agent/src/app/layout.tsx index f5c1de7b..17829cf6 100644 --- a/apps/minimal-ts-agent/src/app/layout.tsx +++ b/apps/minimal-ts-agent/src/app/layout.tsx @@ -15,7 +15,7 @@ const geistMono = Geist_Mono({ export const metadata: Metadata = { title: "MongoDB RAG Agent — Brand Book Expert", description: - "A fully autonomous RAG agent powered by Vercel AI SDK ToolLoopAgent and MongoDB MongoDB Vector Search", + "A fully autonomous RAG agent powered by Vercel AI SDK ToolLoopAgent and MongoDB Vector Search", }; export default function RootLayout({ From f3814670af734b82e2d639e7f7eb9353ed700a64 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:05:50 +0100 Subject: [PATCH 04/22] Update README.md --- apps/minimal-ts-agent/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/minimal-ts-agent/README.md b/apps/minimal-ts-agent/README.md index 0dfa8ae3..f833650c 100644 --- a/apps/minimal-ts-agent/README.md +++ b/apps/minimal-ts-agent/README.md @@ -1,6 +1,6 @@ # RAG Agent Demo — How to Create an AI Agent with Minimal Coding -Companion project for the **"How to Create an AI Agent with Minimal Coding"** video. This demo builds a fully functional RAG (Retrieval-Augmented Generation) agent that answers questions about the MongoDB Brand Book using MongoDB MongoDB Vector Search, Voyage AI embeddings, and the Vercel AI SDK's `ToolLoopAgent`. +Companion project for the **"How to Create an AI Agent with Minimal Coding"** video. This demo builds a fully functional RAG (Retrieval-Augmented Generation) agent that answers questions about the MongoDB Brand Book using MongoDB Vector Search, Voyage AI embeddings, and the Vercel AI SDK's `ToolLoopAgent`. ## What It Does @@ -23,7 +23,7 @@ flowchart TD D -->|Reasoning step| E{Need more context?} E -->|Yes| F[searchDocumentation tool] F -->|Embed query| G[Voyage AI] - G -->|Query vector| H[MongoDB MongoDB Vector Search] + G -->|Query vector| H[MongoDB Vector Search] H -->|Top 5 results| D E -->|No| I[Generate final response] I -->|Stream| B From af4a41189702402b27b8d23a75b8fc388062c083 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:06:31 +0100 Subject: [PATCH 05/22] Update README.md --- apps/mongostory/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/mongostory/README.md b/apps/mongostory/README.md index 15b7069b..c2f95345 100644 --- a/apps/mongostory/README.md +++ b/apps/mongostory/README.md @@ -40,7 +40,7 @@ MongoStory is a cloud-native platform designed to empower content creators, edit ### Backend - **API Routes**: Next.js API routes for server-side functionality - **Database**: MongoDB for flexible document storage -- **Vector Search**: MongoDB MongoDB Vector Search for semantic content operations +- **Vector Search**: MongoDB Vector Search for semantic content operations - **AI Integration**: Integration with AI models via AI SDK - xAI (Grok) ### AI Integration @@ -60,7 +60,7 @@ MongoStory leverages MongoDB's document model for flexible content storage and i - `clusters`: AI-generated content clusters - `socialMediaPosts`: Generated social media content -- **Vector Search**: Uses MongoDB MongoDB Vector Search for semantic operations: +- **Vector Search**: Uses MongoDB Vector Search for semantic operations: - Content similarity detection - Semantic search functionality - Automatic content clustering From 8cf2daadee5e841e9f47dc79be63193561a0b69f Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:07:56 +0100 Subject: [PATCH 06/22] Update README.md --- apps/springai-terraform-rag/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/springai-terraform-rag/README.md b/apps/springai-terraform-rag/README.md index bd0b8c62..e72ffb4f 100644 --- a/apps/springai-terraform-rag/README.md +++ b/apps/springai-terraform-rag/README.md @@ -1,6 +1,6 @@ # MongoDB Atlas + Terraform Spring Boot RAG Application -This repository demonstrates how to build a **Retrieval-Augmented Generation (RAG)** application using **Spring Boot**, **OpenAI embeddings**, and **MongoDB MongoDB Vector Search**. The infrastructure is automated using **Terraform** to provision and manage MongoDB Atlas resources. +This repository demonstrates how to build a **Retrieval-Augmented Generation (RAG)** application using **Spring Boot**, **OpenAI embeddings**, and **MongoDB Vector Search**. The infrastructure is automated using **Terraform** to provision and manage MongoDB Atlas resources. ## Overview From 6fded991d969eba7f5868c35c91d6e1f4e175d42 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:08:25 +0100 Subject: [PATCH 07/22] Update setup_indexes.py --- apps/video-intelligence/backend/setup_indexes.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/video-intelligence/backend/setup_indexes.py b/apps/video-intelligence/backend/setup_indexes.py index 2b84eb87..40015354 100755 --- a/apps/video-intelligence/backend/setup_indexes.py +++ b/apps/video-intelligence/backend/setup_indexes.py @@ -1,6 +1,6 @@ #!/usr/bin/env python3 """ -MongoDB MongoDB Search Index Setup Script +MongoDB Search Index Setup Script Creates the required vector search and text search indexes for the Video Intelligence app. """ @@ -18,7 +18,7 @@ def setup_indexes(): # Get embedding dimensions from environment variable EMBEDDING_DIM_SIZE = int(os.getenv("EMBEDDING_DIM_SIZE", "1024")) print(f"Using embedding dimensions: {EMBEDDING_DIM_SIZE}") - print("🔧 Setting up MongoDB MongoDB Search Indexes") + print("🔧 Setting up MongoDB Search Indexes") print("=" * 50) # Load environment variables From 40e538693b4850ed2701fcd729a6d10f7fa994f3 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:09:00 +0100 Subject: [PATCH 08/22] Update tools.py --- apps/voice-openai-mongo-rentals-agent/src/server/tools.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/voice-openai-mongo-rentals-agent/src/server/tools.py b/apps/voice-openai-mongo-rentals-agent/src/server/tools.py index ce6b5fed..20fd569a 100644 --- a/apps/voice-openai-mongo-rentals-agent/src/server/tools.py +++ b/apps/voice-openai-mongo-rentals-agent/src/server/tools.py @@ -37,7 +37,7 @@ class Booking(BaseModel): @tool def rentlas_search_tool(query: str, k: int = 5): """ - Perform a vector similarity search using MongoDB MongoDB Vector Search to find rentals. + Perform a vector similarity search using MongoDB Vector Search to find rentals. Args: query (str): The search query string. @@ -48,7 +48,7 @@ def rentlas_search_tool(query: str, k: int = 5): and score is the similarity score (lower is more similar). Note: - Uses MongoDB MongoDB Vector Search for semantic search capabilities. + Uses MongoDB Vector Search for semantic search capabilities. """ vector_store = MongoDBAtlasVectorSearch.from_connection_string( connection_string=os.environ["MONGODB_ATLAS_URI"], From 9a16b8b90880e8a169d668054f2b43550897b8fc Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:09:26 +0100 Subject: [PATCH 09/22] Update README.md --- apps/voice-openai-mongo-rentals-agent/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/voice-openai-mongo-rentals-agent/README.md b/apps/voice-openai-mongo-rentals-agent/README.md index d4c6a96f..17700521 100644 --- a/apps/voice-openai-mongo-rentals-agent/README.md +++ b/apps/voice-openai-mongo-rentals-agent/README.md @@ -1,4 +1,4 @@ -# Voice Agent with MongoDB MongoDB Vector Search +# Voice Agent with MongoDB Vector Search Thumbnail From c441e6f74e27ac903ba2d99e7a306a28aa8bcd1e Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:09:54 +0100 Subject: [PATCH 10/22] Update BuildShip.md --- misc/low-code/BuildShip.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/misc/low-code/BuildShip.md b/misc/low-code/BuildShip.md index f315e7f7..9faba88a 100644 --- a/misc/low-code/BuildShip.md +++ b/misc/low-code/BuildShip.md @@ -63,7 +63,7 @@ This workflow serves as a versatile template for creating various types of AI ag ### Extend MongoDB Integration - Implement complex aggregation pipelines for advanced queries -- Add MongoDB MongoDB Search for full-text search capabilities +- Add MongoDB Search for full-text search capabilities - Utilize MongoDB Change Streams for real-time updates - Incorporate MongoDB Charts for data visualization From 814bb36ee5507ec0398f4be5dc237371aaebd00e Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:10:24 +0100 Subject: [PATCH 11/22] Update evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb --- ...resentation_capacity_retention_with_mongodb_voyageai.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb b/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb index c89c46c4..9b9a98d0 100644 --- a/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb +++ b/notebooks/advanced_techniques/evaluation_of_representation_capacity_retention_with_mongodb_voyageai.ipynb @@ -41,7 +41,7 @@ "- Binary Quantization: A technique used to reduce the precision of a vector by converting it to a lower precision.\n", "- Representational Capacity Retention: The ability of a vector to retain the information of the original vector.\n", "\n", - "In this guide, we demonstrate how to leverage MongoDB MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. \n", + "In this guide, we demonstrate how to leverage MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. \n", "\n", "By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", "\n", @@ -4211,7 +4211,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "In this guide, we demonstrate how to leverage MongoDB MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", + "In this guide, we demonstrate how to leverage MongoDB Search with automatic quantization and Voyage AI embeddings to build a scalable, high-performance vector search pipeline. By compressing the embedding space—whether through scalar or binary quantization—you can dramatically reduce memory usage while retaining the vast majority of retrieval accuracy compared to a float32 baseline. \n", "\n", "These techniques not only cut operational costs but also improve throughput, allowing you to handle larger workloads or more complex queries. \n", "\n", From 6f79917ec4c8c04980d8cf79c916eaf377af992f Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:10:58 +0100 Subject: [PATCH 12/22] Update geospatialqueries_vectorsearch_spritzes.ipynb --- .../geospatialqueries_vectorsearch_spritzes.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb b/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb index 5b0d16b5..95897794 100644 --- a/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb +++ b/notebooks/advanced_techniques/geospatialqueries_vectorsearch_spritzes.ipynb @@ -458,9 +458,9 @@ "## Which one comes first, Vector Search or Geospatial Queries?\n", "Both of these need to be the first stage in their aggregation pipelines, so instead of making one pipeline we are going to do a little loophole. We will do two pipelines. But how will we decide which?!\n", "\n", - "When I'm using Google Maps to figure out where to go, I normally first search for what I'm looking for and then I see how far away it is from where I currently am and pick the closest location to me. So let's keep that mindset in place and start off with MongoDB MongoDB Vector Search for this tutorial. But, I understand intuitively some of you might prefer to search via all nearby locations and then utilize Vector Search, so I'll highlight that method of searching for your spritz's as well.\n", + "When I'm using Google Maps to figure out where to go, I normally first search for what I'm looking for and then I see how far away it is from where I currently am and pick the closest location to me. So let's keep that mindset in place and start off with MongoDB Vector Search for this tutorial. But, I understand intuitively some of you might prefer to search via all nearby locations and then utilize Vector Search, so I'll highlight that method of searching for your spritz's as well.\n", "\n", - "## MongoDB MongoDB Vector Search\n", + "## MongoDB Vector Search\n", "We have a couple steps here. Our first step is to create a Vector Search Index. Do this inside of MongoDB Atlas by following this documentation. Please keep in mind that your index is NOT run in your script, it lives in your cluster. You'll know it's ready to go when the button turns green and it's activated." ] }, From 680ef0df2ccc31c1a471cf867ed061a7d3bb5983 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:11:32 +0100 Subject: [PATCH 13/22] Update Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb --- ...2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb index aad21719..7e89269d 100644 --- a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb +++ b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb @@ -5446,9 +5446,9 @@ "id": "EVb8Ia6LCv3B" }, "source": [ - "### MongoDB MongoDB Vector Search with Gemini 2.0\n", + "### MongoDB Vector Search with Gemini 2.0\n", "\n", - "A vector similarity search implementation that leverages MongoDB MongoDB Vector Search and Google's Gemini 2.0 embeddings to perform semantic document searches, returning the k-most similar documents based on query embedding comparison." + "A vector similarity search implementation that leverages MongoDB Vector Search and Google's Gemini 2.0 embeddings to perform semantic document searches, returning the k-most similar documents based on query embedding comparison." ] }, { @@ -5477,7 +5477,7 @@ " )\n", "def atlas_search(query: str, k: int = 5):\n", " \"\"\"\n", - " Perform a vector similarity search using MongoDB MongoDB Vector Search.\n", + " Perform a vector similarity search using MongoDB Vector Search.\n", " \"\"\"\n", " try:\n", "\n", From a24a40bfb2beb9fd1508fda452938ca9d32c9764 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:12:01 +0100 Subject: [PATCH 14/22] Update implementing_working_memory_with_tavily_and_mongodb.ipynb --- .../implementing_working_memory_with_tavily_and_mongodb.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb b/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb index c08162a6..b937ac95 100644 --- a/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb +++ b/notebooks/agents/implementing_working_memory_with_tavily_and_mongodb.ipynb @@ -1936,7 +1936,7 @@ "source": [ "Retrieving data from MongoDB involves leveraging both traditional queries and vector search. For traditional queries, the pymongo library provides methods like `find_one()` and `find()` to retrieve documents based on specific criteria.\n", "\n", - "MongoDB MongoDB Vector Search is used for semantic-based retrieval. This feature allows for efficient similarity searches using the pre-calculated product embeddings. The system can retrieve products that are semantically similar to the query by querying the' embedding' field with a target embedding.\n", + "MongoDB Vector Search is used for semantic-based retrieval. This feature allows for efficient similarity searches using the pre-calculated product embeddings. The system can retrieve products that are semantically similar to the query by querying the' embedding' field with a target embedding.\n", "\n", "This approach significantly enhances the AI sales assistant's ability to understand user intent and offer relevant product suggestions. Variables like `embedding_field_name` and `vector_search_index_name` are used to configure and interact with the vector search index within MongoDB, ensuring efficient retrieval of similar products.\n" ] @@ -1960,7 +1960,7 @@ "source": [ "# The field containing the text embeddings on each document\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB MongoDB Vector Search index name\n", + "# MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, From 4ae35046b0d01fa05f645aeaaa95a615da684a57 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:12:28 +0100 Subject: [PATCH 15/22] Update mongodb_as_a_toolbox_for_llamaindex_agents.ipynb --- .../agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb index 035d43db..360871f3 100644 --- a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb +++ b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb @@ -23,7 +23,7 @@ "**Key Features:**\n", "\n", "* **MongoDB as a Tool Registry:** Instead of hardcoding tool definitions within the agent, this application stores tool metadata (name, description, parameters) directly in a MongoDB collection.\n", - "* **MongoDB MongoDB Vector Search for Tool Discovery:** LlamaIndex uses the vector embeddings of tool descriptions stored in MongoDB to perform semantic searches based on user queries. This allows the agent to dynamically discover and select the most relevant tools for a given task.\n", + "* **MongoDB Vector Search for Tool Discovery:** LlamaIndex uses the vector embeddings of tool descriptions stored in MongoDB to perform semantic searches based on user queries. This allows the agent to dynamically discover and select the most relevant tools for a given task.\n", "* **LlamaIndex Agent with Function Calling:** The LlamaIndex agent is configured to use the retrieved tool definitions from MongoDB to enable function calling. This means the agent can understand the user's intent and execute the appropriate Python function (tool) stored in the application.\n", "* **Data Storage in MongoDB:** Besides tool definitions, the application also uses separate MongoDB collections to store operational data like customer orders, return requests, and policy documents.\n", "* **Integration with External Services:** The tools defined and managed in MongoDB can interact with external services (e.g., fetching real-time data, processing requests) or perform operations on the data stored within MongoDB itself (e.g., looking up order details, creating return requests).\n", @@ -48,7 +48,7 @@ "- `llama-index-core`: The core LlamaIndex library.\n", "- `llama-index-llms-openai`: LlamaIndex integration with OpenAI LLMs.\n", "- `llama-index-embeddings-voyageai`: LlamaIndex integration with VoyageAI embeddings.\n", - "- `llama-index-vector-stores-mongodb`: LlamaIndex integration with MongoDB MongoDB Vector Search.\n", + "- `llama-index-vector-stores-mongodb`: LlamaIndex integration with MongoDB Vector Search.\n", "- `llama-index-readers-file`: LlamaIndex file readers." ] }, From 4542d7f7ff90c02627837566104b10b0d4bedf12 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:12:57 +0100 Subject: [PATCH 16/22] Update mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb --- ...db_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb b/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb index 81a6b027..8eed32f4 100644 --- a/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb +++ b/notebooks/agents/mongodb_voyage_ai_openai_rag_hybrid_agentic_sports_scores.ipynb @@ -6,9 +6,9 @@ "id": "Pff8TULfBfmW" }, "source": [ - "# MongoDB MongoDB Vector Search with VoyageAI Embeddings for Sports Scores and Stories\n", + "# MongoDB Vector Search with VoyageAI Embeddings for Sports Scores and Stories\n", "\n", - "This notebook demonstrates how to use VoyageAI embeddings with MongoDB MongoDB Vector Search for retrieving relevant sports scores and stories based on user queries." + "This notebook demonstrates how to use VoyageAI embeddings with MongoDB Vector Search for retrieving relevant sports scores and stories based on user queries." ] }, { From b8abf629949838fcd4ce56cbc1e5b27d3a23df70 Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:13:36 +0100 Subject: [PATCH 17/22] Update smolagents_hf_with_mongodb.ipynb --- notebooks/agents/smolagents_hf_with_mongodb.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebooks/agents/smolagents_hf_with_mongodb.ipynb b/notebooks/agents/smolagents_hf_with_mongodb.ipynb index 489111c5..04f5960c 100644 --- a/notebooks/agents/smolagents_hf_with_mongodb.ipynb +++ b/notebooks/agents/smolagents_hf_with_mongodb.ipynb @@ -1275,7 +1275,7 @@ "source": [ "## Vector Search based RAG with MongoDB Search\n", "\n", - "Vector search allows us to find relevant documents based on the semantic meaning of the query rather than just keyword matching. In this section, we demonstrate how to build a Retrieval-Augmented Generation (RAG) agent that leverages MongoDB MongoDB Search's vector search capabilities.\n", + "Vector search allows us to find relevant documents based on the semantic meaning of the query rather than just keyword matching. In this section, we demonstrate how to build a Retrieval-Augmented Generation (RAG) agent that leverages MongoDB Search's vector search capabilities.\n", "\n", "The RAG agent uses the `vector_search_rentals` tool to find relevant documents based on the query's embeddings. This approach enhances the search results by considering the context and meaning of the query, providing more accurate and relevant results.\n", "\n", From cbb6988abbd5b84864b2dc6f5d4adbcc839de57b Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:14:09 +0100 Subject: [PATCH 18/22] Update video_intelligence_agent.ipynb --- notebooks/agents/video_intelligence_agent.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebooks/agents/video_intelligence_agent.ipynb b/notebooks/agents/video_intelligence_agent.ipynb index 6eeae8c1..a3667335 100644 --- a/notebooks/agents/video_intelligence_agent.ipynb +++ b/notebooks/agents/video_intelligence_agent.ipynb @@ -1163,7 +1163,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "The code below is a helper wraps MongoDB MongoDB Search index creation: \n", + "The code below is a helper wraps MongoDB Search index creation: \n", "- given a collection, an index-definition dict, and a name, \n", "- it builds a SearchIndexModel, calls create_search_index, \n", "- and returns the result—printing success or catching errors and returning None.\n" From ac5c014789325d9e5affa6cb842066c4c2abf28d Mon Sep 17 00:00:00 2001 From: murrayhu-mdb Date: Thu, 21 May 2026 16:14:35 +0100 Subject: [PATCH 19/22] Update zero_to_hero_with_genai_with_mongodb_openai.ipynb --- .../agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb b/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb index b78c586a..c2c7292a 100644 --- a/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb +++ b/notebooks/agents/zero_to_hero_with_genai_with_mongodb_openai.ipynb @@ -688,7 +688,7 @@ "A vector search index organizes high-dimensional embeddings for efficient similarity searches. Without it, finding similar vectors would require exhaustive comparisons against every vector in your database—becoming impractical at scale. These indexes enable fast semantic searches by organizing vectors based on their geometric relationships, essential for RAG, recommendation systems, and semantic search.\n", "\n", "#### Understanding HNSW (Hierarchical Navigable Small Worlds)\n", - "HNSW is MongoDB MongoDB Vector Search's algorithm of choice for approximate nearest neighbor searches:\n", + "HNSW is MongoDB Vector Search's algorithm of choice for approximate nearest neighbor searches:\n", "- Creates a multi-layered graph connecting vectors to their nearest neighbors\n", "- Enables logarithmic search complexity through a hierarchical approach\n", "- Balances speed and accuracy via configurable parameters\n", From 1d492e0a1d794f918222cfd1e3ac9143c7f04e77 Mon Sep 17 00:00:00 2001 From: ajosh0504 Date: Fri, 22 May 2026 10:41:08 -0700 Subject: [PATCH 20/22] More renames --- apps/graph_rag_demo/addEmbeddings.js | 2 +- apps/minimal-ts-agent/src/app/page.tsx | 2 +- apps/mongo-feed/components/past-analysis.tsx | 2 +- .../components/semantic-content-explorer.tsx | 2 +- apps/springai-terraform-rag/README.md | 2 +- .../backend/setup_indexes.py | 2 +- entries.json | 2 + ...rieval_strategies_mongodb_llamaindex.ipynb | 2 +- ...tegies_mongodb_llamaindex_togetherai.ipynb | 2 +- ...lity_with_mongodb_atlas_vector_store.ipynb | 9638 ++++++++--------- ...ystack_self_reflecting_Cooking_agent.ipynb | 2 +- ...rbnb_agent_openai_llamaindex_mongodb.ipynb | 2 +- ...b_as_a_toolbox_for_llamaindex_agents.ipynb | 4 +- .../self_reflecting_gift_agent_haystack.ipynb | 2 +- notebooks/evals/Patronus_MongoDB.ipynb | 2 +- notebooks/evals/ragas-evaluation.ipynb | 2 +- ...ner_PlaywrightLlamaIndexVectorSearch.ipynb | 2 +- notebooks/rag/openai_text_3_emebdding.ipynb | 2 +- notebooks/rag/rag_chunking_strategies.ipynb | 4 +- ...allucination_detection_and_reduction.ipynb | 2 +- 20 files changed, 4833 insertions(+), 4847 deletions(-) create mode 100644 entries.json diff --git a/apps/graph_rag_demo/addEmbeddings.js b/apps/graph_rag_demo/addEmbeddings.js index 48898073..f9507900 100644 --- a/apps/graph_rag_demo/addEmbeddings.js +++ b/apps/graph_rag_demo/addEmbeddings.js @@ -17,7 +17,7 @@ async function run() { const collection = database.collection("knowledge_graph"); const dbConfig = { collection: collection, - indexName: "vector_index", // The name of the Atlas search index to use. + indexName: "vector_index", // The name of the MongoDB search index to use. textKey: "chunks", // Field name for the raw text content. Defaults to "text". embeddingKey: "embedding", // Field name for the vector embeddings. Defaults to "embedding". }; diff --git a/apps/minimal-ts-agent/src/app/page.tsx b/apps/minimal-ts-agent/src/app/page.tsx index 0fe75e1d..13c950ac 100644 --- a/apps/minimal-ts-agent/src/app/page.tsx +++ b/apps/minimal-ts-agent/src/app/page.tsx @@ -84,7 +84,7 @@ export default function ChatPage() { Ask me about the MongoDB Brand Book

- I use an agentic reasoning loop to search MongoDB Atlas Vector + I use an agentic reasoning loop to search MongoDB Vector Search and deliver precise answers from the official brand guidelines.

diff --git a/apps/mongo-feed/components/past-analysis.tsx b/apps/mongo-feed/components/past-analysis.tsx index 22803499..e8d3f533 100644 --- a/apps/mongo-feed/components/past-analysis.tsx +++ b/apps/mongo-feed/components/past-analysis.tsx @@ -52,7 +52,7 @@ export function PastAnalysis() { -

Past analysis results are stored in MongoDB and can be quickly retrieved using Atlas vector search.

+

Past analysis results are stored in MongoDB and can be quickly retrieved using MongoDB Vector Search.

Potential query: "Find similar analyses to the most recent customer feedback report"

diff --git a/apps/mongostory/components/semantic-content-explorer.tsx b/apps/mongostory/components/semantic-content-explorer.tsx index 51dfd434..cde3ddf5 100644 --- a/apps/mongostory/components/semantic-content-explorer.tsx +++ b/apps/mongostory/components/semantic-content-explorer.tsx @@ -103,7 +103,7 @@ export function SemanticContentExplorer() { } } - // Update the handleSearch function to better reflect MongoDB Atlas vector search + // Update the handleSearch function to better reflect MongoDB Vector Search const handleSearch = async () => { if (!searchQuery.trim()) return diff --git a/apps/springai-terraform-rag/README.md b/apps/springai-terraform-rag/README.md index e72ffb4f..cf7eb539 100644 --- a/apps/springai-terraform-rag/README.md +++ b/apps/springai-terraform-rag/README.md @@ -11,7 +11,7 @@ In this project, we: ## Features - **Automated Infrastructure**: Terraform is used to provision MongoDB Atlas resources including clusters, vector search indices, and access controls. -- **RAG Implementation**: A Spring Boot application that uses OpenAI to generate embeddings, with MongoDB Atlas vector search to perform semantic searches. +- **RAG Implementation**: A Spring Boot application that uses OpenAI to generate embeddings, with MongoDB Vector Search to perform semantic searches. - **Document Loading**: Upload documents and store their embeddings for use in vector search. - **Querying with Vector Search**: Search documents by semantic similarity using a custom `/question` endpoint. diff --git a/apps/video-intelligence/backend/setup_indexes.py b/apps/video-intelligence/backend/setup_indexes.py index 40015354..c71eb9f7 100755 --- a/apps/video-intelligence/backend/setup_indexes.py +++ b/apps/video-intelligence/backend/setup_indexes.py @@ -13,7 +13,7 @@ def setup_indexes(): - """Setup MongoDB Atlas search indexes""" + """Setup MongoDB Search indexes""" # Get embedding dimensions from environment variable EMBEDDING_DIM_SIZE = int(os.getenv("EMBEDDING_DIM_SIZE", "1024")) diff --git a/entries.json b/entries.json new file mode 100644 index 00000000..d6c9c0b8 --- /dev/null +++ b/entries.json @@ -0,0 +1,2 @@ +{"_id":{"$oid":"694447bbe08fda8e5bb9b311"},"user_id":"Apoorva","title":"17/12/2025","version":2,"created_at":{"$date":"2025-12-17T00:00:00Z"},"sentiment":"positive","themes":["nature","appreciation","beauty"]} +{"_id":{"$oid":"694448f66d70d639dc47434c"},"user_id":"Apoorva","title":"17/12/2025","version":1,"created_at":{"$date":"2025-12-17T00:00:00Z"}} diff --git a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb index ebf9d143..e13450b9 100644 --- a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb +++ b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex.ipynb @@ -462,7 +462,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Step 4: Create MongoDB Atlas vector store" + "## Step 4: Create MongoDB Vector Store" ] }, { diff --git a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb index 5e2a6cf1..e64d06d4 100644 --- a/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb +++ b/notebooks/advanced_techniques/retrieval_strategies_mongodb_llamaindex_togetherai.ipynb @@ -271,7 +271,7 @@ "id": "sFUS0_EURg2Q" }, "source": [ - "## Step 5: Create MongoDB Atlas Vector store" + "## Step 5: Create MongoDB Vector Store" ] }, { diff --git a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb index 7e89269d..347440f4 100644 --- a/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb +++ b/notebooks/agents/Gemini2_0_multi_modality_with_mongodb_atlas_vector_store.ipynb @@ -6,7 +6,7 @@ "id": "3hp_P0cDzTWp" }, "source": [ - "# Gemini 2.0 - Multimodal live API and MongoDB Atlas Vector store as tools\n", + "# Gemini 2.0 - Multimodal live API and MongoDB Vector store as tools\n", "\n", "Inspired and built on top of the following Google [example notebook](https://github.com/google-gemini/cookbook/blob/main/gemini-2/live_api_tool_use.ipynb)." ] @@ -101,8 +101,7 @@ "import os\n", "import getpass\n", "\n", - "\n", - "os.environ['GOOGLE_API_KEY'] = getpass.getpass(\"Input your Google API Key\")" + "os.environ[\"GOOGLE_API_KEY\"] = getpass.getpass(\"Input your Google API Key\")" ] }, { @@ -127,9 +126,7 @@ "source": [ "from google import genai\n", "\n", - "client = genai.Client(http_options= {\n", - " 'api_version': 'v1alpha'\n", - "})" + "client = genai.Client(http_options={\"api_version\": \"v1alpha\"})" ] }, { @@ -235,9 +232,10 @@ "outputs": [], "source": [ "import logging\n", - "logger = logging.getLogger('Live')\n", - "#logger.setLevel('DEBUG') # Switch between \"INFO\" and \"DEBUG\" to toggle debug messages.\n", - "logger.setLevel('INFO')" + "\n", + "logger = logging.getLogger(\"Live\")\n", + "# logger.setLevel('DEBUG') # Switch between \"INFO\" and \"DEBUG\" to toggle debug messages.\n", + "logger.setLevel(\"INFO\")" ] }, { @@ -269,51 +267,52 @@ "outputs": [], "source": [ "n = 0\n", - "async def run(prompt, modality=\"AUDIO\", tools=None):\n", - " global n\n", - " if tools is None:\n", - " tools=[]\n", "\n", - " config = {\n", - " \"tools\": tools,\n", - " \"system_instruction\" : \"You are a helpful HR assistant who can search employees with atlas_search_tool and create teams in the database with create_team tool\",\n", - " \"generation_config\": {\n", - " \"response_modalities\": [modality]}}\n", - " print(f\"before client invoke {tools}\")\n", - " async with client.aio.live.connect(model=model_name, config=config) as session:\n", - " display.display(display.Markdown(prompt))\n", - " display.display(display.Markdown('-------------------------------'))\n", - " await session.send(prompt, end_of_turn=True)\n", "\n", - " audio = False\n", - " filename = f'audio_{n}.wav'\n", - " with wave_file(filename) as wf:\n", - " async for response in session.receive():\n", - " logger.debug(str(response))\n", - " if text:=response.text:\n", - " display.display(display.Markdown(text))\n", - " continue\n", + "async def run(prompt, modality=\"AUDIO\", tools=None):\n", + " global n\n", + " if tools is None:\n", + " tools = []\n", + "\n", + " config = {\n", + " \"tools\": tools,\n", + " \"system_instruction\": \"You are a helpful HR assistant who can search employees with atlas_search_tool and create teams in the database with create_team tool\",\n", + " \"generation_config\": {\"response_modalities\": [modality]},\n", + " }\n", + " print(f\"before client invoke {tools}\")\n", + " async with client.aio.live.connect(model=model_name, config=config) as session:\n", + " display.display(display.Markdown(prompt))\n", + " display.display(display.Markdown(\"-------------------------------\"))\n", + " await session.send(prompt, end_of_turn=True)\n", "\n", - " if data:=response.data:\n", - " print('.', end='')\n", - " wf.writeframes(data)\n", - " audio = True\n", - " continue\n", + " audio = False\n", + " filename = f\"audio_{n}.wav\"\n", + " with wave_file(filename) as wf:\n", + " async for response in session.receive():\n", + " logger.debug(str(response))\n", + " if text := response.text:\n", + " display.display(display.Markdown(text))\n", + " continue\n", "\n", - " server_content = response.server_content\n", - " if server_content is not None:\n", - " handle_server_content(wf, server_content)\n", - " continue\n", - " print(f\"Before tool call {response.tool_call}\")\n", + " if data := response.data:\n", + " print(\".\", end=\"\")\n", + " wf.writeframes(data)\n", + " audio = True\n", + " continue\n", "\n", - " tool_call = response.tool_call\n", - " if tool_call is not None:\n", - " await handle_tool_call(session, tool_call)\n", + " server_content = response.server_content\n", + " if server_content is not None:\n", + " handle_server_content(wf, server_content)\n", + " continue\n", + " print(f\"Before tool call {response.tool_call}\")\n", "\n", + " tool_call = response.tool_call\n", + " if tool_call is not None:\n", + " await handle_tool_call(session, tool_call)\n", "\n", - " if audio:\n", - " display.display(display.Audio(filename, autoplay=True))\n", - " n = n+1" + " if audio:\n", + " display.display(display.Audio(filename, autoplay=True))\n", + " n = n + 1" ] }, { @@ -339,27 +338,32 @@ "outputs": [], "source": [ "def handle_server_content(wf, server_content):\n", - " model_turn = server_content.model_turn\n", - " if model_turn:\n", - " for part in model_turn.parts:\n", - " executable_code = part.executable_code\n", - " if executable_code is not None:\n", - " display.display(display.Markdown('-------------------------------'))\n", - " display.display(display.Markdown(f'``` python\\n{executable_code.code}\\n```'))\n", - " display.display(display.Markdown('-------------------------------'))\n", + " model_turn = server_content.model_turn\n", + " if model_turn:\n", + " for part in model_turn.parts:\n", + " executable_code = part.executable_code\n", + " if executable_code is not None:\n", + " display.display(display.Markdown(\"-------------------------------\"))\n", + " display.display(\n", + " display.Markdown(f\"``` python\\n{executable_code.code}\\n```\")\n", + " )\n", + " display.display(display.Markdown(\"-------------------------------\"))\n", "\n", - " code_execution_result = part.code_execution_result\n", - " if code_execution_result is not None:\n", - " display.display(display.Markdown('-------------------------------'))\n", - " display.display(display.Markdown(f'```\\n{code_execution_result.output}\\n```'))\n", - " display.display(display.Markdown('-------------------------------'))\n", + " code_execution_result = part.code_execution_result\n", + " if code_execution_result is not None:\n", + " display.display(display.Markdown(\"-------------------------------\"))\n", + " display.display(\n", + " display.Markdown(f\"```\\n{code_execution_result.output}\\n```\")\n", + " )\n", + " display.display(display.Markdown(\"-------------------------------\"))\n", "\n", - " grounding_metadata = getattr(server_content, 'grounding_metadata', None)\n", - " if grounding_metadata is not None:\n", - " display.display(\n", - " display.HTML(grounding_metadata.search_entry_point.rendered_content))\n", + " grounding_metadata = getattr(server_content, \"grounding_metadata\", None)\n", + " if grounding_metadata is not None:\n", + " display.display(\n", + " display.HTML(grounding_metadata.search_entry_point.rendered_content)\n", + " )\n", "\n", - " return" + " return" ] }, { @@ -382,27 +386,31 @@ "outputs": [], "source": [ "import json\n", + "\n", + "\n", "async def handle_tool_call(session, tool_call):\n", - " for fc in tool_call.function_calls:\n", - " function_name = fc.name\n", - " arguments = fc.args\n", - " if function_name == \"create_team\":\n", - " team = arguments.get(\"team_data\")\n", - " result = create_team(team.get('name'), team.get('people'))\n", - " elif function_name == \"atlas_search_tool\":\n", - " result = atlas_search(arguments.get(\"query\"), arguments.get(\"k\", 5))\n", - " else:\n", - " result = \"Unknown function\"\n", - " tool_response = types.LiveClientToolResponse(\n", - " function_responses=[types.FunctionResponse(\n", - " name=fc.name,\n", - " id=fc.id,\n", - " response={'result': result},\n", - " )]\n", - " )\n", + " for fc in tool_call.function_calls:\n", + " function_name = fc.name\n", + " arguments = fc.args\n", + " if function_name == \"create_team\":\n", + " team = arguments.get(\"team_data\")\n", + " result = create_team(team.get(\"name\"), team.get(\"people\"))\n", + " elif function_name == \"atlas_search_tool\":\n", + " result = atlas_search(arguments.get(\"query\"), arguments.get(\"k\", 5))\n", + " else:\n", + " result = \"Unknown function\"\n", + " tool_response = types.LiveClientToolResponse(\n", + " function_responses=[\n", + " types.FunctionResponse(\n", + " name=fc.name,\n", + " id=fc.id,\n", + " response={\"result\": result},\n", + " )\n", + " ]\n", + " )\n", "\n", - " print('\\n>>> ', tool_response)\n", - " await session.send(tool_response)" + " print(\"\\n>>> \", tool_response)\n", + " await session.send(tool_response)" ] }, { @@ -483,7 +491,7 @@ } ], "source": [ - "await run(prompt=\"Hello?\", tools=None, modality = \"AUDIO\")" + "await run(prompt=\"Hello?\", tools=None, modality=\"AUDIO\")" ] }, { @@ -501,10 +509,7 @@ "source": [ "### MongoDB Vector Database and Connection Setup\n", "\n", - "MongoDB acts as both an operational and a vector database for the RAG system.\n", - "MongoDB Atlas specifically provides a database solution that efficiently stores, queries and retrieves vector embeddings.\n", - "\n", - "Creating a database and collection within MongoDB is made simple with MongoDB Atlas.\n", + "MongoDB acts as both an operational and a vector database for the RAG system. Creating a database and collection within MongoDB is made simple with MongoDB Atlas.\n", "\n", "1. First, register for a [MongoDB Atlas account](https://www.mongodb.com/cloud/atlas/register). For existing users, sign into MongoDB Atlas.\n", "2. [Follow the instructions](https://www.mongodb.com/docs/atlas/tutorial/deploy-free-tier-cluster/). Select Atlas UI as the procedure to deploy your first cluster." @@ -665,7 +670,7 @@ "id": "KJT6axzPeUvq" }, "source": [ - "# Prepare MongoDB Atlas vector store\n", + "# Prepare MongoDB vector store\n", "\n", "Run the following code to create the MongoDB Vector Search index and insert some vectorised employee records for our database." ] @@ -713,35 +718,32 @@ "# Create the search index\n", "## create index\n", "search_index_model = SearchIndexModel(\n", - " definition={\n", - " \"fields\": [\n", - " {\n", - " \"type\": \"vector\",\n", - " \"numDimensions\": 768,\n", - " \"path\": \"embedding\",\n", - " \"similarity\": \"cosine\"\n", - " },\n", - " ]\n", - " },\n", - " name=\"vector_index\",\n", - " type=\"vectorSearch\",\n", + " definition={\n", + " \"fields\": [\n", + " {\n", + " \"type\": \"vector\",\n", + " \"numDimensions\": 768,\n", + " \"path\": \"embedding\",\n", + " \"similarity\": \"cosine\",\n", + " },\n", + " ]\n", + " },\n", + " name=\"vector_index\",\n", + " type=\"vectorSearch\",\n", ")\n", "result = collection.create_search_index(model=search_index_model)\n", "print(\"New search index named \" + result + \" is building.\")\n", "# Wait for initial sync to complete\n", "print(\"Polling to check if the index is ready. This may take up to a minute.\")\n", - "predicate=None\n", + "predicate = None\n", "if predicate is None:\n", - " predicate = lambda index: index.get(\"queryable\") is True\n", + " predicate = lambda index: index.get(\"queryable\") is True\n", "while True:\n", - " indices = list(collection.list_search_indexes(result))\n", - " if len(indices) and predicate(indices[0]):\n", - " break\n", - " time.sleep(5)\n", - "print(result + \" is ready for querying.\")\n", - "\n", - "\n", - "\n" + " indices = list(collection.list_search_indexes(result))\n", + " if len(indices) and predicate(indices[0]):\n", + " break\n", + " time.sleep(5)\n", + "print(result + \" is ready for querying.\")" ] }, { @@ -764,7 +766,7 @@ "source": [ "## Insert Employee Data\n", "\n", - "In this section, we will insert sample employee data into the MongoDB Atlas vector store. This data includes employee details such as name, department, location, and salary, along with their respective embeddings." + "In this section, we will insert sample employee data into the MongoDB Vector Store. This data includes employee details such as name, department, location, and salary, along with their respective embeddings." ] }, { @@ -792,4652 +794,4654 @@ "source": [ "## Insert data\n", "\n", - "collection.insert_many([{\n", - " \"_id\": \"54634\",\n", - " \"content\": \"Employee number 54634, name Jane Doe, department Marketing, location Los Angeles, salary 120000\",\n", - " \"embedding\": [\n", - " 0.024926867,\n", - " -0.049224764,\n", - " 0.0051397122,\n", - " -0.015662413,\n", - " 0.036198545,\n", - " 0.020058708,\n", - " 0.07437574,\n", - " -0.023353964,\n", - " 0.009316206,\n", - " 0.010908616,\n", - " -0.022639172,\n", - " 0.008110297,\n", - " -0.03569339,\n", - " 0.016980717,\n", - " -0.014814842,\n", - " 0.0048693726,\n", - " 0.0024207153,\n", - " -0.036100663,\n", - " -0.016500184,\n", - " -0.033307776,\n", - " -0.020310277,\n", - " -0.01708344,\n", - " -0.017491976,\n", - " -0.01000457,\n", - " 0.021011023,\n", - " -0.0017388392,\n", - " 0.00891552,\n", - " -0.10860842,\n", - " -0.046374027,\n", - " -0.01210933,\n", - " -0.043089807,\n", - " 0.027616654,\n", - " -0.058572993,\n", - " -0.0012424898,\n", - " -0.0009245786,\n", - " -0.026917346,\n", - " -0.026614873,\n", - " -0.008031103,\n", - " 0.006364708,\n", - " 0.022180663,\n", - " -0.029214343,\n", - " -0.020451233,\n", - " -0.013976919,\n", - " -0.011516259,\n", - " 0.027531886,\n", - " -0.020989226,\n", - " 0.0011997295,\n", - " -0.008541397,\n", - " 0.013981253,\n", - " -0.09130217,\n", - " 0.031902086,\n", - " -0.014483433,\n", - " 0.04141627,\n", - " -0.022633772,\n", - " -0.0015243818,\n", - " -0.0701282,\n", - " -0.005745007,\n", - " 0.003046663,\n", - " -0.00138343,\n", - " -0.0483541,\n", - " -0.018663412,\n", - " -0.010342808,\n", - " -0.036891118,\n", - " 0.041526485,\n", - " -0.0070978166,\n", - " -0.056960497,\n", - " -0.00027713762,\n", - " 0.00041085767,\n", - " 0.0638381,\n", - " 0.012412274,\n", - " -0.042297978,\n", - " -0.034797642,\n", - " 0.027877614,\n", - " -0.014577787,\n", - " -0.07915758,\n", - " -0.11489053,\n", - " -0.012170335,\n", - " 0.023879664,\n", - " 0.040547226,\n", - " 0.027829757,\n", - " -0.019437442,\n", - " -0.03378374,\n", - " -0.026225261,\n", - " -0.042423252,\n", - " -0.034459304,\n", - " 0.07092275,\n", - " 0.04282131,\n", - " -0.019700523,\n", - " -0.022706546,\n", - " 0.07524933,\n", - " -0.025327584,\n", - " 0.03845969,\n", - " -0.006575861,\n", - " -0.05432576,\n", - " -0.0030720695,\n", - " 0.06054884,\n", - " 0.014463371,\n", - " -0.05177936,\n", - " 0.011856342,\n", - " -0.01622149,\n", - " -0.015594266,\n", - " -0.023064198,\n", - " -0.056572527,\n", - " -0.01887025,\n", - " 0.009372615,\n", - " -0.005908454,\n", - " -0.019093627,\n", - " -0.010138043,\n", - " -0.03215679,\n", - " 0.023405561,\n", - " -0.07793633,\n", - " 0.0022705605,\n", - " -0.03748151,\n", - " -0.040298775,\n", - " 0.05949639,\n", - " -0.02171212,\n", - " -0.05205988,\n", - " 0.056799524,\n", - " 0.046728708,\n", - " 0.00995629,\n", - " 0.018814746,\n", - " 0.052283265,\n", - " 0.0133213885,\n", - " 0.0070853233,\n", - " 0.02381203,\n", - " 0.048278138,\n", - " -0.025068594,\n", - " 0.013948586,\n", - " 0.10241069,\n", - " 0.033334825,\n", - " -0.035002332,\n", - " -0.028427497,\n", - " 0.036363285,\n", - " -0.009638689,\n", - " 0.050988846,\n", - " 0.088660076,\n", - " 0.052428994,\n", - " 0.008259064,\n", - " 0.051591944,\n", - " -0.035510417,\n", - " -0.0025276055,\n", - " 0.020777041,\n", - " -0.02206114,\n", - " 0.00075541,\n", - " -0.038383663,\n", - " 0.0068223546,\n", - " 0.013984699,\n", - " -0.04017368,\n", - " 0.046198152,\n", - " -0.015898008,\n", - " -0.016150242,\n", - " -0.006470939,\n", - " -0.046308447,\n", - " 0.033918925,\n", - " 0.021597652,\n", - " 0.009154935,\n", - " -0.03465381,\n", - " 0.0016349686,\n", - " 0.019491052,\n", - " 0.023978025,\n", - " 0.059030097,\n", - " 0.03193792,\n", - " -0.026359702,\n", - " 0.025488824,\n", - " 0.0014710033,\n", - " 0.021635707,\n", - " 0.028962605,\n", - " -0.0426874,\n", - " -0.025902368,\n", - " -0.03850525,\n", - " -0.0072347843,\n", - " 0.019107448,\n", - " -0.039649457,\n", - " -0.04149649,\n", - " -0.0390399,\n", - " -0.073608436,\n", - " 0.005187664,\n", - " -0.012122672,\n", - " -0.02703804,\n", - " -0.025964485,\n", - " -0.041734103,\n", - " -0.029006453,\n", - " 0.020049337,\n", - " 0.04200867,\n", - " -0.0018111905,\n", - " 0.03557779,\n", - " 0.058680393,\n", - " -0.045999996,\n", - " 0.0054121087,\n", - " -0.028696584,\n", - " 0.036451954,\n", - " -0.00065523863,\n", - " -0.014693241,\n", - " -0.0049391747,\n", - " -0.013985914,\n", - " 0.029479476,\n", - " 0.005661245,\n", - " 0.034519162,\n", - " -0.0017001618,\n", - " -0.014198862,\n", - " -0.044131663,\n", - " 0.04520943,\n", - " 0.021466821,\n", - " -0.0052906116,\n", - " 0.024838196,\n", - " -0.036314182,\n", - " 0.06807027,\n", - " -0.046411086,\n", - " 0.012543244,\n", - " -0.0015524302,\n", - " -0.005904932,\n", - " 0.03395419,\n", - " -0.012026594,\n", - " -0.030101227,\n", - " 0.028219236,\n", - " 0.030846382,\n", - " 0.004014791,\n", - " 0.0011687118,\n", - " -0.005924506,\n", - " -0.045966923,\n", - " 0.011490533,\n", - " 0.0070699626,\n", - " -0.04636452,\n", - " 0.051188413,\n", - " -0.010941066,\n", - " -0.0003843776,\n", - " -0.03554462,\n", - " 0.031527005,\n", - " 0.009976034,\n", - " -0.07566613,\n", - " 0.009484453,\n", - " 0.075585775,\n", - " 0.036681112,\n", - " -0.01997137,\n", - " 0.04221241,\n", - " 0.028756386,\n", - " -0.0051457584,\n", - " 0.017223062,\n", - " -0.026450416,\n", - " -0.0031493392,\n", - " -0.031142443,\n", - " 0.014129824,\n", - " 0.030640334,\n", - " 0.029624552,\n", - " -0.028791834,\n", - " 0.014263747,\n", - " -0.052234437,\n", - " 0.016012207,\n", - " 0.0054665036,\n", - " 0.049960792,\n", - " 0.01722948,\n", - " -0.045383565,\n", - " 0.035611328,\n", - " 0.017666759,\n", - " -0.034179296,\n", - " 0.029283382,\n", - " -0.0925589,\n", - " 0.005352651,\n", - " 0.015380154,\n", - " -0.025827546,\n", - " 0.078813694,\n", - " 0.023472652,\n", - " -0.015502742,\n", - " -0.0109618185,\n", - " -0.062091105,\n", - " 0.020872923,\n", - " 0.0000086566615,\n", - " -0.046515323,\n", - " -0.010241027,\n", - " 0.07056774,\n", - " -0.0039463,\n", - " -0.0049326513,\n", - " 0.08365995,\n", - " 0.04134926,\n", - " 0.028786693,\n", - " 0.003118606,\n", - " -0.00762385,\n", - " 0.0374987,\n", - " 0.011105095,\n", - " -0.063480176,\n", - " 0.0057922564,\n", - " 0.031258017,\n", - " 0.016701866,\n", - " -0.028914252,\n", - " -0.003122066,\n", - " 0.0040146816,\n", - " -0.042392317,\n", - " 0.007909141,\n", - " -0.0074412455,\n", - " -0.061981037,\n", - " -0.0753461,\n", - " -0.017482404,\n", - " 0.0019353802,\n", - " -0.039474253,\n", - " -0.03557083,\n", - " 0.02512347,\n", - " -0.03232185,\n", - " 0.029252835,\n", - " 0.0036022866,\n", - " -0.0006892634,\n", - " 0.020094976,\n", - " -0.038219,\n", - " -0.017786479,\n", - " -0.08057002,\n", - " 0.031012703,\n", - " 0.0027172887,\n", - " 0.008962194,\n", - " -0.052723087,\n", - " -0.010544319,\n", - " -0.015351896,\n", - " 0.032455456,\n", - " -0.018037044,\n", - " -0.031501703,\n", - " -0.00675466,\n", - " 0.0221693,\n", - " 0.045492973,\n", - " -0.0019718895,\n", - " -0.036067158,\n", - " -0.019214695,\n", - " 0.092174225,\n", - " 0.0011163659,\n", - " 0.020685544,\n", - " 0.042855497,\n", - " -0.037252106,\n", - " 0.0040059835,\n", - " 0.01912792,\n", - " -0.015698344,\n", - " 0.04483261,\n", - " -0.004036565,\n", - " 0.034471065,\n", - " -0.00026268934,\n", - " 0.021624925,\n", - " -0.029354827,\n", - " 0.047258046,\n", - " 0.00198258,\n", - " 0.030219225,\n", - " -0.070994265,\n", - " -0.012291296,\n", - " -0.06872952,\n", - " -0.01746057,\n", - " 0.051459547,\n", - " -0.005943351,\n", - " -0.05806519,\n", - " -0.049041413,\n", - " -0.0029545315,\n", - " -0.03594199,\n", - " -0.02741998,\n", - " 0.023392593,\n", - " 0.06987801,\n", - " 0.03409129,\n", - " 0.010657495,\n", - " 0.029227218,\n", - " -0.016149484,\n", - " -0.033026453,\n", - " -0.026461514,\n", - " -0.029547209,\n", - " 0.052853283,\n", - " -0.005257883,\n", - " 0.019270778,\n", - " -0.021651607,\n", - " -0.0679393,\n", - " 0.022915237,\n", - " -0.018916594,\n", - " 0.020382203,\n", - " 0.0061164782,\n", - " -0.0053500766,\n", - " 0.04022389,\n", - " 0.010382376,\n", - " 0.0037303683,\n", - " 0.00038739407,\n", - " 0.043591883,\n", - " -0.050327547,\n", - " -0.0032173207,\n", - " 0.02382172,\n", - " -0.018193057,\n", - " -0.049482215,\n", - " -0.034972608,\n", - " -0.03591731,\n", - " 0.055168044,\n", - " 0.04351997,\n", - " 0.042791825,\n", - " 0.014279212,\n", - " 0.007098134,\n", - " 0.041995537,\n", - " 0.02505999,\n", - " -0.014369368,\n", - " 0.022210745,\n", - " 0.035329152,\n", - " -0.0018724868,\n", - " 0.04496197,\n", - " -0.015458536,\n", - " -0.035687756,\n", - " 0.11576407,\n", - " 0.014072529,\n", - " 0.01368354,\n", - " -0.044601526,\n", - " -0.017274825,\n", - " -0.035651878,\n", - " 0.018606395,\n", - " -0.02624995,\n", - " -0.008605139,\n", - " -0.05559558,\n", - " -0.031822406,\n", - " -0.0025050528,\n", - " -0.007260074,\n", - " 0.008371022,\n", - " -0.009121923,\n", - " -0.010686996,\n", - " -0.004175405,\n", - " -0.07709291,\n", - " 0.02095484,\n", - " 0.061555583,\n", - " 0.05423064,\n", - " -0.08377491,\n", - " -0.044701204,\n", - " -0.022143545,\n", - " 0.03825245,\n", - " 0.020806536,\n", - " -0.025773121,\n", - " 0.026748922,\n", - " -0.035925206,\n", - " 0.007971478,\n", - " -0.07475945,\n", - " -0.067393735,\n", - " -0.01523033,\n", - " -0.025753228,\n", - " 0.0007241217,\n", - " -0.016581649,\n", - " -0.017368209,\n", - " 0.008112616,\n", - " -0.008466575,\n", - " -0.009379433,\n", - " 0.013422547,\n", - " 0.010592169,\n", - " -0.0036504674,\n", - " -0.041012507,\n", - " -0.018081397,\n", - " 0.005491686,\n", - " -0.02313517,\n", - " 0.010353996,\n", - " 0.06254845,\n", - " -0.029144084,\n", - " 0.07706289,\n", - " -0.002867055,\n", - " -0.022228312,\n", - " -0.028821543,\n", - " 0.00022086965,\n", - " -0.05151184,\n", - " 0.0114417225,\n", - " -0.10001401,\n", - " -0.007430506,\n", - " -0.0810789,\n", - " -0.0106861945,\n", - " -0.022859078,\n", - " -0.011867412,\n", - " -0.03224893,\n", - " 0.017619586,\n", - " 0.07519098,\n", - " -0.0035126992,\n", - " 0.005702041,\n", - " 0.0050863526,\n", - " -0.024752518,\n", - " -0.051708452,\n", - " -0.08042799,\n", - " -0.0016043095,\n", - " -0.054452665,\n", - " 0.04997996,\n", - " -0.022929264,\n", - " 0.07225404,\n", - " 0.057153042,\n", - " 0.016426055,\n", - " -0.04732747,\n", - " 0.015056493,\n", - " 0.036387,\n", - " -0.011774074,\n", - " -0.01798128,\n", - " -0.018891433,\n", - " 0.027562132,\n", - " 0.026849896,\n", - " -0.027375022,\n", - " 0.014004462,\n", - " -0.04581184,\n", - " 0.062606476,\n", - " -0.028271144,\n", - " -0.03200168,\n", - " 0.01676934,\n", - " 0.005372289,\n", - " -0.039633606,\n", - " 0.013623909,\n", - " 0.0483795,\n", - " 0.025562169,\n", - " -0.0007961121,\n", - " -0.010983261,\n", - " -0.03702811,\n", - " -0.020723386,\n", - " 0.01622944,\n", - " 0.028984541,\n", - " 0.052704614,\n", - " 0.026976695,\n", - " 0.040055428,\n", - " -0.027315127,\n", - " 0.022882,\n", - " -0.004998423,\n", - " 0.005663411,\n", - " 0.05058019,\n", - " 0.025238585,\n", - " -0.0043412056,\n", - " -0.010151074,\n", - " -0.005550237,\n", - " 0.012124635,\n", - " -0.012980639,\n", - " -0.030452866,\n", - " -0.009688401,\n", - " 0.0011759287,\n", - " 0.05065029,\n", - " -0.034934316,\n", - " 0.00009035412,\n", - " 0.0016641455,\n", - " 0.038797174,\n", - " -0.041665185,\n", - " 0.02898577,\n", - " 0.0050686207,\n", - " -0.11780856,\n", - " -0.017124109,\n", - " 0.058547672,\n", - " -0.047212645,\n", - " 0.019724954,\n", - " 0.052281905,\n", - " -0.028578363,\n", - " 0.041821305,\n", - " -0.01702321,\n", - " 0.07445442,\n", - " -0.026752556,\n", - " -0.005502298,\n", - " -0.030765718,\n", - " 0.018439377,\n", - " -0.016507415,\n", - " 0.053340096,\n", - " 0.027617462,\n", - " 0.0028326863,\n", - " 0.043026447,\n", - " -0.036896102,\n", - " 0.015555754,\n", - " -0.028502347,\n", - " -0.027034258,\n", - " 0.024761003,\n", - " 0.06037164,\n", - " -0.088444225,\n", - " 0.020785877,\n", - " 0.01979808,\n", - " -0.024642324,\n", - " 0.030752076,\n", - " 0.04398454,\n", - " -0.018832913,\n", - " -0.019311974,\n", - " 0.027594192,\n", - " -0.029102236,\n", - " -0.009168705,\n", - " -0.012181484,\n", - " -0.023603536,\n", - " -0.019860711,\n", - " -0.0035978511,\n", - " 0.012397888,\n", - " 0.0011611527,\n", - " 0.0898995,\n", - " 0.02485896,\n", - " -0.005481566,\n", - " -0.039879583,\n", - " 0.022059798,\n", - " -0.012275004,\n", - " -0.014664887,\n", - " 0.026405737,\n", - " 0.006707709,\n", - " 0.0036560902,\n", - " 0.07902236,\n", - " -0.037842136,\n", - " -0.034537956,\n", - " 0.028122894,\n", - " -0.010967483,\n", - " 0.002525521,\n", - " 0.06961038,\n", - " 0.016122231,\n", - " -0.03932486,\n", - " 0.024220413,\n", - " -0.042630956,\n", - " 0.02517927,\n", - " 0.054458976,\n", - " 0.013454574,\n", - " 0.06871976,\n", - " -0.0023826372,\n", - " -0.06773266,\n", - " 0.02460262,\n", - " -0.062439863,\n", - " -0.05781772,\n", - " -0.045605063,\n", - " 0.027145335,\n", - " -0.04323481,\n", - " -0.027004242,\n", - " 0.027012022,\n", - " 0.0021861214,\n", - " 0.016324826,\n", - " -0.0575887,\n", - " 0.0639403,\n", - " -0.013034681,\n", - " 0.05562446,\n", - " -0.02185531,\n", - " 0.025901046,\n", - " -0.019938763,\n", - " 0.008652073,\n", - " 0.030600363,\n", - " 0.036625423,\n", - " -0.001488325,\n", - " -0.014308819,\n", - " -0.035884213,\n", - " -0.0443492,\n", - " -0.018744895,\n", - " 0.012494876,\n", - " 0.009342181,\n", - " -0.023556268,\n", - " -0.024485394,\n", - " 0.008759082,\n", - " -0.036470927,\n", - " 0.003922266,\n", - " -0.005570674,\n", - " 0.06833909,\n", - " 0.0064327326,\n", - " -0.018937796,\n", - " -0.00621957,\n", - " 0.062171705,\n", - " 0.038591076,\n", - " 0.031692512,\n", - " 0.041171357,\n", - " 0.021134553,\n", - " -0.0029191682,\n", - " -0.03674039,\n", - " 0.024994813,\n", - " -0.023660952,\n", - " -0.055257946,\n", - " 0.040094994,\n", - " -0.008852677,\n", - " -0.087461375,\n", - " 0.01325573,\n", - " 0.040444717,\n", - " -0.01021572,\n", - " -0.026924513,\n", - " 0.034332998,\n", - " 0.03086733,\n", - " -0.07686781,\n", - " -0.016338205,\n", - " -0.020646619,\n", - " -0.042191442,\n", - " 0.009642032,\n", - " 0.027536497,\n", - " 0.022932088,\n", - " -0.014337762,\n", - " -0.035221837,\n", - " -0.031101929,\n", - " -0.050192293,\n", - " 0.04678706,\n", - " 0.0022375528,\n", - " -0.019851457,\n", - " 0.05928813,\n", - " -0.00034617726,\n", - " 0.02348867,\n", - " -0.005559518,\n", - " 0.024877217,\n", - " 0.006464173,\n", - " -0.061497923,\n", - " -0.044427488,\n", - " 0.09275633,\n", - " -0.060154688,\n", - " 0.035813265,\n", - " 0.008149022,\n", - " -0.021311855,\n", - " 0.06460764,\n", - " 0.074633114,\n", - " -0.055023994,\n", - " 0.008292285,\n", - " 0.0034740432,\n", - " 0.04366205,\n", - " -0.019244209,\n", - " -0.011739611,\n", - " 0.010764034,\n", - " 0.009531266,\n", - " 0.01438961,\n", - " 0.036831133,\n", - " -0.014654368,\n", - " 0.025802445,\n", - " -0.05894489,\n", - " -0.024810959,\n", - " -0.0048909825,\n", - " -0.02695748,\n", - " 0.0062228707,\n", - " -0.029853752,\n", - " 0.07839843,\n", - " 0.025475468,\n", - " 0.03605201,\n", - " -0.013841105,\n", - " 0.034315526,\n", - " 0.05802323,\n", - " -0.0065083285,\n", - " -0.049404792,\n", - " 0.0047248784,\n", - " 0.04340827,\n", - " -0.037954953,\n", - " 0.022516504,\n", - " 0.0039298353,\n", - " 0.00731798,\n", - " 0.03454248,\n", - " -0.01497592,\n", - " 0.04957702,\n", - " -0.056836925,\n", - " -0.039613705,\n", - " 0.030464869,\n", - " 0.03466243,\n", - " -0.0054599266,\n", - " 0.0375021,\n", - " -0.0047780927,\n", - " -0.04908544,\n", - " 0.030942274,\n", - " 0.055504274,\n", - " -0.018186081,\n", - " 0.008902889,\n", - " -0.02538345,\n", - " -0.008923959,\n", - " 0.06603814,\n", - " -0.026365338,\n", - " 0.06799129,\n", - " -0.014765047,\n", - " -0.019033851,\n", - " 0.06114885,\n", - " -0.04529476,\n", - " -0.03121909,\n", - " 0.035800617,\n", - " -0.033105463,\n", - " 0.0592133,\n", - " 0.015604761,\n", - " 0.039122812,\n", - " -0.009252219,\n", - " -0.06183396,\n", - " -0.04536972,\n", - " 0.035133872,\n", - " 0.028567217,\n", - " 0.028155535,\n", - " 0.044882603,\n", - " -0.018319324,\n", - " 0.023039794,\n", - " 0.0067167506,\n", - " -0.026577776,\n", - " -0.058001574,\n", - " -0.104534015,\n", - " 0.042269215,\n", - " 0.004363603,\n", - " 0.048697747,\n", - " 0.04533539,\n", - " -0.05496062,\n", - " -0.021759328,\n", - " -0.004851495,\n", - " 0.03850219,\n", - " 0.020519726,\n", - " -0.04097515,\n", - " -0.001369751,\n", - " -0.016953135,\n", - " 0.046057485,\n", - " 0.005478688,\n", - " 0.033872366,\n", - " -0.01388759,\n", - " 0.026152821\n", - " ]\n", - "},\n", - "{\n", - " \"_id\": \"54633\",\n", - " \"content\": \"Employee number 54633, name John Doe, department Sales, location New York, salary 100000\",\n", - " \"embedding\": [\n", - " 0.02363214,\n", - " -0.064981155,\n", - " -0.015693784,\n", - " -0.0007628399,\n", - " 0.053643532,\n", - " 0.03410332,\n", - " 0.061779644,\n", - " -0.018410124,\n", - " 0.00021801237,\n", - " 0.010404121,\n", - " -0.034521878,\n", - " -0.0018919241,\n", - " -0.031763557,\n", - " -0.021995055,\n", - " -0.028728155,\n", - " 0.021817293,\n", - " 0.017098326,\n", - " -0.023482114,\n", - " 0.00035919988,\n", - " -0.030648591,\n", - " -0.040644307,\n", - " -0.022990027,\n", - " -0.03393246,\n", - " -0.006558424,\n", - " 0.02599438,\n", - " -0.002243526,\n", - " -0.005706434,\n", - " -0.09497937,\n", - " -0.041159507,\n", - " -0.014462122,\n", - " -0.07141966,\n", - " 0.036013767,\n", - " -0.040423963,\n", - " 0.015345732,\n", - " -0.010977615,\n", - " -0.031959552,\n", - " -0.04254595,\n", - " 0.0140362885,\n", - " -0.0050170403,\n", - " 0.0062000453,\n", - " -0.03828404,\n", - " -0.0153707955,\n", - " -0.02084843,\n", - " -0.029029334,\n", - " 0.0488787,\n", - " 0.0116918655,\n", - " -0.0008196994,\n", - " 0.02450069,\n", - " 0.012549454,\n", - " -0.098332606,\n", - " 0.034913078,\n", - " -0.011317091,\n", - " 0.05609082,\n", - " -0.023273163,\n", - " -0.018277766,\n", - " -0.06916207,\n", - " 0.00826931,\n", - " 0.010393335,\n", - " -0.01787084,\n", - " -0.042722043,\n", - " -0.011604089,\n", - " -0.0012522464,\n", - " -0.014621865,\n", - " 0.038314685,\n", - " 0.0005260519,\n", - " -0.06758038,\n", - " -0.018045135,\n", - " 0.010444268,\n", - " 0.07087152,\n", - " -0.00284572,\n", - " -0.037000503,\n", - " -0.0025446592,\n", - " 0.04700479,\n", - " -0.001956285,\n", - " -0.052959703,\n", - " -0.12006671,\n", - " -0.0042574876,\n", - " 0.033431716,\n", - " 0.053164013,\n", - " 0.045192037,\n", - " 0.0069061965,\n", - " -0.015518668,\n", - " -0.030133313,\n", - " -0.044831418,\n", - " -0.03726597,\n", - " 0.057425573,\n", - " 0.038113765,\n", - " -0.027094543,\n", - " -0.007922181,\n", - " 0.04684854,\n", - " -0.019562198,\n", - " 0.030295257,\n", - " -0.004370621,\n", - " -0.058695186,\n", - " -0.018610591,\n", - " 0.061370887,\n", - " 0.030731026,\n", - " -0.04589357,\n", - " 0.009940706,\n", - " -0.01948416,\n", - " -0.0046085874,\n", - " 0.0022432224,\n", - " -0.037660263,\n", - " 0.0066369097,\n", - " 0.024275409,\n", - " -0.00056191423,\n", - " -0.000042045995,\n", - " -0.011206171,\n", - " -0.045394268,\n", - " 0.0071125193,\n", - " -0.07760038,\n", - " 0.00075220404,\n", - " -0.01073115,\n", - " -0.04549924,\n", - " 0.06086503,\n", - " -0.039449498,\n", - " -0.058962233,\n", - " 0.06468895,\n", - " 0.04064492,\n", - " 0.0028264702,\n", - " 0.046224788,\n", - " 0.054499805,\n", - " 0.017846588,\n", - " 0.039633967,\n", - " 0.043515794,\n", - " 0.045659285,\n", - " -0.008033441,\n", - " 0.017785944,\n", - " 0.110720046,\n", - " 0.04685865,\n", - " -0.01802922,\n", - " -0.040406503,\n", - " 0.046266943,\n", - " -0.013695085,\n", - " 0.049763296,\n", - " 0.06897263,\n", - " 0.04518968,\n", - " 0.053687356,\n", - " 0.047708154,\n", - " -0.034360345,\n", - " -0.006671896,\n", - " 0.001714356,\n", - " -0.04809813,\n", - " -0.014786435,\n", - " -0.017878355,\n", - " -0.008214343,\n", - " -0.0021909962,\n", - " -0.046269346,\n", - " 0.072654426,\n", - " -0.017648848,\n", - " 0.024896594,\n", - " -0.007919613,\n", - " -0.022969129,\n", - " 0.03022781,\n", - " 0.011041212,\n", - " 0.02506789,\n", - " -0.042059314,\n", - " -0.012793883,\n", - " 0.014914554,\n", - " -0.0069050984,\n", - " 0.04926195,\n", - " 0.029791638,\n", - " 0.00091826794,\n", - " 0.022105714,\n", - " 0.02267874,\n", - " 0.01301686,\n", - " 0.041148506,\n", - " -0.040438164,\n", - " -0.017320365,\n", - " -0.03499895,\n", - " 0.021354463,\n", - " 0.01690759,\n", - " -0.025965609,\n", - " -0.031534,\n", - " -0.030494336,\n", - " -0.07054347,\n", - " -0.013133889,\n", - " -0.012822187,\n", - " -0.029168444,\n", - " -0.0218087,\n", - " -0.026540095,\n", - " -0.03263288,\n", - " 0.0021044614,\n", - " 0.048010275,\n", - " -0.01386612,\n", - " 0.038521104,\n", - " 0.04187871,\n", - " -0.043820612,\n", - " 0.01064401,\n", - " -0.02302523,\n", - " 0.036518324,\n", - " 0.02567038,\n", - " -0.02029525,\n", - " -0.008654853,\n", - " 0.006971086,\n", - " 0.031201571,\n", - " 0.025180522,\n", - " 0.04371456,\n", - " 0.003744122,\n", - " -0.030606078,\n", - " -0.057033766,\n", - " 0.07168329,\n", - " 0.008192757,\n", - " 0.0008544097,\n", - " 0.021805858,\n", - " -0.03130309,\n", - " 0.07239574,\n", - " -0.070142336,\n", - " -0.008480367,\n", - " -0.008728997,\n", - " -0.0034903064,\n", - " 0.046792153,\n", - " -0.023682427,\n", - " -0.030346792,\n", - " 0.019847026,\n", - " 0.012278681,\n", - " -0.0025996969,\n", - " 0.031041447,\n", - " -0.0077332347,\n", - " -0.038237624,\n", - " 0.012388913,\n", - " 0.0188294,\n", - " -0.02149499,\n", - " 0.051257458,\n", - " 0.002782599,\n", - " -0.010533314,\n", - " 0.0011125503,\n", - " 0.012332888,\n", - " 0.01806485,\n", - " -0.06757561,\n", - " 0.0023377982,\n", - " 0.09027674,\n", - " 0.0307473,\n", - " -0.0031313177,\n", - " 0.031805944,\n", - " 0.02137824,\n", - " -0.015408471,\n", - " 0.00030692422,\n", - " -0.020330938,\n", - " 0.023312671,\n", - " -0.030245807,\n", - " 0.025795639,\n", - " 0.04197928,\n", - " 0.00660178,\n", - " -0.040649693,\n", - " 0.024375524,\n", - " -0.04237185,\n", - " 0.032011457,\n", - " 0.015374865,\n", - " 0.04028766,\n", - " 0.010178039,\n", - " -0.03617627,\n", - " 0.047202107,\n", - " 0.020767882,\n", - " -0.04539947,\n", - " 0.019767804,\n", - " -0.10889575,\n", - " 0.017927451,\n", - " 0.017144594,\n", - " -0.015266046,\n", - " 0.06631826,\n", - " 0.02412635,\n", - " -0.024798216,\n", - " -0.008509299,\n", - " -0.0639002,\n", - " 0.0136915855,\n", - " 0.0027062744,\n", - " -0.064476475,\n", - " -0.0012653655,\n", - " 0.07816678,\n", - " -0.012643878,\n", - " -0.008585973,\n", - " 0.07736182,\n", - " 0.04327385,\n", - " 0.025656862,\n", - " 0.0030979763,\n", - " 0.00021765077,\n", - " 0.031746045,\n", - " 0.02362011,\n", - " -0.04819947,\n", - " -0.012916141,\n", - " 0.018860366,\n", - " 0.017766127,\n", - " -0.023901632,\n", - " 0.004137154,\n", - " 0.0041561704,\n", - " -0.0022801503,\n", - " 0.009764509,\n", - " 0.002656565,\n", - " -0.04468994,\n", - " -0.07757732,\n", - " -0.015850794,\n", - " 0.010670362,\n", - " -0.04420402,\n", - " -0.039033562,\n", - " 0.0031982567,\n", - " -0.04361803,\n", - " 0.034209713,\n", - " 0.005868743,\n", - " 0.032322675,\n", - " 0.039166275,\n", - " -0.03746624,\n", - " -0.021231664,\n", - " -0.06653363,\n", - " 0.059266083,\n", - " 0.016893726,\n", - " 0.022510596,\n", - " -0.06638812,\n", - " -0.026510475,\n", - " -0.011830923,\n", - " 0.0069003874,\n", - " -0.043289896,\n", - " -0.03288132,\n", - " -0.011146353,\n", - " 0.0287577,\n", - " 0.04004958,\n", - " -0.0014789595,\n", - " -0.02158115,\n", - " -0.012407836,\n", - " 0.073853076,\n", - " 0.021458639,\n", - " 0.020401636,\n", - " 0.039237395,\n", - " -0.025395788,\n", - " -0.005443788,\n", - " 0.030352518,\n", - " -0.035680313,\n", - " 0.032063533,\n", - " 0.0016429706,\n", - " 0.01741445,\n", - " 0.0024685974,\n", - " 0.034620967,\n", - " -0.010647702,\n", - " 0.0526942,\n", - " -0.0034993906,\n", - " 0.03208014,\n", - " -0.08731866,\n", - " -0.015013707,\n", - " -0.06679643,\n", - " -0.015791807,\n", - " 0.033754732,\n", - " -0.00432221,\n", - " -0.049488492,\n", - " -0.04113329,\n", - " -0.025805045,\n", - " -0.01941248,\n", - " -0.027105281,\n", - " -0.0048762094,\n", - " 0.063147336,\n", - " 0.041223466,\n", - " 0.028617661,\n", - " 0.021648958,\n", - " -0.041316215,\n", - " -0.0313366,\n", - " -0.035062548,\n", - " -0.033159826,\n", - " 0.040288758,\n", - " 0.0010510484,\n", - " 0.007258658,\n", - " -0.032413058,\n", - " -0.061028056,\n", - " 0.031196948,\n", - " -0.021832671,\n", - " 0.014297596,\n", - " 0.01129684,\n", - " -0.014241179,\n", - " 0.019869702,\n", - " 0.02111102,\n", - " 0.0012747784,\n", - " -0.019946355,\n", - " 0.05248107,\n", - " -0.062233597,\n", - " 0.015092951,\n", - " 0.009568825,\n", - " -0.013843593,\n", - " -0.053562496,\n", - " -0.061670925,\n", - " -0.035305984,\n", - " 0.032908812,\n", - " 0.04857493,\n", - " 0.034953453,\n", - " 0.023726141,\n", - " 0.03568444,\n", - " 0.0071175913,\n", - " 0.033559702,\n", - " -0.0121424105,\n", - " 0.03407673,\n", - " 0.057266288,\n", - " -0.012657767,\n", - " 0.06768064,\n", - " -0.022355225,\n", - " -0.030181471,\n", - " 0.12063107,\n", - " 0.012808932,\n", - " 0.030716958,\n", - " -0.036874283,\n", - " -0.008254023,\n", - " -0.01081548,\n", - " 0.020372739,\n", - " -0.027203616,\n", - " 0.0015654373,\n", - " -0.039488234,\n", - " -0.022952735,\n", - " -0.0011268638,\n", - " -0.009785246,\n", - " -0.0019360933,\n", - " 0.016225388,\n", - " -0.018154368,\n", - " -0.014471327,\n", - " -0.05883742,\n", - " 0.012274111,\n", - " 0.06887592,\n", - " 0.052230723,\n", - " -0.06945254,\n", - " -0.036823668,\n", - " -0.012421808,\n", - " 0.035832312,\n", - " 0.02932272,\n", - " -0.013966943,\n", - " 0.057543058,\n", - " -0.023411168,\n", - " 0.025161343,\n", - " -0.0649318,\n", - " -0.06453301,\n", - " -0.024157293,\n", - " -0.03283516,\n", - " 0.0070455656,\n", - " -0.024008652,\n", - " -0.022920165,\n", - " 0.015138752,\n", - " 0.010144105,\n", - " -0.008382338,\n", - " 0.044042453,\n", - " 0.018641355,\n", - " -0.00897114,\n", - " -0.022986831,\n", - " -0.024504658,\n", - " 0.005061791,\n", - " -0.046147745,\n", - " 0.017877372,\n", - " 0.055260062,\n", - " -0.03701096,\n", - " 0.075398736,\n", - " 0.008653546,\n", - " -0.021892056,\n", - " -0.020546617,\n", - " 0.014034242,\n", - " -0.072182335,\n", - " 0.013067999,\n", - " -0.100795396,\n", - " 0.010451056,\n", - " -0.07050469,\n", - " -0.011445101,\n", - " -0.03754845,\n", - " 0.006183421,\n", - " -0.03906792,\n", - " -0.0055965204,\n", - " 0.05707792,\n", - " -0.010429032,\n", - " -0.0011429724,\n", - " 0.005118022,\n", - " -0.016644083,\n", - " -0.04220137,\n", - " -0.07363171,\n", - " 0.0024569791,\n", - " -0.036916792,\n", - " 0.03395262,\n", - " -0.02537861,\n", - " 0.07667082,\n", - " 0.035887685,\n", - " 0.015899615,\n", - " -0.07066271,\n", - " 0.0015284163,\n", - " 0.044092063,\n", - " -0.00084555487,\n", - " -0.031053497,\n", - " -0.009409518,\n", - " 0.019150222,\n", - " 0.039110914,\n", - " -0.026089815,\n", - " 0.025691986,\n", - " -0.052151006,\n", - " 0.072509676,\n", - " -0.024798574,\n", - " -0.03921443,\n", - " 0.008295112,\n", - " -0.00042773844,\n", - " -0.041100286,\n", - " 0.030542733,\n", - " 0.039614253,\n", - " 0.01804182,\n", - " -0.0019106811,\n", - " -0.0048501906,\n", - " -0.03208538,\n", - " -0.0050331447,\n", - " 0.026386712,\n", - " 0.024575505,\n", - " 0.05588996,\n", - " 0.030057926,\n", - " 0.01409509,\n", - " -0.031694356,\n", - " 0.017517397,\n", - " 0.0046301717,\n", - " 0.007145245,\n", - " 0.07115179,\n", - " 0.0035148985,\n", - " -0.014188136,\n", - " 0.007305263,\n", - " -0.0128924055,\n", - " 0.0012173483,\n", - " -0.010264721,\n", - " -0.013301308,\n", - " -0.021946715,\n", - " 0.012608889,\n", - " 0.06063012,\n", - " -0.02197872,\n", - " 0.011334535,\n", - " -0.017498214,\n", - " 0.040217794,\n", - " -0.029707987,\n", - " 0.03888635,\n", - " 0.007113082,\n", - " -0.10245564,\n", - " 0.019598834,\n", - " 0.042800713,\n", - " -0.068540476,\n", - " -0.007941252,\n", - " 0.029602854,\n", - " 0.012320459,\n", - " 0.04070456,\n", - " 0.0048046396,\n", - " 0.057080273,\n", - " -0.041693073,\n", - " 0.0165682,\n", - " -0.037762154,\n", - " 0.030711599,\n", - " -0.023082186,\n", - " 0.06444822,\n", - " 0.02103803,\n", - " -0.0064671254,\n", - " 0.035683487,\n", - " -0.04167311,\n", - " 0.0337175,\n", - " -0.020304035,\n", - " -0.043164253,\n", - " 0.033318438,\n", - " 0.051226508,\n", - " -0.09993186,\n", - " 0.023990132,\n", - " 0.035067804,\n", - " -0.02158245,\n", - " 0.02973254,\n", - " 0.045522075,\n", - " -0.037720405,\n", - " -0.016477076,\n", - " 0.017233508,\n", - " -0.031183288,\n", - " -0.002931218,\n", - " -0.006327033,\n", - " -0.018274536,\n", - " -0.0043489537,\n", - " -0.010508976,\n", - " 0.010018209,\n", - " 0.029612847,\n", - " 0.092786245,\n", - " 0.030959306,\n", - " -0.006647051,\n", - " -0.027481854,\n", - " 0.033632692,\n", - " -0.023163252,\n", - " -0.010413391,\n", - " 0.04556712,\n", - " -0.0027589782,\n", - " 0.029712437,\n", - " 0.06004067,\n", - " -0.030746799,\n", - " -0.03539816,\n", - " 0.02215609,\n", - " -0.008097731,\n", - " 0.0035610283,\n", - " 0.060080826,\n", - " -0.0088831335,\n", - " -0.019353531,\n", - " 0.012506012,\n", - " -0.04578203,\n", - " 0.026642656,\n", - " 0.034759957,\n", - " 0.03317829,\n", - " 0.06778447,\n", - " -0.0039658644,\n", - " -0.055566087,\n", - " 0.023027683,\n", - " -0.041180346,\n", - " -0.035393525,\n", - " -0.027815914,\n", - " 0.014628632,\n", - " -0.040841658,\n", - " -0.02875485,\n", - " 0.017050356,\n", - " -0.018104397,\n", - " 0.032889456,\n", - " -0.052504424,\n", - " 0.05182534,\n", - " -0.024680488,\n", - " 0.05011892,\n", - " -0.030946976,\n", - " 0.012457738,\n", - " -0.028428216,\n", - " 0.044254918,\n", - " 0.026299495,\n", - " 0.041920617,\n", - " -0.01592546,\n", - " -0.026756888,\n", - " -0.021019576,\n", - " -0.031648703,\n", - " -0.008724201,\n", - " 0.0025635513,\n", - " 0.0113416435,\n", - " -0.04281193,\n", - " -0.042036083,\n", - " -0.0067297197,\n", - " -0.043461386,\n", - " 0.00083167566,\n", - " -0.009508976,\n", - " 0.059358858,\n", - " -0.014656265,\n", - " -0.00035070922,\n", - " -0.0049913535,\n", - " 0.034104995,\n", - " 0.044627994,\n", - " 0.04142639,\n", - " 0.038221695,\n", - " 0.024629146,\n", - " -0.010383416,\n", - " -0.008619005,\n", - " 0.029898448,\n", - " -0.040645078,\n", - " -0.055725325,\n", - " 0.029977558,\n", - " -0.018410092,\n", - " -0.11042691,\n", - " 0.012425915,\n", - " 0.040628515,\n", - " -0.014945932,\n", - " -0.021799535,\n", - " 0.041060366,\n", - " 0.028451148,\n", - " -0.046030525,\n", - " -0.017889444,\n", - " -0.017596401,\n", - " -0.016248139,\n", - " -0.013585491,\n", - " 0.012225498,\n", - " 0.022918489,\n", - " -0.0130026005,\n", - " -0.036756888,\n", - " -0.015256263,\n", - " -0.06046553,\n", - " 0.034536958,\n", - " 0.010706609,\n", - " -0.01574817,\n", - " 0.054597396,\n", - " 0.010708762,\n", - " 0.02091631,\n", - " 0.007813075,\n", - " 0.035738565,\n", - " 0.0096743,\n", - " -0.05741579,\n", - " -0.034075104,\n", - " 0.06407018,\n", - " -0.058274616,\n", - " 0.040782902,\n", - " 0.019084051,\n", - " -0.028117944,\n", - " 0.097568005,\n", - " 0.06757993,\n", - " -0.04616895,\n", - " 0.01835175,\n", - " 0.009599453,\n", - " 0.009899384,\n", - " -0.006697724,\n", - " -0.030587083,\n", - " -0.0057633854,\n", - " -0.0035771965,\n", - " 0.005236175,\n", - " 0.03161966,\n", - " -0.0014421007,\n", - " 0.02654683,\n", - " -0.06784111,\n", - " -0.033109434,\n", - " 0.0015561683,\n", - " -0.028957006,\n", - " -0.010133545,\n", - " -0.009049643,\n", - " 0.095160015,\n", - " 0.038473047,\n", - " 0.015532988,\n", - " -0.026837075,\n", - " 0.004548446,\n", - " 0.036702897,\n", - " 0.0034548303,\n", - " -0.04240495,\n", - " 0.0085659055,\n", - " 0.03814674,\n", - " -0.02157155,\n", - " 0.03191628,\n", - " 0.0018405454,\n", - " -0.004841512,\n", - " 0.016154964,\n", - " -0.022462817,\n", - " 0.04318009,\n", - " -0.055848856,\n", - " -0.037207298,\n", - " 0.05138956,\n", - " 0.047032602,\n", - " -0.02519051,\n", - " 0.021451518,\n", - " 0.004464725,\n", - " -0.055046022,\n", - " 0.02026468,\n", - " 0.056096263,\n", - " -0.031548444,\n", - " 0.03434432,\n", - " -0.048271492,\n", - " 0.0059668403,\n", - " 0.07247701,\n", - " -0.01061879,\n", - " 0.054317787,\n", - " -0.026415752,\n", - " -0.024185874,\n", - " 0.08290211,\n", - " -0.029081488,\n", - " -0.03949319,\n", - " 0.055290263,\n", - " -0.030485872,\n", - " 0.06952478,\n", - " 0.011051205,\n", - " 0.032816757,\n", - " -0.012162714,\n", - " -0.03957713,\n", - " -0.04050204,\n", - " 0.027956164,\n", - " 0.016105121,\n", - " 0.0035087462,\n", - " 0.04936729,\n", - " -0.04183739,\n", - " 0.0054607657,\n", - " 0.00022244385,\n", - " -0.048364908,\n", - " -0.05708388,\n", - " -0.05690664,\n", - " 0.02973829,\n", - " -0.0031154295,\n", - " 0.025180794,\n", - " 0.05131079,\n", - " -0.052830625,\n", - " -0.022286385,\n", - " 0.0075936974,\n", - " 0.016310522,\n", - " 0.027947418,\n", - " -0.04063135,\n", - " 0.0024504068,\n", - " 0.011263393,\n", - " 0.021755524,\n", - " -0.018598292,\n", - " 0.038954616,\n", - " -0.0022197817,\n", - " 0.0030547322\n", - " ]\n", - "},\n", - "{\n", - " \"_id\": \"54636\",\n", - " \"content\": \"Employee number 54636, name Jane Smith, department Finance, location Chicago, salary 130000\",\n", - " \"embedding\": [\n", - " 0.033282682,\n", - " -0.03909191,\n", - " 0.0007547619,\n", - " -0.00166024,\n", - " 0.039782085,\n", - " 0.0022312212,\n", - " 0.050308637,\n", - " 0.0008865104,\n", - " 0.0044103186,\n", - " 0.03072421,\n", - " -0.0051613366,\n", - " -0.026194286,\n", - " -0.013544969,\n", - " -0.011848663,\n", - " -0.047196925,\n", - " -0.0067790328,\n", - " 0.027002288,\n", - " -0.020260727,\n", - " -0.0076200166,\n", - " -0.03599207,\n", - " -0.035114743,\n", - " -0.023491457,\n", - " -0.0077283946,\n", - " -0.026173472,\n", - " 0.021463424,\n", - " 0.0039335107,\n", - " 0.018358603,\n", - " -0.106973566,\n", - " -0.042405866,\n", - " -0.018040666,\n", - " -0.06100321,\n", - " 0.017380144,\n", - " -0.02887869,\n", - " 0.04157278,\n", - " -0.026515594,\n", - " 0.002928644,\n", - " -0.012694755,\n", - " 0.012007126,\n", - " 0.0037733233,\n", - " 0.046051748,\n", - " 0.005322323,\n", - " 0.0059584975,\n", - " -0.009696193,\n", - " -0.0066717616,\n", - " 0.0436459,\n", - " -0.022382155,\n", - " 0.032507967,\n", - " -0.0065392246,\n", - " 0.025054803,\n", - " -0.08322342,\n", - " 0.046882447,\n", - " -0.024875944,\n", - " 0.06102459,\n", - " -0.008675405,\n", - " -0.0209155,\n", - " -0.07849695,\n", - " 0.0020140782,\n", - " -0.0011147283,\n", - " -0.019611986,\n", - " -0.025552176,\n", - " -0.027990913,\n", - " 0.0037930773,\n", - " -0.009247857,\n", - " 0.052749302,\n", - " -0.0102324905,\n", - " -0.062436964,\n", - " -0.02680414,\n", - " 0.0022140676,\n", - " 0.06792232,\n", - " 0.003922225,\n", - " -0.032647397,\n", - " -0.03346009,\n", - " 0.07331381,\n", - " -0.019998021,\n", - " -0.06043405,\n", - " -0.07097224,\n", - " -0.018178217,\n", - " 0.007255711,\n", - " 0.05574352,\n", - " 0.03521836,\n", - " -0.008382421,\n", - " -0.0054113218,\n", - " -0.038427114,\n", - " -0.038553275,\n", - " -0.03860179,\n", - " 0.06459174,\n", - " 0.029251965,\n", - " -0.009218864,\n", - " -0.01445029,\n", - " 0.046301886,\n", - " -0.010660837,\n", - " 0.030970545,\n", - " 0.02029129,\n", - " -0.07135827,\n", - " -0.013141149,\n", - " 0.052297823,\n", - " -0.014865988,\n", - " -0.015496633,\n", - " -0.016228134,\n", - " -0.021733683,\n", - " 0.019089619,\n", - " -0.016229896,\n", - " -0.052840963,\n", - " -0.008882637,\n", - " -0.006283083,\n", - " 0.0034171198,\n", - " -0.009800554,\n", - " -0.00035290318,\n", - " -0.025829503,\n", - " 0.02211951,\n", - " -0.071032286,\n", - " -0.021045374,\n", - " -0.025188517,\n", - " -0.048652653,\n", - " 0.07619293,\n", - " -0.010589923,\n", - " -0.059194453,\n", - " 0.053808484,\n", - " 0.041753646,\n", - " 0.0038279262,\n", - " 0.027524192,\n", - " 0.059054792,\n", - " -0.0120413685,\n", - " 0.008316597,\n", - " 0.031715844,\n", - " 0.03668256,\n", - " -0.01620795,\n", - " 0.00094534125,\n", - " 0.1083495,\n", - " 0.030639175,\n", - " -0.029737566,\n", - " -0.057788074,\n", - " 0.027845988,\n", - " -0.009652855,\n", - " 0.055340156,\n", - " 0.0663029,\n", - " 0.04380604,\n", - " -0.011622515,\n", - " 0.06322969,\n", - " -0.019971412,\n", - " 0.003166246,\n", - " 0.022834063,\n", - " -0.018897917,\n", - " -0.0016617388,\n", - " -0.02413109,\n", - " 0.0017157173,\n", - " 0.010872734,\n", - " -0.011352978,\n", - " 0.006001529,\n", - " 0.015488254,\n", - " 0.0011707869,\n", - " 0.018522937,\n", - " -0.018514102,\n", - " 0.02900784,\n", - " 0.020825073,\n", - " 0.022771334,\n", - " -0.04606071,\n", - " 0.030873852,\n", - " 0.032193057,\n", - " -0.010461426,\n", - " 0.062585354,\n", - " 0.015402362,\n", - " -0.013989444,\n", - " 0.023873847,\n", - " -0.0001557276,\n", - " 0.028785564,\n", - " 0.082039945,\n", - " -0.04562552,\n", - " -0.040299766,\n", - " -0.027677026,\n", - " 0.018488018,\n", - " 0.041104753,\n", - " -0.03979478,\n", - " -0.030792084,\n", - " -0.043800704,\n", - " -0.07498492,\n", - " -0.009120495,\n", - " 0.009481535,\n", - " -0.006981507,\n", - " -0.019725543,\n", - " -0.033017475,\n", - " -0.011190301,\n", - " 0.008700168,\n", - " 0.030437404,\n", - " 0.0058765025,\n", - " 0.03509147,\n", - " 0.04839477,\n", - " -0.04233951,\n", - " -0.0050839223,\n", - " -0.00681981,\n", - " 0.03836845,\n", - " 0.004685588,\n", - " -0.03892133,\n", - " 0.006600561,\n", - " -0.0019655793,\n", - " 0.039389588,\n", - " -0.01809466,\n", - " 0.011489714,\n", - " -0.025835218,\n", - " -0.018884161,\n", - " -0.03204627,\n", - " 0.048295826,\n", - " 0.019568602,\n", - " 0.0053548636,\n", - " 0.033916872,\n", - " -0.015454683,\n", - " 0.05538897,\n", - " -0.033823296,\n", - " -0.0039371606,\n", - " 0.0037781983,\n", - " -0.0023951076,\n", - " 0.031877134,\n", - " -0.028111735,\n", - " -0.015856108,\n", - " 0.038164444,\n", - " 0.012281067,\n", - " 0.011310771,\n", - " 0.004349233,\n", - " -0.014538568,\n", - " -0.029191358,\n", - " -0.006300531,\n", - " 0.019091565,\n", - " -0.056574304,\n", - " 0.06351933,\n", - " 0.0007920405,\n", - " -0.00020863887,\n", - " -0.01369187,\n", - " 0.014471601,\n", - " 0.0048121824,\n", - " -0.06280206,\n", - " -0.0026793373,\n", - " 0.067380674,\n", - " 0.007164001,\n", - " -0.038997144,\n", - " 0.054033946,\n", - " -0.0022533264,\n", - " 0.013708685,\n", - " 0.038419407,\n", - " -0.015276563,\n", - " -0.004239497,\n", - " -0.026898738,\n", - " 0.005635743,\n", - " 0.03847782,\n", - " 0.022422716,\n", - " -0.030474218,\n", - " 0.0047512124,\n", - " -0.04953256,\n", - " 0.015068766,\n", - " 0.020016206,\n", - " 0.042567335,\n", - " 0.0028769623,\n", - " -0.03851735,\n", - " 0.046420325,\n", - " 0.011925669,\n", - " -0.022733988,\n", - " 0.026839085,\n", - " -0.07413135,\n", - " -0.0020509947,\n", - " 0.012577789,\n", - " -0.01844622,\n", - " 0.05583869,\n", - " 0.051888652,\n", - " -0.0048309774,\n", - " 0.009347729,\n", - " -0.049620014,\n", - " 0.047792498,\n", - " -0.01790054,\n", - " -0.0583071,\n", - " -0.021284584,\n", - " 0.06689755,\n", - " 0.004781726,\n", - " -0.012770478,\n", - " 0.07697373,\n", - " 0.03392616,\n", - " 0.014641257,\n", - " 0.008315434,\n", - " 0.004641932,\n", - " 0.057688177,\n", - " -0.00011591461,\n", - " -0.05162363,\n", - " 0.0132949175,\n", - " 0.054461304,\n", - " 0.04132465,\n", - " -0.05228104,\n", - " -0.008330981,\n", - " 0.024090331,\n", - " 0.0035575673,\n", - " 0.020221887,\n", - " 0.0046284744,\n", - " -0.08109927,\n", - " -0.08293294,\n", - " -0.0143710505,\n", - " -0.00088063197,\n", - " -0.066603884,\n", - " -0.05854246,\n", - " 0.023163913,\n", - " -0.048908163,\n", - " 0.016917551,\n", - " 0.0307055,\n", - " 0.006515332,\n", - " 0.0063499426,\n", - " -0.03967575,\n", - " -0.04001876,\n", - " -0.05907809,\n", - " 0.03273935,\n", - " 0.01719176,\n", - " 0.02424203,\n", - " -0.072151884,\n", - " -0.016568365,\n", - " -0.013442307,\n", - " 0.0270092,\n", - " -0.034306023,\n", - " -0.03671066,\n", - " -0.0067472355,\n", - " 0.019714633,\n", - " 0.057815082,\n", - " -0.012577134,\n", - " -0.013382564,\n", - " -0.03911529,\n", - " 0.050835066,\n", - " -0.0037874833,\n", - " -0.008278123,\n", - " 0.042883575,\n", - " -0.052752126,\n", - " -0.0025583908,\n", - " 0.033462517,\n", - " -0.00065002317,\n", - " 0.04533471,\n", - " -0.0154035175,\n", - " 0.031390563,\n", - " -0.0136398645,\n", - " 0.05136288,\n", - " -0.005182816,\n", - " 0.063051686,\n", - " 0.0050854594,\n", - " 0.035023358,\n", - " -0.083840184,\n", - " 0.006783878,\n", - " -0.08204774,\n", - " 0.007304815,\n", - " 0.063131176,\n", - " 0.007564634,\n", - " -0.054168995,\n", - " -0.04331101,\n", - " 0.011824145,\n", - " -0.03706767,\n", - " -0.013556429,\n", - " 0.040878236,\n", - " 0.0807747,\n", - " 0.055227622,\n", - " -0.018239543,\n", - " 0.012912111,\n", - " -0.022989053,\n", - " -0.0028701182,\n", - " -0.031126976,\n", - " -0.0047545466,\n", - " 0.029136088,\n", - " -0.017281001,\n", - " 0.01922514,\n", - " -0.012010304,\n", - " -0.04137593,\n", - " 0.034444544,\n", - " -0.02019,\n", - " 0.019743202,\n", - " 0.011670469,\n", - " -0.007273119,\n", - " 0.013197889,\n", - " 0.028474236,\n", - " -0.01086087,\n", - " 0.021434411,\n", - " 0.024562098,\n", - " -0.04574378,\n", - " 0.0064201616,\n", - " 0.0066477978,\n", - " -0.011263019,\n", - " -0.053637076,\n", - " -0.038792353,\n", - " -0.027472662,\n", - " 0.028990641,\n", - " 0.048245337,\n", - " 0.033630706,\n", - " 0.0068463734,\n", - " -0.008434694,\n", - " 0.05721538,\n", - " 0.032129478,\n", - " 0.00040128073,\n", - " 0.012669716,\n", - " 0.05994472,\n", - " -0.0030158863,\n", - " 0.0371618,\n", - " -0.0053152503,\n", - " -0.016319215,\n", - " 0.11017134,\n", - " -0.0046604937,\n", - " 0.0047023036,\n", - " -0.010484685,\n", - " -0.011737418,\n", - " -0.029090436,\n", - " 0.017523576,\n", - " -0.03561854,\n", - " -0.015012307,\n", - " -0.043565813,\n", - " -0.0042169513,\n", - " -0.015257499,\n", - " -0.0013578214,\n", - " -0.020777592,\n", - " -0.0026453973,\n", - " -0.037206873,\n", - " 0.01621471,\n", - " -0.033481725,\n", - " 0.023214078,\n", - " 0.07240724,\n", - " 0.038964514,\n", - " -0.10446012,\n", - " -0.024342356,\n", - " -0.012709968,\n", - " 0.06211316,\n", - " 0.028951973,\n", - " -0.017876118,\n", - " 0.033162788,\n", - " -0.01688093,\n", - " -0.0017007018,\n", - " -0.06386243,\n", - " -0.06569357,\n", - " -0.019704562,\n", - " 0.0058997083,\n", - " 0.02682609,\n", - " 0.0019023331,\n", - " 0.0017976766,\n", - " 0.047627747,\n", - " -0.0009570554,\n", - " 0.003511069,\n", - " -0.028590811,\n", - " 0.008931729,\n", - " 0.0056299744,\n", - " -0.045468964,\n", - " -0.015844844,\n", - " 0.024054134,\n", - " -0.027469898,\n", - " 0.022173349,\n", - " 0.08148612,\n", - " -0.019955546,\n", - " 0.071963444,\n", - " 0.017910395,\n", - " -0.03124338,\n", - " -0.025000984,\n", - " 0.0054683266,\n", - " -0.043931495,\n", - " 0.0008234161,\n", - " -0.088591345,\n", - " 0.000479956,\n", - " -0.060126673,\n", - " -0.03357947,\n", - " -0.056410566,\n", - " -0.032589775,\n", - " -0.061390713,\n", - " 0.023527699,\n", - " 0.06446886,\n", - " -0.007932508,\n", - " -0.0031587793,\n", - " -0.038047824,\n", - " -0.016549844,\n", - " -0.020477492,\n", - " -0.075683415,\n", - " -0.012110268,\n", - " -0.04891436,\n", - " 0.026568849,\n", - " -0.029075945,\n", - " 0.088291675,\n", - " 0.05912708,\n", - " 0.015805336,\n", - " -0.049823914,\n", - " 0.024532974,\n", - " 0.045406923,\n", - " 0.0095926905,\n", - " -0.020348761,\n", - " -0.027956523,\n", - " 0.030030653,\n", - " 0.04987238,\n", - " -0.032793604,\n", - " -0.011533045,\n", - " -0.023860402,\n", - " 0.062345207,\n", - " -0.019582005,\n", - " -0.031335227,\n", - " 0.04970386,\n", - " -0.023734426,\n", - " -0.021209128,\n", - " 0.026652478,\n", - " 0.030278446,\n", - " 0.0072057345,\n", - " 0.015214752,\n", - " 0.030629016,\n", - " -0.038683932,\n", - " -0.019320292,\n", - " -0.002425624,\n", - " 0.027636893,\n", - " 0.061737496,\n", - " 0.024350017,\n", - " 0.056657396,\n", - " -0.026632559,\n", - " 0.031648163,\n", - " 0.017482013,\n", - " -0.0008389236,\n", - " 0.059907097,\n", - " -0.02123141,\n", - " -0.0025512732,\n", - " 0.0016537616,\n", - " 0.013569981,\n", - " 0.0036193815,\n", - " 0.0020932176,\n", - " -0.024130942,\n", - " 0.0026975519,\n", - " -0.0041695293,\n", - " 0.04122382,\n", - " -0.011495905,\n", - " -0.008079376,\n", - " -0.0057473094,\n", - " 0.039514784,\n", - " -0.04971112,\n", - " 0.038069297,\n", - " -0.026460811,\n", - " -0.09403351,\n", - " 0.0051518404,\n", - " 0.041077457,\n", - " -0.02429841,\n", - " 0.030635186,\n", - " 0.023150187,\n", - " -0.015075604,\n", - " 0.018495653,\n", - " -0.015820375,\n", - " 0.06806306,\n", - " -0.041917916,\n", - " -0.0020552087,\n", - " -0.03989304,\n", - " 0.0018853423,\n", - " -0.03138397,\n", - " 0.043138567,\n", - " 0.03781449,\n", - " -0.022061005,\n", - " 0.05022614,\n", - " -0.024115918,\n", - " 0.060577173,\n", - " -0.015132834,\n", - " -0.036388364,\n", - " -0.008102943,\n", - " 0.04300946,\n", - " -0.06315613,\n", - " 0.0036877454,\n", - " 0.01845251,\n", - " -0.01958063,\n", - " 0.020833353,\n", - " 0.04074978,\n", - " -0.016953025,\n", - " -0.022429537,\n", - " 0.014793756,\n", - " -0.040389486,\n", - " -0.013773572,\n", - " -0.009218371,\n", - " 0.005113001,\n", - " -0.05334978,\n", - " -0.017054679,\n", - " 0.0047935587,\n", - " 0.008970996,\n", - " 0.090954326,\n", - " 0.040972985,\n", - " -0.012958875,\n", - " -0.048973564,\n", - " 0.036145844,\n", - " -0.014689881,\n", - " -0.019061541,\n", - " 0.011643549,\n", - " 0.0013238543,\n", - " 0.010562913,\n", - " 0.05699919,\n", - " -0.033291608,\n", - " -0.038737576,\n", - " 0.033350945,\n", - " 0.004073598,\n", - " -0.0031493988,\n", - " 0.064587645,\n", - " 0.0049619107,\n", - " -0.033150792,\n", - " 0.009891267,\n", - " -0.05739713,\n", - " 0.037735194,\n", - " 0.062099792,\n", - " -0.0033623695,\n", - " 0.07860333,\n", - " 0.009854467,\n", - " -0.06447139,\n", - " 0.031053409,\n", - " -0.058900006,\n", - " -0.05029678,\n", - " -0.027897462,\n", - " 0.056934282,\n", - " -0.023755403,\n", - " -0.02699664,\n", - " 0.0148529,\n", - " -0.01666892,\n", - " -0.0018880437,\n", - " -0.0457452,\n", - " 0.053869832,\n", - " -0.017661236,\n", - " 0.041393574,\n", - " -0.029723926,\n", - " 0.035513297,\n", - " -0.033740062,\n", - " 0.017888788,\n", - " 0.025985245,\n", - " 0.04350399,\n", - " -0.005232885,\n", - " -0.0005693812,\n", - " -0.0033883732,\n", - " -0.037065566,\n", - " -0.02527872,\n", - " -0.0013861161,\n", - " -0.009989347,\n", - " 0.017875295,\n", - " -0.024106601,\n", - " 0.019750569,\n", - " -0.010035022,\n", - " 0.023742517,\n", - " -0.011065428,\n", - " 0.033420607,\n", - " 0.010958177,\n", - " -0.01141841,\n", - " 0.004739421,\n", - " 0.09271151,\n", - " 0.058798864,\n", - " 0.052398294,\n", - " 0.024582228,\n", - " 0.031933635,\n", - " -0.005510293,\n", - " -0.055356447,\n", - " 0.04904649,\n", - " -0.016862152,\n", - " -0.057705753,\n", - " 0.024840772,\n", - " -0.00048015165,\n", - " -0.10546246,\n", - " 0.033585515,\n", - " 0.054793786,\n", - " -0.0070182765,\n", - " -0.031317633,\n", - " 0.034208145,\n", - " 0.015181784,\n", - " -0.062814064,\n", - " -0.019155085,\n", - " -0.03985083,\n", - " -0.0043001687,\n", - " -0.027612321,\n", - " 0.025576307,\n", - " 0.020972272,\n", - " -0.015960751,\n", - " -0.03785616,\n", - " -0.03439213,\n", - " -0.035648625,\n", - " 0.03173273,\n", - " 0.030685507,\n", - " -0.018922847,\n", - " 0.067803204,\n", - " -0.0148015395,\n", - " 0.044523258,\n", - " 0.0061558536,\n", - " 0.0054381737,\n", - " 0.016035475,\n", - " -0.07147066,\n", - " -0.04419202,\n", - " 0.07741728,\n", - " -0.045105446,\n", - " 0.03828778,\n", - " 0.0073140706,\n", - " -0.05118925,\n", - " 0.061084356,\n", - " 0.05001082,\n", - " -0.041532677,\n", - " -0.0016793367,\n", - " 0.019244568,\n", - " 0.005559429,\n", - " 0.017637422,\n", - " -0.012980126,\n", - " 0.013700538,\n", - " 0.04216373,\n", - " 0.026694974,\n", - " 0.043757316,\n", - " 0.012165836,\n", - " 0.023159562,\n", - " -0.056082647,\n", - " -0.030905947,\n", - " 0.016382935,\n", - " -0.0074324473,\n", - " -0.016718535,\n", - " -0.0066933725,\n", - " 0.07567363,\n", - " -0.009259794,\n", - " 0.019372217,\n", - " 0.014743861,\n", - " 0.020617943,\n", - " 0.057029292,\n", - " 0.0050983094,\n", - " -0.032250557,\n", - " 0.013374774,\n", - " 0.047974505,\n", - " -0.049952496,\n", - " 0.012993495,\n", - " 0.02056461,\n", - " -0.0057155536,\n", - " 0.021704368,\n", - " -0.0010753982,\n", - " 0.03720598,\n", - " -0.062292766,\n", - " -0.03158331,\n", - " 0.04137522,\n", - " 0.013299325,\n", - " 0.0049977377,\n", - " 0.04511127,\n", - " -0.013574835,\n", - " -0.033320617,\n", - " 0.0153828645,\n", - " 0.05682976,\n", - " -0.015472821,\n", - " -0.0013420929,\n", - " -0.054665994,\n", - " -0.0047995877,\n", - " 0.056595206,\n", - " -0.03133152,\n", - " 0.08055057,\n", - " -0.019866763,\n", - " -0.008866304,\n", - " 0.10177134,\n", - " -0.035269864,\n", - " -0.027235541,\n", - " 0.04055463,\n", - " -0.0308909,\n", - " 0.08752392,\n", - " 0.036332566,\n", - " 0.022787439,\n", - " -0.036100462,\n", - " -0.08477476,\n", - " -0.059534717,\n", - " 0.03207563,\n", - " 0.013661438,\n", - " 0.013927431,\n", - " 0.025811398,\n", - " -0.025891041,\n", - " 0.030257259,\n", - " -0.020082533,\n", - " -0.010865357,\n", - " -0.07682985,\n", - " -0.08710289,\n", - " 0.026793221,\n", - " -0.03599497,\n", - " 0.036737897,\n", - " 0.038387842,\n", - " -0.067557946,\n", - " -0.018947005,\n", - " -0.020812513,\n", - " 0.04308112,\n", - " 0.0135874795,\n", - " -0.026089147,\n", - " -0.00018917858,\n", - " -0.033624545,\n", - " 0.038969826,\n", - " 0.027176073,\n", - " 0.034541093,\n", - " -0.0001338307,\n", - " 0.009559905\n", - " ]\n", - "},\n", - "{\n", - " \"_id\": \"54635\",\n", - " \"content\": \"Employee number 54635, name John Smith, department Engineering, location San Francisco, salary 150000\",\n", - " \"embedding\": [\n", - " 0.02751842,\n", - " -0.035257466,\n", - " -0.017211914,\n", - " -0.00021509113,\n", - " 0.065513395,\n", - " 0.015236125,\n", - " 0.046573777,\n", - " -0.027342448,\n", - " 0.013279674,\n", - " 0.015880402,\n", - " -0.0026871182,\n", - " -0.020755854,\n", - " -0.028976398,\n", - " -0.025017332,\n", - " -0.02915205,\n", - " 0.03748723,\n", - " 0.026784075,\n", - " -0.008561052,\n", - " 0.0061514685,\n", - " -0.08216181,\n", - " -0.012679269,\n", - " -0.019104697,\n", - " -0.035561316,\n", - " -0.013733142,\n", - " -0.002272582,\n", - " -0.014719888,\n", - " 0.030248245,\n", - " -0.08619838,\n", - " -0.03771919,\n", - " 0.018865846,\n", - " -0.063968174,\n", - " 0.03219376,\n", - " -0.035308257,\n", - " 0.036639687,\n", - " -0.04739701,\n", - " 0.01655839,\n", - " -0.025951466,\n", - " 0.019777248,\n", - " 0.008441114,\n", - " 0.0397848,\n", - " -0.007323799,\n", - " -0.010856907,\n", - " -0.015435451,\n", - " -0.024571002,\n", - " 0.0608382,\n", - " -0.001076124,\n", - " -0.01160508,\n", - " 0.027767012,\n", - " 0.020741891,\n", - " -0.08319567,\n", - " 0.04286476,\n", - " -0.0065871845,\n", - " 0.030671211,\n", - " -0.008211031,\n", - " -0.05312356,\n", - " -0.07651591,\n", - " -0.013340908,\n", - " -0.012418467,\n", - " -0.02554261,\n", - " -0.027668754,\n", - " -0.028723458,\n", - " 0.0072301184,\n", - " 0.018877236,\n", - " 0.03554761,\n", - " -0.004688246,\n", - " -0.07433135,\n", - " -0.0035417427,\n", - " -0.006659041,\n", - " 0.04192288,\n", - " -0.0207361,\n", - " -0.006254261,\n", - " -0.024812873,\n", - " 0.059861075,\n", - " -0.03134214,\n", - " -0.07463872,\n", - " -0.11254215,\n", - " -0.007414231,\n", - " 0.01804921,\n", - " 0.057197362,\n", - " 0.02665551,\n", - " 0.0064427084,\n", - " -0.013575005,\n", - " -0.029392047,\n", - " -0.012261425,\n", - " -0.030408913,\n", - " 0.074111775,\n", - " 0.016163299,\n", - " -0.017348083,\n", - " -0.027919967,\n", - " 0.040365145,\n", - " 0.016613623,\n", - " 0.0008838358,\n", - " 0.035404228,\n", - " -0.07160502,\n", - " -0.014951479,\n", - " 0.06784549,\n", - " 0.0066313925,\n", - " -0.052722607,\n", - " -0.029260378,\n", - " -0.053105693,\n", - " -0.0045598387,\n", - " -0.05004554,\n", - " -0.052556243,\n", - " -0.0067943437,\n", - " 0.019090641,\n", - " 0.007432553,\n", - " -0.020073954,\n", - " -0.0042186803,\n", - " -0.005367988,\n", - " 0.018064711,\n", - " -0.073992364,\n", - " -0.017997328,\n", - " -0.032181244,\n", - " -0.04996697,\n", - " 0.06846196,\n", - " -0.03522803,\n", - " -0.035346393,\n", - " 0.07071394,\n", - " 0.041346475,\n", - " 0.007324973,\n", - " 0.08921032,\n", - " 0.068063006,\n", - " 0.020346623,\n", - " 0.040123172,\n", - " -0.010046104,\n", - " 0.025201118,\n", - " -0.003961309,\n", - " 0.023122495,\n", - " 0.09587856,\n", - " 0.05031979,\n", - " -0.01057047,\n", - " -0.04394514,\n", - " 0.034751166,\n", - " -0.014335325,\n", - " 0.03341888,\n", - " 0.05706479,\n", - " 0.05054945,\n", - " 0.004166189,\n", - " 0.061515614,\n", - " -0.022616953,\n", - " -0.0050968137,\n", - " 0.0010603444,\n", - " -0.030782396,\n", - " 0.008184928,\n", - " -0.011474374,\n", - " 0.003339862,\n", - " -0.0067458292,\n", - " -0.010549199,\n", - " 0.027625475,\n", - " -0.0020265754,\n", - " 0.006763103,\n", - " 0.009542199,\n", - " -0.03164191,\n", - " 0.027494777,\n", - " 0.015781684,\n", - " 0.010094312,\n", - " -0.026690045,\n", - " 0.027364649,\n", - " 0.020415021,\n", - " -0.0379163,\n", - " 0.032620024,\n", - " 0.040363166,\n", - " -0.005355615,\n", - " 0.02923704,\n", - " 0.0073294668,\n", - " 0.008268878,\n", - " 0.046909377,\n", - " -0.035831597,\n", - " -0.037963904,\n", - " -0.05067842,\n", - " -0.023855058,\n", - " 0.031068098,\n", - " -0.060321517,\n", - " -0.017361106,\n", - " -0.03714339,\n", - " -0.052008033,\n", - " -0.017402591,\n", - " -0.0000853109,\n", - " -0.01522777,\n", - " 0.004505938,\n", - " -0.035380103,\n", - " -0.04122089,\n", - " 0.017592149,\n", - " 0.017477088,\n", - " 0.009680622,\n", - " 0.0601484,\n", - " 0.053315826,\n", - " -0.04279214,\n", - " 0.009589118,\n", - " -0.010029888,\n", - " 0.020045798,\n", - " 0.024653148,\n", - " -0.023524566,\n", - " 0.011961308,\n", - " 0.0017022899,\n", - " 0.029609565,\n", - " 0.028629072,\n", - " 0.021015882,\n", - " 0.00012135336,\n", - " -0.04946617,\n", - " -0.034740772,\n", - " 0.031152897,\n", - " 0.027573282,\n", - " -0.017018853,\n", - " 0.020141952,\n", - " -0.020575022,\n", - " 0.08574167,\n", - " -0.025361745,\n", - " 0.0000718993,\n", - " 0.07202345,\n", - " -0.035066936,\n", - " 0.042211156,\n", - " -0.02737654,\n", - " -0.007903302,\n", - " 0.055386215,\n", - " 0.03386666,\n", - " 0.007098444,\n", - " -0.0011916764,\n", - " -0.0077267145,\n", - " -0.039679147,\n", - " 0.0109159555,\n", - " 0.013889261,\n", - " -0.020267498,\n", - " 0.057652816,\n", - " -0.01675666,\n", - " -0.01046991,\n", - " 0.0063280216,\n", - " 0.036489647,\n", - " 0.014317979,\n", - " -0.04359035,\n", - " -0.0038247926,\n", - " 0.03433474,\n", - " 0.0046200114,\n", - " -0.028734986,\n", - " 0.033694655,\n", - " -0.0072179954,\n", - " 0.0065697636,\n", - " 0.0035546091,\n", - " -0.018106835,\n", - " 0.0008928709,\n", - " -0.04377693,\n", - " 0.015936524,\n", - " 0.026221775,\n", - " 0.004182328,\n", - " -0.055179127,\n", - " 0.010751439,\n", - " -0.038998943,\n", - " 0.039809167,\n", - " -0.015138335,\n", - " 0.009765969,\n", - " -0.0081632165,\n", - " -0.05567452,\n", - " 0.05554104,\n", - " 0.026053185,\n", - " -0.05740401,\n", - " 0.03465235,\n", - " -0.076469,\n", - " 0.0015592162,\n", - " 0.009639975,\n", - " -0.030025609,\n", - " 0.05954854,\n", - " 0.021440376,\n", - " -0.006658576,\n", - " 0.02273896,\n", - " -0.031426214,\n", - " 0.040050857,\n", - " -0.021161372,\n", - " -0.068565525,\n", - " -0.028184833,\n", - " 0.068864435,\n", - " -0.005223995,\n", - " -0.006345874,\n", - " 0.07794489,\n", - " 0.046531476,\n", - " 0.035680976,\n", - " -0.010769412,\n", - " -0.006249256,\n", - " 0.041365553,\n", - " 0.003833638,\n", - " -0.058614638,\n", - " -0.0052710325,\n", - " 0.07343842,\n", - " 0.03782047,\n", - " -0.046215393,\n", - " -0.029175224,\n", - " 0.011108449,\n", - " -0.0022866763,\n", - " 0.010857836,\n", - " 0.008042948,\n", - " -0.07578336,\n", - " -0.09506901,\n", - " 0.0028703813,\n", - " -0.017622843,\n", - " -0.05017095,\n", - " -0.06601734,\n", - " 0.016744547,\n", - " -0.030435143,\n", - " 0.010448069,\n", - " 0.023559375,\n", - " 0.003017711,\n", - " -0.010440744,\n", - " -0.051503733,\n", - " -0.031850483,\n", - " -0.06224817,\n", - " 0.03302146,\n", - " 0.0022398247,\n", - " 0.012647616,\n", - " -0.05779213,\n", - " -0.012409115,\n", - " -0.01943723,\n", - " 0.027941398,\n", - " -0.022145638,\n", - " -0.015692553,\n", - " -0.0011641445,\n", - " 0.026432425,\n", - " 0.05613625,\n", - " 0.010688817,\n", - " -0.014724717,\n", - " -0.029040305,\n", - " 0.07541772,\n", - " -0.0038578296,\n", - " 0.0063860323,\n", - " 0.028974347,\n", - " -0.048377227,\n", - " -0.0020083082,\n", - " 0.061093163,\n", - " -0.0015345091,\n", - " 0.04327932,\n", - " -0.006280553,\n", - " -0.004461047,\n", - " -0.004969216,\n", - " 0.079298794,\n", - " 0.005280641,\n", - " 0.075993665,\n", - " -0.00903695,\n", - " 0.01402909,\n", - " -0.088527754,\n", - " 0.007002133,\n", - " -0.06112628,\n", - " -0.025775367,\n", - " 0.035340235,\n", - " 0.011317101,\n", - " -0.058157604,\n", - " -0.057730775,\n", - " -0.030742848,\n", - " -0.024909437,\n", - " -0.01292577,\n", - " 0.025219142,\n", - " 0.07330923,\n", - " 0.04195776,\n", - " 0.0330579,\n", - " 0.027340477,\n", - " -0.018308474,\n", - " -0.040544774,\n", - " -0.043364618,\n", - " -0.017788624,\n", - " 0.024081899,\n", - " -0.02448898,\n", - " 0.025725441,\n", - " -0.014032703,\n", - " -0.03716917,\n", - " 0.030908864,\n", - " 0.0046337834,\n", - " -0.017839137,\n", - " 0.025155617,\n", - " -0.005961568,\n", - " 0.0017926248,\n", - " 0.010721402,\n", - " 0.008076512,\n", - " 0.000014950954,\n", - " 0.03687499,\n", - " -0.080296755,\n", - " -0.0022581385,\n", - " 0.0135227805,\n", - " -0.007616169,\n", - " -0.059810784,\n", - " -0.06190626,\n", - " -0.022344204,\n", - " 0.04095455,\n", - " 0.024678344,\n", - " 0.040884405,\n", - " 0.01146623,\n", - " -0.010222091,\n", - " 0.023510607,\n", - " 0.013003448,\n", - " -0.024498258,\n", - " 0.01566375,\n", - " 0.03966229,\n", - " -0.013284801,\n", - " 0.05625292,\n", - " 0.0035774496,\n", - " -0.041765593,\n", - " 0.075709105,\n", - " 0.0025806301,\n", - " 0.002827293,\n", - " -0.0127510615,\n", - " 0.0076297605,\n", - " -0.018482147,\n", - " 0.0195352,\n", - " -0.008572333,\n", - " -0.023895975,\n", - " -0.022642754,\n", - " -0.021384051,\n", - " -0.025655594,\n", - " 0.011634965,\n", - " -0.040602997,\n", - " -0.0025013296,\n", - " -0.019177016,\n", - " 0.025949784,\n", - " -0.044972513,\n", - " 0.036257338,\n", - " 0.07511653,\n", - " 0.036459416,\n", - " -0.115887314,\n", - " -0.03673168,\n", - " -0.027124275,\n", - " 0.06939686,\n", - " 0.022735972,\n", - " -0.017979583,\n", - " 0.03082303,\n", - " -0.017964998,\n", - " -0.002043333,\n", - " -0.045927435,\n", - " -0.083149225,\n", - " -0.023609241,\n", - " 0.008159602,\n", - " -0.0014957677,\n", - " -0.019364858,\n", - " 0.017326526,\n", - " 0.03703413,\n", - " 0.021754017,\n", - " -0.024310483,\n", - " 0.012974437,\n", - " 0.0025437805,\n", - " 0.009190147,\n", - " -0.03622636,\n", - " -0.025097648,\n", - " 0.03175117,\n", - " -0.060564324,\n", - " 0.025262883,\n", - " 0.045786444,\n", - " -0.03756287,\n", - " 0.077972464,\n", - " 0.014882087,\n", - " -0.035983026,\n", - " -0.03335668,\n", - " 0.012810578,\n", - " -0.05117928,\n", - " 0.016779415,\n", - " -0.09439797,\n", - " -0.0063598235,\n", - " -0.046981793,\n", - " -0.0028302062,\n", - " -0.058332726,\n", - " -0.025126418,\n", - " -0.0774988,\n", - " -0.005797502,\n", - " 0.051930707,\n", - " -0.031145284,\n", - " -0.017120061,\n", - " -0.019712316,\n", - " -0.03858973,\n", - " -0.0066188793,\n", - " -0.07773236,\n", - " 0.014307085,\n", - " -0.027230764,\n", - " 0.0331902,\n", - " -0.057089612,\n", - " 0.057789687,\n", - " 0.06540567,\n", - " 0.022184646,\n", - " -0.048069406,\n", - " 0.015343113,\n", - " 0.0558476,\n", - " 0.0001679844,\n", - " -0.019582808,\n", - " -0.026129218,\n", - " 0.030448413,\n", - " 0.03634036,\n", - " -0.041653648,\n", - " -0.03448554,\n", - " -0.023397086,\n", - " 0.076667525,\n", - " -0.009382471,\n", - " -0.03721751,\n", - " 0.023369618,\n", - " -0.014296145,\n", - " -0.008192296,\n", - " -0.009530903,\n", - " 0.03565617,\n", - " 0.017519575,\n", - " 0.02974625,\n", - " 0.003261011,\n", - " -0.048980772,\n", - " -0.011459121,\n", - " -0.020589355,\n", - " 0.00025388523,\n", - " 0.05537085,\n", - " 0.03211041,\n", - " 0.020657161,\n", - " -0.008744432,\n", - " 0.022239113,\n", - " 0.03172477,\n", - " -0.012103961,\n", - " 0.06935857,\n", - " -0.030093772,\n", - " -0.022945607,\n", - " 0.006408147,\n", - " 0.020852357,\n", - " 0.028491085,\n", - " -0.0023250037,\n", - " -0.002611426,\n", - " -0.017636396,\n", - " -0.02044602,\n", - " 0.03541466,\n", - " -0.016902495,\n", - " -0.006867505,\n", - " -0.00012285702,\n", - " 0.017117904,\n", - " -0.020677648,\n", - " 0.0557191,\n", - " -0.015488911,\n", - " -0.10235103,\n", - " -0.0028210408,\n", - " 0.010193204,\n", - " -0.032251876,\n", - " 0.01060267,\n", - " 0.03557713,\n", - " -0.0063216602,\n", - " 0.009259219,\n", - " 0.0051827505,\n", - " 0.038854543,\n", - " -0.031460393,\n", - " -0.0076761693,\n", - " -0.026699234,\n", - " 0.018988753,\n", - " -0.0137761375,\n", - " 0.046094075,\n", - " 0.016433887,\n", - " -0.003973164,\n", - " 0.063081056,\n", - " -0.029332547,\n", - " 0.054982897,\n", - " -0.03574009,\n", - " -0.053488664,\n", - " -0.0065793497,\n", - " 0.04935732,\n", - " -0.07006432,\n", - " 0.02812001,\n", - " 0.00647268,\n", - " -0.0075788135,\n", - " 0.022446249,\n", - " 0.0481543,\n", - " -0.028088065,\n", - " -0.00019163998,\n", - " 0.0115054725,\n", - " -0.045824103,\n", - " -0.0041767946,\n", - " 0.0011554541,\n", - " -0.010604986,\n", - " -0.00820998,\n", - " -0.015158567,\n", - " 0.006710291,\n", - " 0.027485032,\n", - " 0.0827062,\n", - " 0.035160348,\n", - " -0.0056700693,\n", - " -0.06100241,\n", - " 0.03775862,\n", - " -0.055310618,\n", - " 0.0020003193,\n", - " 0.003878855,\n", - " 0.0039324365,\n", - " 0.021707052,\n", - " 0.056594085,\n", - " -0.023516221,\n", - " -0.051027056,\n", - " 0.02914387,\n", - " -0.01747557,\n", - " -0.00048578077,\n", - " 0.06910575,\n", - " -0.02813352,\n", - " -0.0067434846,\n", - " 0.02015622,\n", - " -0.030215016,\n", - " 0.013908208,\n", - " 0.0559234,\n", - " 0.007264178,\n", - " 0.07277442,\n", - " -0.0056195944,\n", - " -0.07750021,\n", - " 0.050576977,\n", - " -0.06140354,\n", - " -0.045618854,\n", - " -0.020566126,\n", - " 0.039101325,\n", - " -0.025846323,\n", - " -0.014014278,\n", - " -0.010953099,\n", - " 0.0053575314,\n", - " 0.01853153,\n", - " -0.059806224,\n", - " 0.079701826,\n", - " -0.026566066,\n", - " 0.040181253,\n", - " -0.02266395,\n", - " 0.0054217833,\n", - " -0.027931219,\n", - " 0.04334095,\n", - " 0.03031099,\n", - " 0.02989241,\n", - " -0.00061276584,\n", - " -0.013604992,\n", - " 0.008013184,\n", - " -0.03547994,\n", - " -0.01926322,\n", - " -0.007489133,\n", - " -0.0029699102,\n", - " -0.010580029,\n", - " -0.018646544,\n", - " 0.0047476776,\n", - " -0.020718446,\n", - " 0.009074871,\n", - " -0.0027520477,\n", - " 0.0387986,\n", - " -0.023973802,\n", - " -0.01189377,\n", - " 0.013701782,\n", - " 0.068496615,\n", - " 0.04820877,\n", - " 0.019212667,\n", - " 0.045648925,\n", - " 0.0318747,\n", - " -0.028331727,\n", - " -0.025103705,\n", - " 0.0328582,\n", - " -0.03484345,\n", - " -0.05530036,\n", - " 0.011778919,\n", - " -0.005664444,\n", - " -0.113750234,\n", - " 0.018433394,\n", - " 0.03918017,\n", - " -0.012234621,\n", - " -0.016486265,\n", - " 0.017421383,\n", - " 0.024043733,\n", - " -0.04742088,\n", - " 0.020483378,\n", - " -0.038147032,\n", - " -0.009845963,\n", - " -0.006499819,\n", - " 0.028929604,\n", - " 0.025346762,\n", - " -0.012089239,\n", - " -0.032945115,\n", - " -0.04614911,\n", - " -0.028733844,\n", - " 0.03818017,\n", - " 0.04198492,\n", - " -0.024049556,\n", - " 0.06125142,\n", - " -0.008327446,\n", - " 0.030352222,\n", - " 0.015361837,\n", - " -0.013292321,\n", - " 0.006475574,\n", - " -0.072518654,\n", - " -0.036767293,\n", - " 0.0740501,\n", - " -0.06637531,\n", - " 0.043207835,\n", - " 0.034058686,\n", - " -0.03576254,\n", - " 0.047720406,\n", - " 0.037699528,\n", - " -0.023285469,\n", - " 0.025489798,\n", - " 0.002287648,\n", - " -0.008411476,\n", - " 0.02260013,\n", - " -0.020512147,\n", - " 0.008027023,\n", - " 0.029532177,\n", - " 0.0059477957,\n", - " 0.04624887,\n", - " 0.021156397,\n", - " 0.036551874,\n", - " -0.041027997,\n", - " -0.049307615,\n", - " 0.02526815,\n", - " -0.02010938,\n", - " -0.019960264,\n", - " -0.014263981,\n", - " 0.079093084,\n", - " 0.010921492,\n", - " 0.018967591,\n", - " -0.008221532,\n", - " 0.0058250814,\n", - " 0.07463721,\n", - " -0.03572568,\n", - " -0.013496767,\n", - " -0.00042068915,\n", - " 0.019645795,\n", - " -0.049485173,\n", - " 0.03608238,\n", - " -0.01177695,\n", - " 0.0020465946,\n", - " 0.012326075,\n", - " -0.0023621495,\n", - " 0.049434356,\n", - " -0.078708716,\n", - " -0.048812617,\n", - " 0.015036083,\n", - " 0.020805584,\n", - " -0.0033854137,\n", - " 0.0066305967,\n", - " 0.015715208,\n", - " -0.027279327,\n", - " 0.03890442,\n", - " 0.028212277,\n", - " -0.025578374,\n", - " -0.0042159823,\n", - " -0.04713265,\n", - " 0.0012227457,\n", - " 0.07078375,\n", - " -0.028477665,\n", - " 0.05951706,\n", - " -0.0190399,\n", - " -0.026970295,\n", - " 0.06499598,\n", - " -0.034548096,\n", - " -0.036340587,\n", - " 0.0422616,\n", - " -0.03698566,\n", - " 0.0678964,\n", - " 0.012707417,\n", - " 0.03466419,\n", - " -0.015625846,\n", - " -0.08137007,\n", - " -0.045645062,\n", - " 0.023715043,\n", - " 0.0023143874,\n", - " 0.008170114,\n", - " 0.041747324,\n", - " -0.022417393,\n", - " 0.011471595,\n", - " -0.020469397,\n", - " -0.02913878,\n", - " -0.07025473,\n", - " -0.07867984,\n", - " 0.025465682,\n", - " -0.026013091,\n", - " -0.011840964,\n", - " 0.047041006,\n", - " -0.058210913,\n", - " -0.027502269,\n", - " -0.01028805,\n", - " 0.029465359,\n", - " 0.03936156,\n", - " -0.028816642,\n", - " 0.022757342,\n", - " -0.002236254,\n", - " 0.035480563,\n", - " 0.0058484883,\n", - " 0.026348954,\n", - " -0.016547782,\n", - " 0.018939447\n", - " ]\n", - "},\n", - "{\n", - " \"_id\": \"54637\",\n", - " \"content\": \"Employee number 54637, name John Johnson, department HR, location Miami, salary 110000\",\n", - " \"embedding\": [\n", - " 0.0151990615,\n", - " -0.018385835,\n", - " -0.031483263,\n", - " 0.0082740635,\n", - " 0.047831737,\n", - " 0.022178285,\n", - " 0.042604085,\n", - " -0.015300213,\n", - " 0.0052842684,\n", - " 0.04275969,\n", - " -0.031947587,\n", - " -0.055677623,\n", - " -0.01569269,\n", - " -0.016129037,\n", - " -0.044204526,\n", - " 0.0340167,\n", - " 0.0040199882,\n", - " -0.014162755,\n", - " 0.011139275,\n", - " -0.018563714,\n", - " -0.03279649,\n", - " 0.0037455678,\n", - " -0.01916476,\n", - " -0.02534246,\n", - " 0.020670477,\n", - " -0.010130891,\n", - " 0.028611206,\n", - " -0.084460564,\n", - " -0.04089965,\n", - " -0.006191601,\n", - " -0.059610564,\n", - " 0.07042831,\n", - " -0.0019582002,\n", - " 0.040124465,\n", - " -0.010672403,\n", - " 0.00023288652,\n", - " -0.036172427,\n", - " 0.019273408,\n", - " 0.022685157,\n", - " 0.019930484,\n", - " -0.0069136596,\n", - " -0.018724103,\n", - " -0.027178712,\n", - " 0.0102139255,\n", - " 0.060994297,\n", - " 0.01205306,\n", - " 0.008931071,\n", - " 0.030500712,\n", - " 0.039762385,\n", - " -0.0844163,\n", - " 0.03557818,\n", - " 0.016239291,\n", - " 0.011505173,\n", - " 0.016626962,\n", - " -0.051115632,\n", - " -0.089058846,\n", - " 0.006736814,\n", - " 0.0016996651,\n", - " -0.018498152,\n", - " -0.02900407,\n", - " -0.037330467,\n", - " -0.0019586603,\n", - " -0.006318982,\n", - " 0.011514259,\n", - " -0.020778127,\n", - " -0.060733095,\n", - " -0.03416104,\n", - " 0.003209011,\n", - " 0.037856832,\n", - " -0.02291265,\n", - " -0.02566606,\n", - " -0.04075286,\n", - " 0.06387488,\n", - " -0.013900549,\n", - " -0.06662302,\n", - " -0.11717324,\n", - " -0.021233523,\n", - " 0.03737273,\n", - " 0.062059958,\n", - " 0.018934567,\n", - " -0.0021977667,\n", - " -0.017087216,\n", - " -0.03001248,\n", - " -0.029826604,\n", - " -0.053601734,\n", - " 0.07904818,\n", - " -0.0050950386,\n", - " -0.027237581,\n", - " -0.009588286,\n", - " 0.02798285,\n", - " -0.015427634,\n", - " 0.010472741,\n", - " -0.019344417,\n", - " -0.0884872,\n", - " -0.03772547,\n", - " 0.07433684,\n", - " -0.005178444,\n", - " -0.04721746,\n", - " 0.016155189,\n", - " -0.020898396,\n", - " 0.027348634,\n", - " -0.03220877,\n", - " -0.039294083,\n", - " 0.025916431,\n", - " 0.03894846,\n", - " 0.0050957613,\n", - " 0.011876476,\n", - " 0.009665685,\n", - " -0.0010955081,\n", - " -0.0035323082,\n", - " -0.056610696,\n", - " 0.0042955126,\n", - " 0.004623993,\n", - " -0.047537014,\n", - " 0.065262586,\n", - " -0.045530386,\n", - " -0.043586448,\n", - " 0.08124031,\n", - " 0.0058494746,\n", - " 0.017003875,\n", - " 0.06947752,\n", - " 0.045389757,\n", - " -0.00809288,\n", - " 0.003066964,\n", - " 0.024357231,\n", - " 0.05353458,\n", - " 0.0041651297,\n", - " 0.015048914,\n", - " 0.09423512,\n", - " 0.059014294,\n", - " -0.01673688,\n", - " -0.025130406,\n", - " 0.030101426,\n", - " 0.00313877,\n", - " 0.05056692,\n", - " 0.05799128,\n", - " 0.06417359,\n", - " 0.0070831957,\n", - " 0.061689373,\n", - " -0.025019836,\n", - " -0.013782963,\n", - " -0.006486025,\n", - " -0.04184629,\n", - " 0.0021818338,\n", - " -0.0029972838,\n", - " -0.0069409898,\n", - " -0.008351021,\n", - " -0.009658322,\n", - " 0.048463274,\n", - " -0.029926352,\n", - " 0.024303105,\n", - " -0.017629249,\n", - " -0.014122519,\n", - " 0.006829436,\n", - " 0.015102068,\n", - " 0.02918675,\n", - " -0.047867116,\n", - " 0.017428437,\n", - " 0.004246343,\n", - " -0.02182751,\n", - " 0.05868468,\n", - " -0.0012855188,\n", - " -0.005099442,\n", - " 0.001516126,\n", - " -0.002746483,\n", - " -0.0103094075,\n", - " 0.009653553,\n", - " -0.03586081,\n", - " -0.042287398,\n", - " -0.060810238,\n", - " 0.007971088,\n", - " 0.030602243,\n", - " -0.07896841,\n", - " -0.019366264,\n", - " -0.059197318,\n", - " -0.040017575,\n", - " -0.0060959007,\n", - " 0.0067164223,\n", - " -0.031493124,\n", - " -0.024010602,\n", - " -0.037667226,\n", - " -0.03403944,\n", - " -0.00097576715,\n", - " 0.027220456,\n", - " -0.0021284383,\n", - " 0.06373505,\n", - " 0.041661903,\n", - " -0.025651291,\n", - " -0.0026189024,\n", - " -0.026962018,\n", - " 0.04662318,\n", - " 0.029713636,\n", - " -0.0072639524,\n", - " -0.008331813,\n", - " -0.013575179,\n", - " 0.030916931,\n", - " 0.015517671,\n", - " 0.028786736,\n", - " 0.0042063724,\n", - " -0.029553477,\n", - " -0.016450562,\n", - " 0.060844745,\n", - " -0.0013221892,\n", - " -0.0055684242,\n", - " 0.04769308,\n", - " -0.038562633,\n", - " 0.04191216,\n", - " -0.07439696,\n", - " -0.013617095,\n", - " 0.04565873,\n", - " 0.0075634466,\n", - " 0.04673023,\n", - " -0.041626494,\n", - " -0.03232615,\n", - " 0.04359808,\n", - " 0.024681205,\n", - " 0.024057476,\n", - " 0.007089288,\n", - " -0.00020997692,\n", - " -0.05840243,\n", - " 0.0011099685,\n", - " 0.012605227,\n", - " -0.020300457,\n", - " 0.072397396,\n", - " 0.0029569077,\n", - " -0.012561521,\n", - " -0.0031120302,\n", - " 0.04246921,\n", - " 0.019347874,\n", - " -0.016595539,\n", - " 0.008932043,\n", - " 0.038021155,\n", - " 0.022360448,\n", - " -0.041870937,\n", - " 0.03759141,\n", - " 0.017054925,\n", - " 0.023967758,\n", - " 0.017783063,\n", - " -0.02351047,\n", - " 0.023144009,\n", - " -0.054543506,\n", - " 0.012925695,\n", - " 0.08040064,\n", - " 0.007308367,\n", - " -0.08529201,\n", - " -0.0056034215,\n", - " -0.028788855,\n", - " 0.00034720462,\n", - " 0.014641983,\n", - " 0.024667779,\n", - " -0.028710028,\n", - " -0.041735,\n", - " 0.08198758,\n", - " 0.041555718,\n", - " -0.04926944,\n", - " 0.052032072,\n", - " -0.086632214,\n", - " -0.00159897,\n", - " -0.009663495,\n", - " -0.0071806083,\n", - " 0.051270913,\n", - " 0.024380185,\n", - " -0.01310986,\n", - " 0.021249343,\n", - " -0.032247756,\n", - " 0.040103268,\n", - " -0.0109099755,\n", - " -0.07212998,\n", - " -0.018791035,\n", - " 0.047924884,\n", - " -0.01295749,\n", - " -0.00022769881,\n", - " 0.08965714,\n", - " 0.056537516,\n", - " 0.039999932,\n", - " 0.011153844,\n", - " -0.0015653945,\n", - " 0.052498676,\n", - " 0.0031664725,\n", - " -0.04293477,\n", - " -0.018758398,\n", - " 0.045290086,\n", - " 0.025194753,\n", - " -0.036377974,\n", - " -0.013312391,\n", - " -0.004944805,\n", - " -0.0059067444,\n", - " -0.019272402,\n", - " 0.011710215,\n", - " -0.06544868,\n", - " -0.08821586,\n", - " 0.017618323,\n", - " -0.025412118,\n", - " -0.053164277,\n", - " -0.046637923,\n", - " 0.004189994,\n", - " -0.029162928,\n", - " 0.016743293,\n", - " 0.017788872,\n", - " 0.02451719,\n", - " 0.011813669,\n", - " -0.014297119,\n", - " 0.0047462014,\n", - " -0.0604839,\n", - " 0.030824589,\n", - " -0.011509641,\n", - " 0.030518167,\n", - " -0.06083328,\n", - " -0.008108362,\n", - " -0.010405061,\n", - " 0.0279155,\n", - " -0.030137705,\n", - " -0.037425663,\n", - " -0.003826426,\n", - " 0.045524806,\n", - " 0.04506571,\n", - " -0.0003876464,\n", - " -0.025874265,\n", - " -0.035840876,\n", - " 0.04633308,\n", - " 0.015148351,\n", - " 0.02118069,\n", - " 0.022964032,\n", - " -0.015708314,\n", - " -0.012418845,\n", - " 0.017429173,\n", - " -0.011633802,\n", - " 0.026676752,\n", - " 0.016578717,\n", - " 0.00702841,\n", - " -0.030563941,\n", - " 0.028610306,\n", - " 0.014839663,\n", - " 0.079686195,\n", - " -0.004785117,\n", - " 0.027001834,\n", - " -0.06591138,\n", - " 0.008991921,\n", - " -0.08665218,\n", - " -0.024576634,\n", - " 0.042076416,\n", - " -0.002764758,\n", - " -0.037591983,\n", - " -0.06974853,\n", - " -0.008148083,\n", - " -0.0010839726,\n", - " -0.03883453,\n", - " 0.029932331,\n", - " 0.07715753,\n", - " 0.0428311,\n", - " 0.00048389743,\n", - " 0.02941479,\n", - " -0.023215424,\n", - " -0.021311667,\n", - " -0.029051634,\n", - " -0.0078097307,\n", - " 0.05971781,\n", - " -0.0003501407,\n", - " 0.020407172,\n", - " -0.020588633,\n", - " -0.045638587,\n", - " 0.05452016,\n", - " -0.033031806,\n", - " 0.0018599117,\n", - " 0.021753361,\n", - " -0.017417207,\n", - " 0.011331878,\n", - " 0.025535421,\n", - " -0.012881257,\n", - " 0.0020049305,\n", - " 0.027690342,\n", - " -0.05566046,\n", - " -0.009303709,\n", - " 0.02051795,\n", - " -0.0012120871,\n", - " -0.05989722,\n", - " -0.05193341,\n", - " -0.03752882,\n", - " 0.0151110515,\n", - " 0.04022004,\n", - " 0.059206907,\n", - " -0.0004753494,\n", - " -0.015862446,\n", - " 0.008765484,\n", - " 0.002500967,\n", - " -0.024079999,\n", - " 0.037471678,\n", - " 0.04361219,\n", - " -0.009226066,\n", - " 0.06009437,\n", - " -0.0072968435,\n", - " -0.03503233,\n", - " 0.12823524,\n", - " -0.019953987,\n", - " 0.022029717,\n", - " -0.03506259,\n", - " -0.0069630756,\n", - " -0.010650351,\n", - " 0.00024113746,\n", - " -0.005909056,\n", - " -0.026001915,\n", - " -0.05297878,\n", - " -0.019525815,\n", - " -0.011212167,\n", - " -0.0011330652,\n", - " -0.029903706,\n", - " -0.013018626,\n", - " -0.04529402,\n", - " 0.022067638,\n", - " -0.042428583,\n", - " 0.011411191,\n", - " 0.07941165,\n", - " 0.046710193,\n", - " -0.09081757,\n", - " -0.020232175,\n", - " -0.021946874,\n", - " 0.04843305,\n", - " 0.025839098,\n", - " -0.029347481,\n", - " 0.052311007,\n", - " -0.019753845,\n", - " 0.015101981,\n", - " -0.02324361,\n", - " -0.06853173,\n", - " -0.013895659,\n", - " -0.027288755,\n", - " 0.014830132,\n", - " -0.019731691,\n", - " -0.012770851,\n", - " 0.047408056,\n", - " 0.010517912,\n", - " -0.018772654,\n", - " 0.008655169,\n", - " 0.004405761,\n", - " 0.028954867,\n", - " -0.043041132,\n", - " -0.005176918,\n", - " -0.01609051,\n", - " -0.028849607,\n", - " 0.05003634,\n", - " 0.029869856,\n", - " -0.050169658,\n", - " 0.08384437,\n", - " 0.01797906,\n", - " -0.01214695,\n", - " -0.027093818,\n", - " 0.025474763,\n", - " -0.035368394,\n", - " -0.0013650756,\n", - " -0.10130171,\n", - " -0.019761328,\n", - " -0.058286637,\n", - " -0.031827793,\n", - " -0.018027933,\n", - " -0.020658895,\n", - " -0.06964426,\n", - " 0.015475856,\n", - " 0.06776502,\n", - " -0.014362135,\n", - " -0.002891477,\n", - " -0.024214484,\n", - " -0.019469662,\n", - " -0.038628835,\n", - " -0.05970077,\n", - " 0.013868974,\n", - " -0.041725248,\n", - " 0.018331435,\n", - " -0.027626732,\n", - " 0.047414143,\n", - " 0.048645236,\n", - " 0.015711607,\n", - " -0.019731916,\n", - " 0.02018027,\n", - " 0.037067145,\n", - " 0.015580378,\n", - " -0.02074777,\n", - " -0.037656497,\n", - " 0.0315254,\n", - " 0.027829327,\n", - " -0.04953328,\n", - " -0.008974909,\n", - " -0.036621064,\n", - " 0.08268924,\n", - " -0.000099023084,\n", - " -0.010808362,\n", - " 0.017444545,\n", - " -0.036837447,\n", - " -0.033786334,\n", - " 0.024554044,\n", - " 0.038338773,\n", - " 0.0015833074,\n", - " -0.016416071,\n", - " 0.026449595,\n", - " -0.032863718,\n", - " 0.020646136,\n", - " -0.005101266,\n", - " 0.003269877,\n", - " 0.043449853,\n", - " 0.026952377,\n", - " 0.0030762502,\n", - " -0.043083463,\n", - " 0.011685804,\n", - " 0.02702897,\n", - " -0.019786451,\n", - " 0.09016056,\n", - " -0.019395946,\n", - " 0.00547562,\n", - " 0.00805198,\n", - " 0.027644351,\n", - " 0.013978436,\n", - " -0.01701422,\n", - " 0.0027872338,\n", - " 0.0068438747,\n", - " -0.034153488,\n", - " 0.041465588,\n", - " 0.0065093203,\n", - " -0.010097714,\n", - " -0.008133783,\n", - " 0.033143714,\n", - " -0.017333148,\n", - " 0.043355733,\n", - " -0.00871402,\n", - " -0.08563055,\n", - " -0.0106432075,\n", - " 0.035572823,\n", - " -0.023785846,\n", - " -0.004012492,\n", - " 0.042794853,\n", - " -0.031091385,\n", - " 0.0576266,\n", - " 0.0070195203,\n", - " 0.0765921,\n", - " -0.043606408,\n", - " -0.023182996,\n", - " -0.04500981,\n", - " 0.0025196855,\n", - " -0.015288511,\n", - " 0.031438597,\n", - " 0.051824644,\n", - " -0.042258043,\n", - " 0.03338895,\n", - " -0.025437905,\n", - " 0.031160489,\n", - " -0.0072392435,\n", - " -0.031922713,\n", - " 0.029755816,\n", - " 0.012957701,\n", - " -0.10024418,\n", - " 0.032848,\n", - " -0.007295161,\n", - " -0.0035617317,\n", - " 0.028405763,\n", - " 0.061833233,\n", - " -0.04108825,\n", - " -0.020171262,\n", - " 0.020549063,\n", - " -0.026362132,\n", - " -0.023915224,\n", - " 0.007996089,\n", - " -0.030391349,\n", - " -0.0028575344,\n", - " -0.018893851,\n", - " 0.02560692,\n", - " 0.008163355,\n", - " 0.087368175,\n", - " 0.008817629,\n", - " -0.00850316,\n", - " -0.059040304,\n", - " 0.041495502,\n", - " -0.040280342,\n", - " 0.0068111503,\n", - " 0.0021893613,\n", - " 0.0022273697,\n", - " 0.005985552,\n", - " 0.0505196,\n", - " -0.04750377,\n", - " -0.03359202,\n", - " 0.020417644,\n", - " 0.0044759694,\n", - " -0.0035043096,\n", - " 0.048957326,\n", - " -0.011384678,\n", - " 0.008479551,\n", - " 0.025835814,\n", - " 0.0014910818,\n", - " 0.039479405,\n", - " 0.057871632,\n", - " 0.016251555,\n", - " 0.06249111,\n", - " -0.019609375,\n", - " -0.04390419,\n", - " 0.017925067,\n", - " -0.055957958,\n", - " -0.019112395,\n", - " -0.04754885,\n", - " 0.026070505,\n", - " -0.019006608,\n", - " -0.030362992,\n", - " -0.0067993933,\n", - " -0.006561339,\n", - " 0.026431026,\n", - " -0.03405452,\n", - " 0.057274282,\n", - " -0.026786203,\n", - " 0.063958324,\n", - " -0.04453278,\n", - " 0.027547128,\n", - " -0.03851104,\n", - " 0.01796476,\n", - " 0.031259652,\n", - " 0.04863174,\n", - " -0.024669012,\n", - " -0.034748323,\n", - " -0.018997308,\n", - " -0.05671984,\n", - " -0.021414421,\n", - " 0.020377612,\n", - " -0.030505922,\n", - " -0.0050755935,\n", - " -0.033292443,\n", - " 0.002657024,\n", - " -0.038488954,\n", - " 0.009190322,\n", - " -0.049295817,\n", - " 0.041600667,\n", - " 0.0049329526,\n", - " 0.0032398892,\n", - " -0.027688216,\n", - " 0.060459703,\n", - " 0.03917895,\n", - " 0.05121542,\n", - " 0.011903356,\n", - " 0.0094349375,\n", - " -0.01939282,\n", - " -0.040036276,\n", - " 0.019289287,\n", - " 0.007947662,\n", - " -0.05668005,\n", - " 0.01639571,\n", - " 0.013513371,\n", - " -0.10730804,\n", - " 0.011741851,\n", - " 0.052281383,\n", - " 0.0060147797,\n", - " -0.0016338177,\n", - " 0.016279288,\n", - " 0.012750764,\n", - " -0.04507693,\n", - " -0.00013838317,\n", - " -0.020932881,\n", - " 0.0028839025,\n", - " -0.0015208381,\n", - " 0.0013958535,\n", - " 0.023533827,\n", - " -0.010494416,\n", - " -0.061766583,\n", - " -0.02134274,\n", - " -0.022852637,\n", - " 0.054971635,\n", - " 0.026075963,\n", - " -0.021454506,\n", - " 0.02648363,\n", - " -0.030089613,\n", - " 0.028793827,\n", - " 0.004582815,\n", - " -0.021465372,\n", - " -0.017831849,\n", - " -0.06147862,\n", - " -0.05767438,\n", - " 0.09083923,\n", - " -0.05611259,\n", - " 0.017855838,\n", - " 0.009335081,\n", - " -0.045156814,\n", - " 0.06599881,\n", - " 0.018773748,\n", - " -0.05827166,\n", - " 0.016615061,\n", - " -0.006753534,\n", - " 0.01607565,\n", - " 0.027570006,\n", - " -0.020239603,\n", - " -0.03056045,\n", - " 0.046354145,\n", - " 0.03691325,\n", - " 0.031975202,\n", - " 0.022407934,\n", - " 0.025474546,\n", - " -0.045023665,\n", - " -0.040520623,\n", - " 0.0005759944,\n", - " -0.03525117,\n", - " -0.009240973,\n", - " -0.011385803,\n", - " 0.08493358,\n", - " 0.018094597,\n", - " 0.035135623,\n", - " 0.016993279,\n", - " 0.01320788,\n", - " 0.07891705,\n", - " -0.020045092,\n", - " -0.033938758,\n", - " -0.0056153582,\n", - " 0.03615839,\n", - " -0.031113567,\n", - " 0.057805743,\n", - " -0.001218427,\n", - " -0.021837134,\n", - " 0.029644802,\n", - " -0.0033356778,\n", - " 0.040365815,\n", - " -0.018033424,\n", - " -0.02393337,\n", - " 0.05093956,\n", - " 0.030515084,\n", - " -0.037502967,\n", - " 0.009851229,\n", - " 0.0072234045,\n", - " -0.048626166,\n", - " 0.037203453,\n", - " 0.05917087,\n", - " -0.03617051,\n", - " 0.00980295,\n", - " -0.038709767,\n", - " 0.02074771,\n", - " 0.03775127,\n", - " -0.03192831,\n", - " 0.05048824,\n", - " -0.001492862,\n", - " -0.021132791,\n", - " 0.08444902,\n", - " -0.03443452,\n", - " -0.040238414,\n", - " 0.048974395,\n", - " -0.027845262,\n", - " 0.07948588,\n", - " 0.0208495,\n", - " 0.026636329,\n", - " -0.02487519,\n", - " -0.029094454,\n", - " -0.05993427,\n", - " 0.03780091,\n", - " -0.012249043,\n", - " 0.0028786385,\n", - " 0.043765884,\n", - " -0.028861433,\n", - " 0.009502931,\n", - " -0.030093342,\n", - " -0.026304517,\n", - " -0.05845765,\n", - " -0.0392811,\n", - " 0.029583348,\n", - " -0.01641044,\n", - " -0.005475869,\n", - " 0.04321726,\n", - " -0.06391988,\n", - " -0.025680711,\n", - " -0.0030519557,\n", - " 0.030743454,\n", - " -0.0007805563,\n", - " -0.04256318,\n", - " -0.005030573,\n", - " -0.0041211224,\n", - " 0.021191673,\n", - " 0.04913769,\n", - " 0.027602818,\n", - " -0.014373903,\n", - " 0.03175012\n", - " ]\n", - "},\n", - "{\n", - " \"_id\": \"54638\",\n", - " \"content\": \"Employee number 54638, name Jane Johnson, department Operations, location Seattle, salary 140000\",\n", - " \"embedding\": [\n", - " 0.026050478,\n", - " -0.048555247,\n", - " -0.008828629,\n", - " 0.019901045,\n", - " 0.034666445,\n", - " 0.010111517,\n", - " 0.06873206,\n", - " -0.030538522,\n", - " 0.009940293,\n", - " 0.0339663,\n", - " -0.03364418,\n", - " -0.03269781,\n", - " -0.029471608,\n", - " -0.0027008695,\n", - " -0.02049043,\n", - " -0.0029114042,\n", - " 0.010917951,\n", - " -0.028362973,\n", - " -0.0075063263,\n", - " -0.06207452,\n", - " -0.021798516,\n", - " 0.0039276425,\n", - " 0.00055708154,\n", - " -0.02095584,\n", - " 0.01713003,\n", - " -0.01722649,\n", - " 0.008000153,\n", - " -0.08242634,\n", - " -0.028559122,\n", - " 0.018734612,\n", - " -0.066623494,\n", - " 0.034287848,\n", - " -0.03751501,\n", - " 0.03244232,\n", - " -0.03420307,\n", - " 0.023143344,\n", - " -0.03240853,\n", - " -0.023571912,\n", - " -0.00683183,\n", - " 0.03096674,\n", - " -0.014259085,\n", - " -0.011342896,\n", - " -0.026998486,\n", - " 0.014940984,\n", - " 0.050578054,\n", - " -0.028980328,\n", - " 0.023303777,\n", - " -0.004296986,\n", - " 0.0293136,\n", - " -0.061096653,\n", - " 0.03287692,\n", - " 0.015354411,\n", - " 0.021088544,\n", - " -0.0015228266,\n", - " 0.0029424573,\n", - " -0.082046166,\n", - " 0.0040660985,\n", - " 0.0074269758,\n", - " -0.010958359,\n", - " -0.035012763,\n", - " -0.018889561,\n", - " -0.0059276978,\n", - " 0.002083359,\n", - " 0.036374025,\n", - " -0.004819571,\n", - " -0.04908644,\n", - " -0.017455256,\n", - " -0.009606802,\n", - " 0.06495625,\n", - " 0.0032073925,\n", - " -0.052301414,\n", - " -0.041856,\n", - " 0.05783131,\n", - " -0.017050996,\n", - " -0.061963696,\n", - " -0.06982274,\n", - " -0.03540072,\n", - " 0.03466075,\n", - " 0.055206526,\n", - " 0.011832436,\n", - " 0.0021956502,\n", - " -0.007684086,\n", - " -0.020636348,\n", - " -0.018782893,\n", - " -0.047240626,\n", - " 0.047610387,\n", - " -0.0076809353,\n", - " -0.0100567825,\n", - " -0.025776941,\n", - " 0.04181693,\n", - " -0.0046912674,\n", - " -0.012204287,\n", - " 0.014001371,\n", - " -0.063043125,\n", - " -0.036930084,\n", - " 0.059859123,\n", - " -0.010818763,\n", - " -0.045730297,\n", - " -0.0075380807,\n", - " -0.019068131,\n", - " 0.019801125,\n", - " -0.049903613,\n", - " -0.05432268,\n", - " -0.0071445843,\n", - " 0.0057908674,\n", - " -0.002666185,\n", - " -0.0075345123,\n", - " -0.019908248,\n", - " -0.00643323,\n", - " -0.00071061886,\n", - " -0.0838654,\n", - " -0.008257412,\n", - " -0.038826358,\n", - " -0.0513455,\n", - " 0.072962046,\n", - " -0.020993974,\n", - " -0.049816236,\n", - " 0.070966154,\n", - " 0.00079034764,\n", - " 0.015203719,\n", - " 0.05684234,\n", - " 0.03761177,\n", - " 0.016545977,\n", - " 0.020625291,\n", - " 0.0210726,\n", - " 0.02898525,\n", - " -0.0033419074,\n", - " 0.0032714924,\n", - " 0.11322761,\n", - " 0.054507524,\n", - " -0.04121643,\n", - " -0.039163385,\n", - " 0.040570177,\n", - " -0.0072572003,\n", - " 0.038773507,\n", - " 0.0637184,\n", - " 0.069037475,\n", - " -0.028668208,\n", - " 0.07188595,\n", - " -0.02913201,\n", - " 0.0063090385,\n", - " 0.007426714,\n", - " -0.03193378,\n", - " -0.006524865,\n", - " -0.0127412435,\n", - " 0.015498198,\n", - " -0.020522788,\n", - " -0.011274028,\n", - " 0.028620226,\n", - " 0.005763184,\n", - " 0.022521585,\n", - " 0.0072611654,\n", - " -0.048059847,\n", - " -0.01234606,\n", - " 0.04490082,\n", - " 0.03871421,\n", - " -0.044477567,\n", - " 0.027942147,\n", - " -0.0066905613,\n", - " -0.014890972,\n", - " 0.048969653,\n", - " 0.019693347,\n", - " -0.021390632,\n", - " 0.033437464,\n", - " -0.015723728,\n", - " -0.011988548,\n", - " 0.0554776,\n", - " -0.03956305,\n", - " -0.07680316,\n", - " -0.031703744,\n", - " -0.01612956,\n", - " 0.04235391,\n", - " -0.070821315,\n", - " 0.011926204,\n", - " -0.053500686,\n", - " -0.050267965,\n", - " 0.00074491126,\n", - " -0.008569316,\n", - " -0.027631104,\n", - " 0.0061910404,\n", - " -0.033930015,\n", - " -0.007472883,\n", - " 0.0026893707,\n", - " 0.0384716,\n", - " 0.018170964,\n", - " 0.050014913,\n", - " 0.05871329,\n", - " -0.044597052,\n", - " -0.014061176,\n", - " -0.003683495,\n", - " 0.025531424,\n", - " 0.017034912,\n", - " -0.027470706,\n", - " -0.006491179,\n", - " -0.009489945,\n", - " 0.017133964,\n", - " -0.015572295,\n", - " 0.0139110815,\n", - " -0.02003761,\n", - " -0.037344135,\n", - " -0.030428719,\n", - " 0.06549211,\n", - " 0.010248525,\n", - " 0.0028726796,\n", - " 0.033761874,\n", - " -0.015765324,\n", - " 0.046935823,\n", - " -0.04185924,\n", - " -0.006468727,\n", - " 0.050379142,\n", - " 0.007927611,\n", - " 0.03851822,\n", - " 0.008543064,\n", - " 0.0078075267,\n", - " 0.039120134,\n", - " 0.03586357,\n", - " 0.04638511,\n", - " -0.010768516,\n", - " -0.0067371903,\n", - " -0.025532754,\n", - " -0.0051189596,\n", - " 0.02152079,\n", - " -0.04576048,\n", - " 0.04305608,\n", - " -0.026554907,\n", - " -0.018880805,\n", - " -0.01480849,\n", - " 0.026723232,\n", - " 0.001033573,\n", - " -0.037126005,\n", - " -0.0020229125,\n", - " 0.040790092,\n", - " 0.0018653974,\n", - " -0.049913183,\n", - " 0.04781728,\n", - " 0.027713154,\n", - " 0.010776397,\n", - " 0.01318502,\n", - " -0.026499385,\n", - " -0.009594083,\n", - " -0.03862901,\n", - " 0.016218811,\n", - " 0.06014656,\n", - " 0.025734013,\n", - " -0.0347474,\n", - " 0.0116609605,\n", - " -0.038452834,\n", - " 0.0052867737,\n", - " 0.010370307,\n", - " 0.027156852,\n", - " -0.0015308461,\n", - " -0.06445644,\n", - " 0.050907042,\n", - " 0.022530565,\n", - " -0.048766818,\n", - " 0.05991084,\n", - " -0.09708642,\n", - " -0.009711094,\n", - " 0.015859898,\n", - " -0.029318294,\n", - " 0.050506905,\n", - " 0.00735409,\n", - " -0.0138486065,\n", - " 0.024359517,\n", - " -0.034031246,\n", - " 0.024766166,\n", - " -0.01821558,\n", - " -0.06686822,\n", - " -0.0487108,\n", - " 0.052032128,\n", - " 0.016451957,\n", - " -0.03551824,\n", - " 0.08024126,\n", - " 0.051618367,\n", - " 0.013979535,\n", - " 0.010763741,\n", - " -0.023814084,\n", - " 0.04610131,\n", - " 0.008492314,\n", - " -0.06802373,\n", - " -0.015461633,\n", - " 0.055361446,\n", - " 0.0074120234,\n", - " -0.04642445,\n", - " -0.028934892,\n", - " 0.01169551,\n", - " -0.030712495,\n", - " 0.0039937347,\n", - " 0.008349997,\n", - " -0.06625405,\n", - " -0.08341982,\n", - " 0.013278654,\n", - " -0.026365193,\n", - " -0.039572082,\n", - " -0.064723566,\n", - " 0.0052512945,\n", - " -0.02465726,\n", - " 0.025906282,\n", - " 0.005685407,\n", - " 0.006141651,\n", - " 0.0044314065,\n", - " -0.039461534,\n", - " -0.032410044,\n", - " -0.074979536,\n", - " 0.05221336,\n", - " -0.010037091,\n", - " -0.00015792609,\n", - " -0.070082806,\n", - " -0.0063522724,\n", - " -0.036909256,\n", - " 0.024703242,\n", - " -0.025880957,\n", - " -0.03181115,\n", - " 0.025542444,\n", - " 0.020821305,\n", - " 0.05083042,\n", - " 0.00440165,\n", - " -0.017547268,\n", - " -0.038332768,\n", - " 0.06295742,\n", - " -0.003380332,\n", - " 0.0017819487,\n", - " 0.031406853,\n", - " -0.03936085,\n", - " -0.014774891,\n", - " 0.05555366,\n", - " 0.0013044683,\n", - " 0.071219094,\n", - " 0.0027098448,\n", - " 0.0090771,\n", - " 0.004294718,\n", - " 0.04097738,\n", - " 0.0038274624,\n", - " 0.09351304,\n", - " 0.01993581,\n", - " 0.03123765,\n", - " -0.062362995,\n", - " 0.017761108,\n", - " -0.06349266,\n", - " -0.023149393,\n", - " 0.041712813,\n", - " 0.023032729,\n", - " -0.046279017,\n", - " -0.059766676,\n", - " 0.013576986,\n", - " -0.035526287,\n", - " 0.0009959425,\n", - " 0.042815145,\n", - " 0.052038774,\n", - " 0.047260206,\n", - " -0.015755137,\n", - " 0.011777429,\n", - " -0.013718928,\n", - " -0.018773504,\n", - " -0.041940242,\n", - " -0.016540648,\n", - " 0.056323376,\n", - " -0.009581614,\n", - " 0.012827593,\n", - " 0.002802622,\n", - " -0.047416028,\n", - " 0.06029572,\n", - " -0.026624044,\n", - " -0.0059878556,\n", - " -0.01112658,\n", - " 0.0064357584,\n", - " 0.015744798,\n", - " 0.0027346082,\n", - " -0.013077302,\n", - " 0.027371943,\n", - " 0.028480768,\n", - " -0.029083466,\n", - " -0.016170066,\n", - " 0.018732633,\n", - " -0.02920547,\n", - " -0.049596816,\n", - " -0.050539367,\n", - " -0.023739604,\n", - " -0.016439682,\n", - " 0.023610277,\n", - " 0.03793149,\n", - " -0.01936672,\n", - " 0.00054942124,\n", - " 0.03477947,\n", - " 0.022074739,\n", - " -0.008824361,\n", - " -0.016267285,\n", - " 0.032433596,\n", - " -0.026371641,\n", - " 0.06440936,\n", - " 0.016472073,\n", - " -0.012704358,\n", - " 0.12420736,\n", - " -0.0101508675,\n", - " 0.023653913,\n", - " -0.036456037,\n", - " -0.009319963,\n", - " -0.02745349,\n", - " 0.011565427,\n", - " -0.016726809,\n", - " -0.00910894,\n", - " -0.027309556,\n", - " -0.020953115,\n", - " -0.0004489086,\n", - " -0.017622823,\n", - " -0.026881404,\n", - " -0.016441276,\n", - " -0.028333068,\n", - " 0.051373687,\n", - " -0.06849969,\n", - " 0.048643496,\n", - " 0.06129681,\n", - " 0.043112013,\n", - " -0.10503493,\n", - " -0.032169662,\n", - " -0.016303875,\n", - " 0.038900618,\n", - " 0.017744469,\n", - " -0.0078635495,\n", - " 0.011909131,\n", - " -0.02633716,\n", - " 0.012839195,\n", - " -0.034210175,\n", - " -0.049735658,\n", - " -0.012025739,\n", - " 0.024162453,\n", - " -0.017275587,\n", - " -0.027206033,\n", - " -0.01216894,\n", - " 0.056151856,\n", - " -0.002266644,\n", - " -0.017719636,\n", - " -0.024023125,\n", - " 0.012112513,\n", - " 0.035618242,\n", - " -0.066973604,\n", - " -0.038296815,\n", - " 0.046060294,\n", - " -0.03857978,\n", - " 0.04528379,\n", - " 0.043774627,\n", - " -0.025222767,\n", - " 0.08498407,\n", - " 0.0023034313,\n", - " -0.007176461,\n", - " -0.018639492,\n", - " 0.023903845,\n", - " -0.040975634,\n", - " 0.014675711,\n", - " -0.08696412,\n", - " -0.0012359321,\n", - " -0.060993966,\n", - " -0.024204629,\n", - " -0.045965314,\n", - " -0.05470206,\n", - " -0.0545379,\n", - " 0.031496808,\n", - " 0.059156094,\n", - " 0.009160291,\n", - " 0.0072219935,\n", - " -0.006173258,\n", - " -0.03295994,\n", - " -0.01801206,\n", - " -0.057803974,\n", - " 0.041660473,\n", - " -0.039624795,\n", - " 0.028510751,\n", - " -0.030607404,\n", - " 0.06521628,\n", - " 0.06455515,\n", - " 0.013236343,\n", - " -0.013641919,\n", - " 0.03251663,\n", - " 0.019429607,\n", - " 0.020611761,\n", - " -0.047394972,\n", - " -0.033903588,\n", - " 0.030801337,\n", - " 0.03389709,\n", - " -0.033200398,\n", - " -0.00968848,\n", - " -0.042483523,\n", - " 0.062307518,\n", - " -0.024104252,\n", - " -0.038019832,\n", - " 0.037520684,\n", - " -0.02434741,\n", - " -0.015609218,\n", - " 0.0065647936,\n", - " 0.043396086,\n", - " 0.014070153,\n", - " 0.0043344726,\n", - " 0.024882345,\n", - " -0.022135641,\n", - " -0.01799605,\n", - " 0.00038329684,\n", - " -0.01741619,\n", - " 0.044463806,\n", - " 0.031136844,\n", - " 0.032308206,\n", - " 0.0007304428,\n", - " 0.035526954,\n", - " 0.028219154,\n", - " -0.021445524,\n", - " 0.059003815,\n", - " -0.0415958,\n", - " -0.0043805623,\n", - " -0.0006041634,\n", - " 0.028271,\n", - " 0.038045794,\n", - " -0.007856862,\n", - " -0.0030909725,\n", - " -0.032664094,\n", - " -0.017286232,\n", - " 0.024400914,\n", - " -0.013834741,\n", - " -0.02652701,\n", - " 0.029634649,\n", - " 0.01700266,\n", - " -0.03734089,\n", - " 0.038840823,\n", - " -0.016492758,\n", - " -0.093306154,\n", - " -0.0044792993,\n", - " 0.04936495,\n", - " -0.016763058,\n", - " 0.024115685,\n", - " 0.05415202,\n", - " -0.04315434,\n", - " 0.015969714,\n", - " -0.021037051,\n", - " 0.05564539,\n", - " -0.055493116,\n", - " -0.02337645,\n", - " -0.025281547,\n", - " -0.0065010595,\n", - " 0.008250707,\n", - " 0.055807795,\n", - " 0.02414763,\n", - " -0.022564175,\n", - " 0.02834781,\n", - " -0.040628407,\n", - " 0.026874747,\n", - " -0.01892121,\n", - " -0.035771616,\n", - " 0.0018971186,\n", - " 0.030991131,\n", - " -0.058407318,\n", - " 0.022544177,\n", - " -0.0099294195,\n", - " -0.003015739,\n", - " 0.009533158,\n", - " 0.06220805,\n", - " -0.0018919198,\n", - " -0.015758067,\n", - " 0.0045811604,\n", - " -0.022871247,\n", - " -0.026954936,\n", - " -0.007922866,\n", - " -0.015751228,\n", - " -0.024009718,\n", - " -0.019846817,\n", - " 0.00086579495,\n", - " 0.007355841,\n", - " 0.07742838,\n", - " 0.039498612,\n", - " 0.0018927547,\n", - " -0.049126364,\n", - " 0.035092838,\n", - " -0.038997784,\n", - " 0.014563989,\n", - " 0.0014772905,\n", - " -0.0058927247,\n", - " 0.0004669789,\n", - " 0.054502,\n", - " -0.0101958765,\n", - " -0.06462403,\n", - " 0.030232383,\n", - " 0.015468133,\n", - " 0.008747526,\n", - " 0.058180943,\n", - " 0.009895715,\n", - " -0.023807824,\n", - " 0.016150286,\n", - " -0.033176575,\n", - " 0.03896909,\n", - " 0.07366637,\n", - " -0.02589846,\n", - " 0.081121355,\n", - " 0.012857258,\n", - " -0.0320698,\n", - " 0.026557323,\n", - " -0.05475815,\n", - " -0.045223676,\n", - " -0.006914698,\n", - " 0.059804097,\n", - " -0.030856598,\n", - " -0.02270003,\n", - " -0.006721817,\n", - " 0.007834129,\n", - " 0.014207969,\n", - " -0.04459566,\n", - " 0.060735647,\n", - " -0.004343931,\n", - " 0.06916978,\n", - " -0.025479676,\n", - " 0.001981753,\n", - " -0.049986716,\n", - " 0.019160662,\n", - " 0.019025618,\n", - " 0.03463173,\n", - " -0.0051061907,\n", - " -0.039971903,\n", - " -0.009554134,\n", - " -0.051973134,\n", - " -0.02322696,\n", - " 0.000666707,\n", - " 0.0076026963,\n", - " 0.0070748134,\n", - " -0.027127214,\n", - " 0.0021439027,\n", - " -0.0380424,\n", - " 0.019361308,\n", - " -0.021825459,\n", - " 0.024104213,\n", - " -0.001751936,\n", - " 0.020918885,\n", - " -0.0037656801,\n", - " 0.053490546,\n", - " 0.072466716,\n", - " 0.06307481,\n", - " 0.025220444,\n", - " 0.030272197,\n", - " -0.011731547,\n", - " -0.056140322,\n", - " 0.048621643,\n", - " -0.022496052,\n", - " -0.06380631,\n", - " 0.038866386,\n", - " -0.010590717,\n", - " -0.108824804,\n", - " 0.006726385,\n", - " 0.050433647,\n", - " 0.0057739234,\n", - " -0.01420325,\n", - " 0.023737092,\n", - " 0.042579204,\n", - " -0.053798538,\n", - " -0.018823216,\n", - " -0.03827396,\n", - " -0.015979653,\n", - " -0.0069397204,\n", - " 0.02125115,\n", - " 0.0033473414,\n", - " -0.013927182,\n", - " -0.05654852,\n", - " -0.019954465,\n", - " -0.035381112,\n", - " 0.056015182,\n", - " 0.0065556956,\n", - " -0.023087364,\n", - " 0.043700524,\n", - " 0.0027661035,\n", - " 0.025146691,\n", - " 0.012687644,\n", - " -0.027370248,\n", - " -0.0010651633,\n", - " -0.06115836,\n", - " -0.029139342,\n", - " 0.08521571,\n", - " -0.042291123,\n", - " 0.030378494,\n", - " 0.014432462,\n", - " -0.046826813,\n", - " 0.050151218,\n", - " 0.045153998,\n", - " -0.04796362,\n", - " 0.022682115,\n", - " 0.011545504,\n", - " 0.020556057,\n", - " -0.0042003356,\n", - " -0.021686615,\n", - " -0.0012217021,\n", - " 0.019806935,\n", - " 0.047820672,\n", - " 0.05978573,\n", - " 0.01758219,\n", - " 0.02204856,\n", - " -0.039568268,\n", - " -0.021229789,\n", - " 0.014548975,\n", - " -0.034249913,\n", - " -0.023128428,\n", - " -0.011201689,\n", - " 0.07169892,\n", - " 0.026005901,\n", - " 0.028781159,\n", - " 0.0130280135,\n", - " 0.03135926,\n", - " 0.0843804,\n", - " -0.0062047434,\n", - " -0.061045166,\n", - " 0.010564766,\n", - " 0.018106297,\n", - " -0.043597803,\n", - " 0.02699747,\n", - " -0.0120446915,\n", - " -0.024967365,\n", - " 0.034383804,\n", - " 0.0030797508,\n", - " 0.03732648,\n", - " -0.06742948,\n", - " -0.041975114,\n", - " 0.036880396,\n", - " 0.025295557,\n", - " 0.016465476,\n", - " 0.028427439,\n", - " -0.004287951,\n", - " -0.008966516,\n", - " 0.03698348,\n", - " 0.05051995,\n", - " -0.024159456,\n", - " 0.0052558105,\n", - " -0.04339689,\n", - " 0.009192153,\n", - " 0.045353524,\n", - " -0.049608096,\n", - " 0.06556983,\n", - " 0.0049719103,\n", - " 0.000014385518,\n", - " 0.06860882,\n", - " -0.03174607,\n", - " -0.0073257447,\n", - " 0.0044105197,\n", - " -0.03662372,\n", - " 0.09250486,\n", - " 0.04256795,\n", - " 0.031364053,\n", - " 0.0016935823,\n", - " -0.0680488,\n", - " -0.07860276,\n", - " 0.024094777,\n", - " 0.016591892,\n", - " 0.022528214,\n", - " 0.029432567,\n", - " -0.02577635,\n", - " 0.013138877,\n", - " -0.021803275,\n", - " -0.030736644,\n", - " -0.064376354,\n", - " -0.0935471,\n", - " 0.018339334,\n", - " -0.040749416,\n", - " 0.036033116,\n", - " 0.040105127,\n", - " -0.059686333,\n", - " -0.028928738,\n", - " -0.0044766283,\n", - " 0.030114502,\n", - " 0.018945087,\n", - " -0.029741868,\n", - " 0.0052247434,\n", - " -0.013826671,\n", - " 0.06707814,\n", - " 0.0406519,\n", - " 0.03318739,\n", - " 0.010909002,\n", - " 0.029758368\n", - " ]\n", - "}])\n", - "\n", - "\n" + "collection.insert_many(\n", + " [\n", + " {\n", + " \"_id\": \"54634\",\n", + " \"content\": \"Employee number 54634, name Jane Doe, department Marketing, location Los Angeles, salary 120000\",\n", + " \"embedding\": [\n", + " 0.024926867,\n", + " -0.049224764,\n", + " 0.0051397122,\n", + " -0.015662413,\n", + " 0.036198545,\n", + " 0.020058708,\n", + " 0.07437574,\n", + " -0.023353964,\n", + " 0.009316206,\n", + " 0.010908616,\n", + " -0.022639172,\n", + " 0.008110297,\n", + " -0.03569339,\n", + " 0.016980717,\n", + " -0.014814842,\n", + " 0.0048693726,\n", + " 0.0024207153,\n", + " -0.036100663,\n", + " -0.016500184,\n", + " -0.033307776,\n", + " -0.020310277,\n", + " -0.01708344,\n", + " -0.017491976,\n", + " -0.01000457,\n", + " 0.021011023,\n", + " -0.0017388392,\n", + " 0.00891552,\n", + " -0.10860842,\n", + " -0.046374027,\n", + " -0.01210933,\n", + " -0.043089807,\n", + " 0.027616654,\n", + " -0.058572993,\n", + " -0.0012424898,\n", + " -0.0009245786,\n", + " -0.026917346,\n", + " -0.026614873,\n", + " -0.008031103,\n", + " 0.006364708,\n", + " 0.022180663,\n", + " -0.029214343,\n", + " -0.020451233,\n", + " -0.013976919,\n", + " -0.011516259,\n", + " 0.027531886,\n", + " -0.020989226,\n", + " 0.0011997295,\n", + " -0.008541397,\n", + " 0.013981253,\n", + " -0.09130217,\n", + " 0.031902086,\n", + " -0.014483433,\n", + " 0.04141627,\n", + " -0.022633772,\n", + " -0.0015243818,\n", + " -0.0701282,\n", + " -0.005745007,\n", + " 0.003046663,\n", + " -0.00138343,\n", + " -0.0483541,\n", + " -0.018663412,\n", + " -0.010342808,\n", + " -0.036891118,\n", + " 0.041526485,\n", + " -0.0070978166,\n", + " -0.056960497,\n", + " -0.00027713762,\n", + " 0.00041085767,\n", + " 0.0638381,\n", + " 0.012412274,\n", + " -0.042297978,\n", + " -0.034797642,\n", + " 0.027877614,\n", + " -0.014577787,\n", + " -0.07915758,\n", + " -0.11489053,\n", + " -0.012170335,\n", + " 0.023879664,\n", + " 0.040547226,\n", + " 0.027829757,\n", + " -0.019437442,\n", + " -0.03378374,\n", + " -0.026225261,\n", + " -0.042423252,\n", + " -0.034459304,\n", + " 0.07092275,\n", + " 0.04282131,\n", + " -0.019700523,\n", + " -0.022706546,\n", + " 0.07524933,\n", + " -0.025327584,\n", + " 0.03845969,\n", + " -0.006575861,\n", + " -0.05432576,\n", + " -0.0030720695,\n", + " 0.06054884,\n", + " 0.014463371,\n", + " -0.05177936,\n", + " 0.011856342,\n", + " -0.01622149,\n", + " -0.015594266,\n", + " -0.023064198,\n", + " -0.056572527,\n", + " -0.01887025,\n", + " 0.009372615,\n", + " -0.005908454,\n", + " -0.019093627,\n", + " -0.010138043,\n", + " -0.03215679,\n", + " 0.023405561,\n", + " -0.07793633,\n", + " 0.0022705605,\n", + " -0.03748151,\n", + " -0.040298775,\n", + " 0.05949639,\n", + " -0.02171212,\n", + " -0.05205988,\n", + " 0.056799524,\n", + " 0.046728708,\n", + " 0.00995629,\n", + " 0.018814746,\n", + " 0.052283265,\n", + " 0.0133213885,\n", + " 0.0070853233,\n", + " 0.02381203,\n", + " 0.048278138,\n", + " -0.025068594,\n", + " 0.013948586,\n", + " 0.10241069,\n", + " 0.033334825,\n", + " -0.035002332,\n", + " -0.028427497,\n", + " 0.036363285,\n", + " -0.009638689,\n", + " 0.050988846,\n", + " 0.088660076,\n", + " 0.052428994,\n", + " 0.008259064,\n", + " 0.051591944,\n", + " -0.035510417,\n", + " -0.0025276055,\n", + " 0.020777041,\n", + " -0.02206114,\n", + " 0.00075541,\n", + " -0.038383663,\n", + " 0.0068223546,\n", + " 0.013984699,\n", + " -0.04017368,\n", + " 0.046198152,\n", + " -0.015898008,\n", + " -0.016150242,\n", + " -0.006470939,\n", + " -0.046308447,\n", + " 0.033918925,\n", + " 0.021597652,\n", + " 0.009154935,\n", + " -0.03465381,\n", + " 0.0016349686,\n", + " 0.019491052,\n", + " 0.023978025,\n", + " 0.059030097,\n", + " 0.03193792,\n", + " -0.026359702,\n", + " 0.025488824,\n", + " 0.0014710033,\n", + " 0.021635707,\n", + " 0.028962605,\n", + " -0.0426874,\n", + " -0.025902368,\n", + " -0.03850525,\n", + " -0.0072347843,\n", + " 0.019107448,\n", + " -0.039649457,\n", + " -0.04149649,\n", + " -0.0390399,\n", + " -0.073608436,\n", + " 0.005187664,\n", + " -0.012122672,\n", + " -0.02703804,\n", + " -0.025964485,\n", + " -0.041734103,\n", + " -0.029006453,\n", + " 0.020049337,\n", + " 0.04200867,\n", + " -0.0018111905,\n", + " 0.03557779,\n", + " 0.058680393,\n", + " -0.045999996,\n", + " 0.0054121087,\n", + " -0.028696584,\n", + " 0.036451954,\n", + " -0.00065523863,\n", + " -0.014693241,\n", + " -0.0049391747,\n", + " -0.013985914,\n", + " 0.029479476,\n", + " 0.005661245,\n", + " 0.034519162,\n", + " -0.0017001618,\n", + " -0.014198862,\n", + " -0.044131663,\n", + " 0.04520943,\n", + " 0.021466821,\n", + " -0.0052906116,\n", + " 0.024838196,\n", + " -0.036314182,\n", + " 0.06807027,\n", + " -0.046411086,\n", + " 0.012543244,\n", + " -0.0015524302,\n", + " -0.005904932,\n", + " 0.03395419,\n", + " -0.012026594,\n", + " -0.030101227,\n", + " 0.028219236,\n", + " 0.030846382,\n", + " 0.004014791,\n", + " 0.0011687118,\n", + " -0.005924506,\n", + " -0.045966923,\n", + " 0.011490533,\n", + " 0.0070699626,\n", + " -0.04636452,\n", + " 0.051188413,\n", + " -0.010941066,\n", + " -0.0003843776,\n", + " -0.03554462,\n", + " 0.031527005,\n", + " 0.009976034,\n", + " -0.07566613,\n", + " 0.009484453,\n", + " 0.075585775,\n", + " 0.036681112,\n", + " -0.01997137,\n", + " 0.04221241,\n", + " 0.028756386,\n", + " -0.0051457584,\n", + " 0.017223062,\n", + " -0.026450416,\n", + " -0.0031493392,\n", + " -0.031142443,\n", + " 0.014129824,\n", + " 0.030640334,\n", + " 0.029624552,\n", + " -0.028791834,\n", + " 0.014263747,\n", + " -0.052234437,\n", + " 0.016012207,\n", + " 0.0054665036,\n", + " 0.049960792,\n", + " 0.01722948,\n", + " -0.045383565,\n", + " 0.035611328,\n", + " 0.017666759,\n", + " -0.034179296,\n", + " 0.029283382,\n", + " -0.0925589,\n", + " 0.005352651,\n", + " 0.015380154,\n", + " -0.025827546,\n", + " 0.078813694,\n", + " 0.023472652,\n", + " -0.015502742,\n", + " -0.0109618185,\n", + " -0.062091105,\n", + " 0.020872923,\n", + " 0.0000086566615,\n", + " -0.046515323,\n", + " -0.010241027,\n", + " 0.07056774,\n", + " -0.0039463,\n", + " -0.0049326513,\n", + " 0.08365995,\n", + " 0.04134926,\n", + " 0.028786693,\n", + " 0.003118606,\n", + " -0.00762385,\n", + " 0.0374987,\n", + " 0.011105095,\n", + " -0.063480176,\n", + " 0.0057922564,\n", + " 0.031258017,\n", + " 0.016701866,\n", + " -0.028914252,\n", + " -0.003122066,\n", + " 0.0040146816,\n", + " -0.042392317,\n", + " 0.007909141,\n", + " -0.0074412455,\n", + " -0.061981037,\n", + " -0.0753461,\n", + " -0.017482404,\n", + " 0.0019353802,\n", + " -0.039474253,\n", + " -0.03557083,\n", + " 0.02512347,\n", + " -0.03232185,\n", + " 0.029252835,\n", + " 0.0036022866,\n", + " -0.0006892634,\n", + " 0.020094976,\n", + " -0.038219,\n", + " -0.017786479,\n", + " -0.08057002,\n", + " 0.031012703,\n", + " 0.0027172887,\n", + " 0.008962194,\n", + " -0.052723087,\n", + " -0.010544319,\n", + " -0.015351896,\n", + " 0.032455456,\n", + " -0.018037044,\n", + " -0.031501703,\n", + " -0.00675466,\n", + " 0.0221693,\n", + " 0.045492973,\n", + " -0.0019718895,\n", + " -0.036067158,\n", + " -0.019214695,\n", + " 0.092174225,\n", + " 0.0011163659,\n", + " 0.020685544,\n", + " 0.042855497,\n", + " -0.037252106,\n", + " 0.0040059835,\n", + " 0.01912792,\n", + " -0.015698344,\n", + " 0.04483261,\n", + " -0.004036565,\n", + " 0.034471065,\n", + " -0.00026268934,\n", + " 0.021624925,\n", + " -0.029354827,\n", + " 0.047258046,\n", + " 0.00198258,\n", + " 0.030219225,\n", + " -0.070994265,\n", + " -0.012291296,\n", + " -0.06872952,\n", + " -0.01746057,\n", + " 0.051459547,\n", + " -0.005943351,\n", + " -0.05806519,\n", + " -0.049041413,\n", + " -0.0029545315,\n", + " -0.03594199,\n", + " -0.02741998,\n", + " 0.023392593,\n", + " 0.06987801,\n", + " 0.03409129,\n", + " 0.010657495,\n", + " 0.029227218,\n", + " -0.016149484,\n", + " -0.033026453,\n", + " -0.026461514,\n", + " -0.029547209,\n", + " 0.052853283,\n", + " -0.005257883,\n", + " 0.019270778,\n", + " -0.021651607,\n", + " -0.0679393,\n", + " 0.022915237,\n", + " -0.018916594,\n", + " 0.020382203,\n", + " 0.0061164782,\n", + " -0.0053500766,\n", + " 0.04022389,\n", + " 0.010382376,\n", + " 0.0037303683,\n", + " 0.00038739407,\n", + " 0.043591883,\n", + " -0.050327547,\n", + " -0.0032173207,\n", + " 0.02382172,\n", + " -0.018193057,\n", + " -0.049482215,\n", + " -0.034972608,\n", + " -0.03591731,\n", + " 0.055168044,\n", + " 0.04351997,\n", + " 0.042791825,\n", + " 0.014279212,\n", + " 0.007098134,\n", + " 0.041995537,\n", + " 0.02505999,\n", + " -0.014369368,\n", + " 0.022210745,\n", + " 0.035329152,\n", + " -0.0018724868,\n", + " 0.04496197,\n", + " -0.015458536,\n", + " -0.035687756,\n", + " 0.11576407,\n", + " 0.014072529,\n", + " 0.01368354,\n", + " -0.044601526,\n", + " -0.017274825,\n", + " -0.035651878,\n", + " 0.018606395,\n", + " -0.02624995,\n", + " -0.008605139,\n", + " -0.05559558,\n", + " -0.031822406,\n", + " -0.0025050528,\n", + " -0.007260074,\n", + " 0.008371022,\n", + " -0.009121923,\n", + " -0.010686996,\n", + " -0.004175405,\n", + " -0.07709291,\n", + " 0.02095484,\n", + " 0.061555583,\n", + " 0.05423064,\n", + " -0.08377491,\n", + " -0.044701204,\n", + " -0.022143545,\n", + " 0.03825245,\n", + " 0.020806536,\n", + " -0.025773121,\n", + " 0.026748922,\n", + " -0.035925206,\n", + " 0.007971478,\n", + " -0.07475945,\n", + " -0.067393735,\n", + " -0.01523033,\n", + " -0.025753228,\n", + " 0.0007241217,\n", + " -0.016581649,\n", + " -0.017368209,\n", + " 0.008112616,\n", + " -0.008466575,\n", + " -0.009379433,\n", + " 0.013422547,\n", + " 0.010592169,\n", + " -0.0036504674,\n", + " -0.041012507,\n", + " -0.018081397,\n", + " 0.005491686,\n", + " -0.02313517,\n", + " 0.010353996,\n", + " 0.06254845,\n", + " -0.029144084,\n", + " 0.07706289,\n", + " -0.002867055,\n", + " -0.022228312,\n", + " -0.028821543,\n", + " 0.00022086965,\n", + " -0.05151184,\n", + " 0.0114417225,\n", + " -0.10001401,\n", + " -0.007430506,\n", + " -0.0810789,\n", + " -0.0106861945,\n", + " -0.022859078,\n", + " -0.011867412,\n", + " -0.03224893,\n", + " 0.017619586,\n", + " 0.07519098,\n", + " -0.0035126992,\n", + " 0.005702041,\n", + " 0.0050863526,\n", + " -0.024752518,\n", + " -0.051708452,\n", + " -0.08042799,\n", + " -0.0016043095,\n", + " -0.054452665,\n", + " 0.04997996,\n", + " -0.022929264,\n", + " 0.07225404,\n", + " 0.057153042,\n", + " 0.016426055,\n", + " -0.04732747,\n", + " 0.015056493,\n", + " 0.036387,\n", + " -0.011774074,\n", + " -0.01798128,\n", + " -0.018891433,\n", + " 0.027562132,\n", + " 0.026849896,\n", + " -0.027375022,\n", + " 0.014004462,\n", + " -0.04581184,\n", + " 0.062606476,\n", + " -0.028271144,\n", + " -0.03200168,\n", + " 0.01676934,\n", + " 0.005372289,\n", + " -0.039633606,\n", + " 0.013623909,\n", + " 0.0483795,\n", + " 0.025562169,\n", + " -0.0007961121,\n", + " -0.010983261,\n", + " -0.03702811,\n", + " -0.020723386,\n", + " 0.01622944,\n", + " 0.028984541,\n", + " 0.052704614,\n", + " 0.026976695,\n", + " 0.040055428,\n", + " -0.027315127,\n", + " 0.022882,\n", + " -0.004998423,\n", + " 0.005663411,\n", + " 0.05058019,\n", + " 0.025238585,\n", + " -0.0043412056,\n", + " -0.010151074,\n", + " -0.005550237,\n", + " 0.012124635,\n", + " -0.012980639,\n", + " -0.030452866,\n", + " -0.009688401,\n", + " 0.0011759287,\n", + " 0.05065029,\n", + " -0.034934316,\n", + " 0.00009035412,\n", + " 0.0016641455,\n", + " 0.038797174,\n", + " -0.041665185,\n", + " 0.02898577,\n", + " 0.0050686207,\n", + " -0.11780856,\n", + " -0.017124109,\n", + " 0.058547672,\n", + " -0.047212645,\n", + " 0.019724954,\n", + " 0.052281905,\n", + " -0.028578363,\n", + " 0.041821305,\n", + " -0.01702321,\n", + " 0.07445442,\n", + " -0.026752556,\n", + " -0.005502298,\n", + " -0.030765718,\n", + " 0.018439377,\n", + " -0.016507415,\n", + " 0.053340096,\n", + " 0.027617462,\n", + " 0.0028326863,\n", + " 0.043026447,\n", + " -0.036896102,\n", + " 0.015555754,\n", + " -0.028502347,\n", + " -0.027034258,\n", + " 0.024761003,\n", + " 0.06037164,\n", + " -0.088444225,\n", + " 0.020785877,\n", + " 0.01979808,\n", + " -0.024642324,\n", + " 0.030752076,\n", + " 0.04398454,\n", + " -0.018832913,\n", + " -0.019311974,\n", + " 0.027594192,\n", + " -0.029102236,\n", + " -0.009168705,\n", + " -0.012181484,\n", + " -0.023603536,\n", + " -0.019860711,\n", + " -0.0035978511,\n", + " 0.012397888,\n", + " 0.0011611527,\n", + " 0.0898995,\n", + " 0.02485896,\n", + " -0.005481566,\n", + " -0.039879583,\n", + " 0.022059798,\n", + " -0.012275004,\n", + " -0.014664887,\n", + " 0.026405737,\n", + " 0.006707709,\n", + " 0.0036560902,\n", + " 0.07902236,\n", + " -0.037842136,\n", + " -0.034537956,\n", + " 0.028122894,\n", + " -0.010967483,\n", + " 0.002525521,\n", + " 0.06961038,\n", + " 0.016122231,\n", + " -0.03932486,\n", + " 0.024220413,\n", + " -0.042630956,\n", + " 0.02517927,\n", + " 0.054458976,\n", + " 0.013454574,\n", + " 0.06871976,\n", + " -0.0023826372,\n", + " -0.06773266,\n", + " 0.02460262,\n", + " -0.062439863,\n", + " -0.05781772,\n", + " -0.045605063,\n", + " 0.027145335,\n", + " -0.04323481,\n", + " -0.027004242,\n", + " 0.027012022,\n", + " 0.0021861214,\n", + " 0.016324826,\n", + " -0.0575887,\n", + " 0.0639403,\n", + " -0.013034681,\n", + " 0.05562446,\n", + " -0.02185531,\n", + " 0.025901046,\n", + " -0.019938763,\n", + " 0.008652073,\n", + " 0.030600363,\n", + " 0.036625423,\n", + " -0.001488325,\n", + " -0.014308819,\n", + " -0.035884213,\n", + " -0.0443492,\n", + " -0.018744895,\n", + " 0.012494876,\n", + " 0.009342181,\n", + " -0.023556268,\n", + " -0.024485394,\n", + " 0.008759082,\n", + " -0.036470927,\n", + " 0.003922266,\n", + " -0.005570674,\n", + " 0.06833909,\n", + " 0.0064327326,\n", + " -0.018937796,\n", + " -0.00621957,\n", + " 0.062171705,\n", + " 0.038591076,\n", + " 0.031692512,\n", + " 0.041171357,\n", + " 0.021134553,\n", + " -0.0029191682,\n", + " -0.03674039,\n", + " 0.024994813,\n", + " -0.023660952,\n", + " -0.055257946,\n", + " 0.040094994,\n", + " -0.008852677,\n", + " -0.087461375,\n", + " 0.01325573,\n", + " 0.040444717,\n", + " -0.01021572,\n", + " -0.026924513,\n", + " 0.034332998,\n", + " 0.03086733,\n", + " -0.07686781,\n", + " -0.016338205,\n", + " -0.020646619,\n", + " -0.042191442,\n", + " 0.009642032,\n", + " 0.027536497,\n", + " 0.022932088,\n", + " -0.014337762,\n", + " -0.035221837,\n", + " -0.031101929,\n", + " -0.050192293,\n", + " 0.04678706,\n", + " 0.0022375528,\n", + " -0.019851457,\n", + " 0.05928813,\n", + " -0.00034617726,\n", + " 0.02348867,\n", + " -0.005559518,\n", + " 0.024877217,\n", + " 0.006464173,\n", + " -0.061497923,\n", + " -0.044427488,\n", + " 0.09275633,\n", + " -0.060154688,\n", + " 0.035813265,\n", + " 0.008149022,\n", + " -0.021311855,\n", + " 0.06460764,\n", + " 0.074633114,\n", + " -0.055023994,\n", + " 0.008292285,\n", + " 0.0034740432,\n", + " 0.04366205,\n", + " -0.019244209,\n", + " -0.011739611,\n", + " 0.010764034,\n", + " 0.009531266,\n", + " 0.01438961,\n", + " 0.036831133,\n", + " -0.014654368,\n", + " 0.025802445,\n", + " -0.05894489,\n", + " -0.024810959,\n", + " -0.0048909825,\n", + " -0.02695748,\n", + " 0.0062228707,\n", + " -0.029853752,\n", + " 0.07839843,\n", + " 0.025475468,\n", + " 0.03605201,\n", + " -0.013841105,\n", + " 0.034315526,\n", + " 0.05802323,\n", + " -0.0065083285,\n", + " -0.049404792,\n", + " 0.0047248784,\n", + " 0.04340827,\n", + " -0.037954953,\n", + " 0.022516504,\n", + " 0.0039298353,\n", + " 0.00731798,\n", + " 0.03454248,\n", + " -0.01497592,\n", + " 0.04957702,\n", + " -0.056836925,\n", + " -0.039613705,\n", + " 0.030464869,\n", + " 0.03466243,\n", + " -0.0054599266,\n", + " 0.0375021,\n", + " -0.0047780927,\n", + " -0.04908544,\n", + " 0.030942274,\n", + " 0.055504274,\n", + " -0.018186081,\n", + " 0.008902889,\n", + " -0.02538345,\n", + " -0.008923959,\n", + " 0.06603814,\n", + " -0.026365338,\n", + " 0.06799129,\n", + " -0.014765047,\n", + " -0.019033851,\n", + " 0.06114885,\n", + " -0.04529476,\n", + " -0.03121909,\n", + " 0.035800617,\n", + " -0.033105463,\n", + " 0.0592133,\n", + " 0.015604761,\n", + " 0.039122812,\n", + " -0.009252219,\n", + " -0.06183396,\n", + " -0.04536972,\n", + " 0.035133872,\n", + " 0.028567217,\n", + " 0.028155535,\n", + " 0.044882603,\n", + " -0.018319324,\n", + " 0.023039794,\n", + " 0.0067167506,\n", + " -0.026577776,\n", + " -0.058001574,\n", + " -0.104534015,\n", + " 0.042269215,\n", + " 0.004363603,\n", + " 0.048697747,\n", + " 0.04533539,\n", + " -0.05496062,\n", + " -0.021759328,\n", + " -0.004851495,\n", + " 0.03850219,\n", + " 0.020519726,\n", + " -0.04097515,\n", + " -0.001369751,\n", + " -0.016953135,\n", + " 0.046057485,\n", + " 0.005478688,\n", + " 0.033872366,\n", + " -0.01388759,\n", + " 0.026152821,\n", + " ],\n", + " },\n", + " {\n", + " \"_id\": \"54633\",\n", + " \"content\": \"Employee number 54633, name John Doe, department Sales, location New York, salary 100000\",\n", + " \"embedding\": [\n", + " 0.02363214,\n", + " -0.064981155,\n", + " -0.015693784,\n", + " -0.0007628399,\n", + " 0.053643532,\n", + " 0.03410332,\n", + " 0.061779644,\n", + " -0.018410124,\n", + " 0.00021801237,\n", + " 0.010404121,\n", + " -0.034521878,\n", + " -0.0018919241,\n", + " -0.031763557,\n", + " -0.021995055,\n", + " -0.028728155,\n", + " 0.021817293,\n", + " 0.017098326,\n", + " -0.023482114,\n", + " 0.00035919988,\n", + " -0.030648591,\n", + " -0.040644307,\n", + " -0.022990027,\n", + " -0.03393246,\n", + " -0.006558424,\n", + " 0.02599438,\n", + " -0.002243526,\n", + " -0.005706434,\n", + " -0.09497937,\n", + " -0.041159507,\n", + " -0.014462122,\n", + " -0.07141966,\n", + " 0.036013767,\n", + " -0.040423963,\n", + " 0.015345732,\n", + " -0.010977615,\n", + " -0.031959552,\n", + " -0.04254595,\n", + " 0.0140362885,\n", + " -0.0050170403,\n", + " 0.0062000453,\n", + " -0.03828404,\n", + " -0.0153707955,\n", + " -0.02084843,\n", + " -0.029029334,\n", + " 0.0488787,\n", + " 0.0116918655,\n", + " -0.0008196994,\n", + " 0.02450069,\n", + " 0.012549454,\n", + " -0.098332606,\n", + " 0.034913078,\n", + " -0.011317091,\n", + " 0.05609082,\n", + " -0.023273163,\n", + " -0.018277766,\n", + " -0.06916207,\n", + " 0.00826931,\n", + " 0.010393335,\n", + " -0.01787084,\n", + " -0.042722043,\n", + " -0.011604089,\n", + " -0.0012522464,\n", + " -0.014621865,\n", + " 0.038314685,\n", + " 0.0005260519,\n", + " -0.06758038,\n", + " -0.018045135,\n", + " 0.010444268,\n", + " 0.07087152,\n", + " -0.00284572,\n", + " -0.037000503,\n", + " -0.0025446592,\n", + " 0.04700479,\n", + " -0.001956285,\n", + " -0.052959703,\n", + " -0.12006671,\n", + " -0.0042574876,\n", + " 0.033431716,\n", + " 0.053164013,\n", + " 0.045192037,\n", + " 0.0069061965,\n", + " -0.015518668,\n", + " -0.030133313,\n", + " -0.044831418,\n", + " -0.03726597,\n", + " 0.057425573,\n", + " 0.038113765,\n", + " -0.027094543,\n", + " -0.007922181,\n", + " 0.04684854,\n", + " -0.019562198,\n", + " 0.030295257,\n", + " -0.004370621,\n", + " -0.058695186,\n", + " -0.018610591,\n", + " 0.061370887,\n", + " 0.030731026,\n", + " -0.04589357,\n", + " 0.009940706,\n", + " -0.01948416,\n", + " -0.0046085874,\n", + " 0.0022432224,\n", + " -0.037660263,\n", + " 0.0066369097,\n", + " 0.024275409,\n", + " -0.00056191423,\n", + " -0.000042045995,\n", + " -0.011206171,\n", + " -0.045394268,\n", + " 0.0071125193,\n", + " -0.07760038,\n", + " 0.00075220404,\n", + " -0.01073115,\n", + " -0.04549924,\n", + " 0.06086503,\n", + " -0.039449498,\n", + " -0.058962233,\n", + " 0.06468895,\n", + " 0.04064492,\n", + " 0.0028264702,\n", + " 0.046224788,\n", + " 0.054499805,\n", + " 0.017846588,\n", + " 0.039633967,\n", + " 0.043515794,\n", + " 0.045659285,\n", + " -0.008033441,\n", + " 0.017785944,\n", + " 0.110720046,\n", + " 0.04685865,\n", + " -0.01802922,\n", + " -0.040406503,\n", + " 0.046266943,\n", + " -0.013695085,\n", + " 0.049763296,\n", + " 0.06897263,\n", + " 0.04518968,\n", + " 0.053687356,\n", + " 0.047708154,\n", + " -0.034360345,\n", + " -0.006671896,\n", + " 0.001714356,\n", + " -0.04809813,\n", + " -0.014786435,\n", + " -0.017878355,\n", + " -0.008214343,\n", + " -0.0021909962,\n", + " -0.046269346,\n", + " 0.072654426,\n", + " -0.017648848,\n", + " 0.024896594,\n", + " -0.007919613,\n", + " -0.022969129,\n", + " 0.03022781,\n", + " 0.011041212,\n", + " 0.02506789,\n", + " -0.042059314,\n", + " -0.012793883,\n", + " 0.014914554,\n", + " -0.0069050984,\n", + " 0.04926195,\n", + " 0.029791638,\n", + " 0.00091826794,\n", + " 0.022105714,\n", + " 0.02267874,\n", + " 0.01301686,\n", + " 0.041148506,\n", + " -0.040438164,\n", + " -0.017320365,\n", + " -0.03499895,\n", + " 0.021354463,\n", + " 0.01690759,\n", + " -0.025965609,\n", + " -0.031534,\n", + " -0.030494336,\n", + " -0.07054347,\n", + " -0.013133889,\n", + " -0.012822187,\n", + " -0.029168444,\n", + " -0.0218087,\n", + " -0.026540095,\n", + " -0.03263288,\n", + " 0.0021044614,\n", + " 0.048010275,\n", + " -0.01386612,\n", + " 0.038521104,\n", + " 0.04187871,\n", + " -0.043820612,\n", + " 0.01064401,\n", + " -0.02302523,\n", + " 0.036518324,\n", + " 0.02567038,\n", + " -0.02029525,\n", + " -0.008654853,\n", + " 0.006971086,\n", + " 0.031201571,\n", + " 0.025180522,\n", + " 0.04371456,\n", + " 0.003744122,\n", + " -0.030606078,\n", + " -0.057033766,\n", + " 0.07168329,\n", + " 0.008192757,\n", + " 0.0008544097,\n", + " 0.021805858,\n", + " -0.03130309,\n", + " 0.07239574,\n", + " -0.070142336,\n", + " -0.008480367,\n", + " -0.008728997,\n", + " -0.0034903064,\n", + " 0.046792153,\n", + " -0.023682427,\n", + " -0.030346792,\n", + " 0.019847026,\n", + " 0.012278681,\n", + " -0.0025996969,\n", + " 0.031041447,\n", + " -0.0077332347,\n", + " -0.038237624,\n", + " 0.012388913,\n", + " 0.0188294,\n", + " -0.02149499,\n", + " 0.051257458,\n", + " 0.002782599,\n", + " -0.010533314,\n", + " 0.0011125503,\n", + " 0.012332888,\n", + " 0.01806485,\n", + " -0.06757561,\n", + " 0.0023377982,\n", + " 0.09027674,\n", + " 0.0307473,\n", + " -0.0031313177,\n", + " 0.031805944,\n", + " 0.02137824,\n", + " -0.015408471,\n", + " 0.00030692422,\n", + " -0.020330938,\n", + " 0.023312671,\n", + " -0.030245807,\n", + " 0.025795639,\n", + " 0.04197928,\n", + " 0.00660178,\n", + " -0.040649693,\n", + " 0.024375524,\n", + " -0.04237185,\n", + " 0.032011457,\n", + " 0.015374865,\n", + " 0.04028766,\n", + " 0.010178039,\n", + " -0.03617627,\n", + " 0.047202107,\n", + " 0.020767882,\n", + " -0.04539947,\n", + " 0.019767804,\n", + " -0.10889575,\n", + " 0.017927451,\n", + " 0.017144594,\n", + " -0.015266046,\n", + " 0.06631826,\n", + " 0.02412635,\n", + " -0.024798216,\n", + " -0.008509299,\n", + " -0.0639002,\n", + " 0.0136915855,\n", + " 0.0027062744,\n", + " -0.064476475,\n", + " -0.0012653655,\n", + " 0.07816678,\n", + " -0.012643878,\n", + " -0.008585973,\n", + " 0.07736182,\n", + " 0.04327385,\n", + " 0.025656862,\n", + " 0.0030979763,\n", + " 0.00021765077,\n", + " 0.031746045,\n", + " 0.02362011,\n", + " -0.04819947,\n", + " -0.012916141,\n", + " 0.018860366,\n", + " 0.017766127,\n", + " -0.023901632,\n", + " 0.004137154,\n", + " 0.0041561704,\n", + " -0.0022801503,\n", + " 0.009764509,\n", + " 0.002656565,\n", + " -0.04468994,\n", + " -0.07757732,\n", + " -0.015850794,\n", + " 0.010670362,\n", + " -0.04420402,\n", + " -0.039033562,\n", + " 0.0031982567,\n", + " -0.04361803,\n", + " 0.034209713,\n", + " 0.005868743,\n", + " 0.032322675,\n", + " 0.039166275,\n", + " -0.03746624,\n", + " -0.021231664,\n", + " -0.06653363,\n", + " 0.059266083,\n", + " 0.016893726,\n", + " 0.022510596,\n", + " -0.06638812,\n", + " -0.026510475,\n", + " -0.011830923,\n", + " 0.0069003874,\n", + " -0.043289896,\n", + " -0.03288132,\n", + " -0.011146353,\n", + " 0.0287577,\n", + " 0.04004958,\n", + " -0.0014789595,\n", + " -0.02158115,\n", + " -0.012407836,\n", + " 0.073853076,\n", + " 0.021458639,\n", + " 0.020401636,\n", + " 0.039237395,\n", + " -0.025395788,\n", + " -0.005443788,\n", + " 0.030352518,\n", + " -0.035680313,\n", + " 0.032063533,\n", + " 0.0016429706,\n", + " 0.01741445,\n", + " 0.0024685974,\n", + " 0.034620967,\n", + " -0.010647702,\n", + " 0.0526942,\n", + " -0.0034993906,\n", + " 0.03208014,\n", + " -0.08731866,\n", + " -0.015013707,\n", + " -0.06679643,\n", + " -0.015791807,\n", + " 0.033754732,\n", + " -0.00432221,\n", + " -0.049488492,\n", + " -0.04113329,\n", + " -0.025805045,\n", + " -0.01941248,\n", + " -0.027105281,\n", + " -0.0048762094,\n", + " 0.063147336,\n", + " 0.041223466,\n", + " 0.028617661,\n", + " 0.021648958,\n", + " -0.041316215,\n", + " -0.0313366,\n", + " -0.035062548,\n", + " -0.033159826,\n", + " 0.040288758,\n", + " 0.0010510484,\n", + " 0.007258658,\n", + " -0.032413058,\n", + " -0.061028056,\n", + " 0.031196948,\n", + " -0.021832671,\n", + " 0.014297596,\n", + " 0.01129684,\n", + " -0.014241179,\n", + " 0.019869702,\n", + " 0.02111102,\n", + " 0.0012747784,\n", + " -0.019946355,\n", + " 0.05248107,\n", + " -0.062233597,\n", + " 0.015092951,\n", + " 0.009568825,\n", + " -0.013843593,\n", + " -0.053562496,\n", + " -0.061670925,\n", + " -0.035305984,\n", + " 0.032908812,\n", + " 0.04857493,\n", + " 0.034953453,\n", + " 0.023726141,\n", + " 0.03568444,\n", + " 0.0071175913,\n", + " 0.033559702,\n", + " -0.0121424105,\n", + " 0.03407673,\n", + " 0.057266288,\n", + " -0.012657767,\n", + " 0.06768064,\n", + " -0.022355225,\n", + " -0.030181471,\n", + " 0.12063107,\n", + " 0.012808932,\n", + " 0.030716958,\n", + " -0.036874283,\n", + " -0.008254023,\n", + " -0.01081548,\n", + " 0.020372739,\n", + " -0.027203616,\n", + " 0.0015654373,\n", + " -0.039488234,\n", + " -0.022952735,\n", + " -0.0011268638,\n", + " -0.009785246,\n", + " -0.0019360933,\n", + " 0.016225388,\n", + " -0.018154368,\n", + " -0.014471327,\n", + " -0.05883742,\n", + " 0.012274111,\n", + " 0.06887592,\n", + " 0.052230723,\n", + " -0.06945254,\n", + " -0.036823668,\n", + " -0.012421808,\n", + " 0.035832312,\n", + " 0.02932272,\n", + " -0.013966943,\n", + " 0.057543058,\n", + " -0.023411168,\n", + " 0.025161343,\n", + " -0.0649318,\n", + " -0.06453301,\n", + " -0.024157293,\n", + " -0.03283516,\n", + " 0.0070455656,\n", + " -0.024008652,\n", + " -0.022920165,\n", + " 0.015138752,\n", + " 0.010144105,\n", + " -0.008382338,\n", + " 0.044042453,\n", + " 0.018641355,\n", + " -0.00897114,\n", + " -0.022986831,\n", + " -0.024504658,\n", + " 0.005061791,\n", + " -0.046147745,\n", + " 0.017877372,\n", + " 0.055260062,\n", + " -0.03701096,\n", + " 0.075398736,\n", + " 0.008653546,\n", + " -0.021892056,\n", + " -0.020546617,\n", + " 0.014034242,\n", + " -0.072182335,\n", + " 0.013067999,\n", + " -0.100795396,\n", + " 0.010451056,\n", + " -0.07050469,\n", + " -0.011445101,\n", + " -0.03754845,\n", + " 0.006183421,\n", + " -0.03906792,\n", + " -0.0055965204,\n", + " 0.05707792,\n", + " -0.010429032,\n", + " -0.0011429724,\n", + " 0.005118022,\n", + " -0.016644083,\n", + " -0.04220137,\n", + " -0.07363171,\n", + " 0.0024569791,\n", + " -0.036916792,\n", + " 0.03395262,\n", + " -0.02537861,\n", + " 0.07667082,\n", + " 0.035887685,\n", + " 0.015899615,\n", + " -0.07066271,\n", + " 0.0015284163,\n", + " 0.044092063,\n", + " -0.00084555487,\n", + " -0.031053497,\n", + " -0.009409518,\n", + " 0.019150222,\n", + " 0.039110914,\n", + " -0.026089815,\n", + " 0.025691986,\n", + " -0.052151006,\n", + " 0.072509676,\n", + " -0.024798574,\n", + " -0.03921443,\n", + " 0.008295112,\n", + " -0.00042773844,\n", + " -0.041100286,\n", + " 0.030542733,\n", + " 0.039614253,\n", + " 0.01804182,\n", + " -0.0019106811,\n", + " -0.0048501906,\n", + " -0.03208538,\n", + " -0.0050331447,\n", + " 0.026386712,\n", + " 0.024575505,\n", + " 0.05588996,\n", + " 0.030057926,\n", + " 0.01409509,\n", + " -0.031694356,\n", + " 0.017517397,\n", + " 0.0046301717,\n", + " 0.007145245,\n", + " 0.07115179,\n", + " 0.0035148985,\n", + " -0.014188136,\n", + " 0.007305263,\n", + " -0.0128924055,\n", + " 0.0012173483,\n", + " -0.010264721,\n", + " -0.013301308,\n", + " -0.021946715,\n", + " 0.012608889,\n", + " 0.06063012,\n", + " -0.02197872,\n", + " 0.011334535,\n", + " -0.017498214,\n", + " 0.040217794,\n", + " -0.029707987,\n", + " 0.03888635,\n", + " 0.007113082,\n", + " -0.10245564,\n", + " 0.019598834,\n", + " 0.042800713,\n", + " -0.068540476,\n", + " -0.007941252,\n", + " 0.029602854,\n", + " 0.012320459,\n", + " 0.04070456,\n", + " 0.0048046396,\n", + " 0.057080273,\n", + " -0.041693073,\n", + " 0.0165682,\n", + " -0.037762154,\n", + " 0.030711599,\n", + " -0.023082186,\n", + " 0.06444822,\n", + " 0.02103803,\n", + " -0.0064671254,\n", + " 0.035683487,\n", + " -0.04167311,\n", + " 0.0337175,\n", + " -0.020304035,\n", + " -0.043164253,\n", + " 0.033318438,\n", + " 0.051226508,\n", + " -0.09993186,\n", + " 0.023990132,\n", + " 0.035067804,\n", + " -0.02158245,\n", + " 0.02973254,\n", + " 0.045522075,\n", + " -0.037720405,\n", + " -0.016477076,\n", + " 0.017233508,\n", + " -0.031183288,\n", + " -0.002931218,\n", + " -0.006327033,\n", + " -0.018274536,\n", + " -0.0043489537,\n", + " -0.010508976,\n", + " 0.010018209,\n", + " 0.029612847,\n", + " 0.092786245,\n", + " 0.030959306,\n", + " -0.006647051,\n", + " -0.027481854,\n", + " 0.033632692,\n", + " -0.023163252,\n", + " -0.010413391,\n", + " 0.04556712,\n", + " -0.0027589782,\n", + " 0.029712437,\n", + " 0.06004067,\n", + " -0.030746799,\n", + " -0.03539816,\n", + " 0.02215609,\n", + " -0.008097731,\n", + " 0.0035610283,\n", + " 0.060080826,\n", + " -0.0088831335,\n", + " -0.019353531,\n", + " 0.012506012,\n", + " -0.04578203,\n", + " 0.026642656,\n", + " 0.034759957,\n", + " 0.03317829,\n", + " 0.06778447,\n", + " -0.0039658644,\n", + " -0.055566087,\n", + " 0.023027683,\n", + " -0.041180346,\n", + " -0.035393525,\n", + " -0.027815914,\n", + " 0.014628632,\n", + " -0.040841658,\n", + " -0.02875485,\n", + " 0.017050356,\n", + " -0.018104397,\n", + " 0.032889456,\n", + " -0.052504424,\n", + " 0.05182534,\n", + " -0.024680488,\n", + " 0.05011892,\n", + " -0.030946976,\n", + " 0.012457738,\n", + " -0.028428216,\n", + " 0.044254918,\n", + " 0.026299495,\n", + " 0.041920617,\n", + " -0.01592546,\n", + " -0.026756888,\n", + " -0.021019576,\n", + " -0.031648703,\n", + " -0.008724201,\n", + " 0.0025635513,\n", + " 0.0113416435,\n", + " -0.04281193,\n", + " -0.042036083,\n", + " -0.0067297197,\n", + " -0.043461386,\n", + " 0.00083167566,\n", + " -0.009508976,\n", + " 0.059358858,\n", + " -0.014656265,\n", + " -0.00035070922,\n", + " -0.0049913535,\n", + " 0.034104995,\n", + " 0.044627994,\n", + " 0.04142639,\n", + " 0.038221695,\n", + " 0.024629146,\n", + " -0.010383416,\n", + " -0.008619005,\n", + " 0.029898448,\n", + " -0.040645078,\n", + " -0.055725325,\n", + " 0.029977558,\n", + " -0.018410092,\n", + " -0.11042691,\n", + " 0.012425915,\n", + " 0.040628515,\n", + " -0.014945932,\n", + " -0.021799535,\n", + " 0.041060366,\n", + " 0.028451148,\n", + " -0.046030525,\n", + " -0.017889444,\n", + " -0.017596401,\n", + " -0.016248139,\n", + " -0.013585491,\n", + " 0.012225498,\n", + " 0.022918489,\n", + " -0.0130026005,\n", + " -0.036756888,\n", + " -0.015256263,\n", + " -0.06046553,\n", + " 0.034536958,\n", + " 0.010706609,\n", + " -0.01574817,\n", + " 0.054597396,\n", + " 0.010708762,\n", + " 0.02091631,\n", + " 0.007813075,\n", + " 0.035738565,\n", + " 0.0096743,\n", + " -0.05741579,\n", + " -0.034075104,\n", + " 0.06407018,\n", + " -0.058274616,\n", + " 0.040782902,\n", + " 0.019084051,\n", + " -0.028117944,\n", + " 0.097568005,\n", + " 0.06757993,\n", + " -0.04616895,\n", + " 0.01835175,\n", + " 0.009599453,\n", + " 0.009899384,\n", + " -0.006697724,\n", + " -0.030587083,\n", + " -0.0057633854,\n", + " -0.0035771965,\n", + " 0.005236175,\n", + " 0.03161966,\n", + " -0.0014421007,\n", + " 0.02654683,\n", + " -0.06784111,\n", + " -0.033109434,\n", + " 0.0015561683,\n", + " -0.028957006,\n", + " -0.010133545,\n", + " -0.009049643,\n", + " 0.095160015,\n", + " 0.038473047,\n", + " 0.015532988,\n", + " -0.026837075,\n", + " 0.004548446,\n", + " 0.036702897,\n", + " 0.0034548303,\n", + " -0.04240495,\n", + " 0.0085659055,\n", + " 0.03814674,\n", + " -0.02157155,\n", + " 0.03191628,\n", + " 0.0018405454,\n", + " -0.004841512,\n", + " 0.016154964,\n", + " -0.022462817,\n", + " 0.04318009,\n", + " -0.055848856,\n", + " -0.037207298,\n", + " 0.05138956,\n", + " 0.047032602,\n", + " -0.02519051,\n", + " 0.021451518,\n", + " 0.004464725,\n", + " -0.055046022,\n", + " 0.02026468,\n", + " 0.056096263,\n", + " -0.031548444,\n", + " 0.03434432,\n", + " -0.048271492,\n", + " 0.0059668403,\n", + " 0.07247701,\n", + " -0.01061879,\n", + " 0.054317787,\n", + " -0.026415752,\n", + " -0.024185874,\n", + " 0.08290211,\n", + " -0.029081488,\n", + " -0.03949319,\n", + " 0.055290263,\n", + " -0.030485872,\n", + " 0.06952478,\n", + " 0.011051205,\n", + " 0.032816757,\n", + " -0.012162714,\n", + " -0.03957713,\n", + " -0.04050204,\n", + " 0.027956164,\n", + " 0.016105121,\n", + " 0.0035087462,\n", + " 0.04936729,\n", + " -0.04183739,\n", + " 0.0054607657,\n", + " 0.00022244385,\n", + " -0.048364908,\n", + " -0.05708388,\n", + " -0.05690664,\n", + " 0.02973829,\n", + " -0.0031154295,\n", + " 0.025180794,\n", + " 0.05131079,\n", + " -0.052830625,\n", + " -0.022286385,\n", + " 0.0075936974,\n", + " 0.016310522,\n", + " 0.027947418,\n", + " -0.04063135,\n", + " 0.0024504068,\n", + " 0.011263393,\n", + " 0.021755524,\n", + " -0.018598292,\n", + " 0.038954616,\n", + " -0.0022197817,\n", + " 0.0030547322,\n", + " ],\n", + " },\n", + " {\n", + " \"_id\": \"54636\",\n", + " \"content\": \"Employee number 54636, name Jane Smith, department Finance, location Chicago, salary 130000\",\n", + " \"embedding\": [\n", + " 0.033282682,\n", + " -0.03909191,\n", + " 0.0007547619,\n", + " -0.00166024,\n", + " 0.039782085,\n", + " 0.0022312212,\n", + " 0.050308637,\n", + " 0.0008865104,\n", + " 0.0044103186,\n", + " 0.03072421,\n", + " -0.0051613366,\n", + " -0.026194286,\n", + " -0.013544969,\n", + " -0.011848663,\n", + " -0.047196925,\n", + " -0.0067790328,\n", + " 0.027002288,\n", + " -0.020260727,\n", + " -0.0076200166,\n", + " -0.03599207,\n", + " -0.035114743,\n", + " -0.023491457,\n", + " -0.0077283946,\n", + " -0.026173472,\n", + " 0.021463424,\n", + " 0.0039335107,\n", + " 0.018358603,\n", + " -0.106973566,\n", + " -0.042405866,\n", + " -0.018040666,\n", + " -0.06100321,\n", + " 0.017380144,\n", + " -0.02887869,\n", + " 0.04157278,\n", + " -0.026515594,\n", + " 0.002928644,\n", + " -0.012694755,\n", + " 0.012007126,\n", + " 0.0037733233,\n", + " 0.046051748,\n", + " 0.005322323,\n", + " 0.0059584975,\n", + " -0.009696193,\n", + " -0.0066717616,\n", + " 0.0436459,\n", + " -0.022382155,\n", + " 0.032507967,\n", + " -0.0065392246,\n", + " 0.025054803,\n", + " -0.08322342,\n", + " 0.046882447,\n", + " -0.024875944,\n", + " 0.06102459,\n", + " -0.008675405,\n", + " -0.0209155,\n", + " -0.07849695,\n", + " 0.0020140782,\n", + " -0.0011147283,\n", + " -0.019611986,\n", + " -0.025552176,\n", + " -0.027990913,\n", + " 0.0037930773,\n", + " -0.009247857,\n", + " 0.052749302,\n", + " -0.0102324905,\n", + " -0.062436964,\n", + " -0.02680414,\n", + " 0.0022140676,\n", + " 0.06792232,\n", + " 0.003922225,\n", + " -0.032647397,\n", + " -0.03346009,\n", + " 0.07331381,\n", + " -0.019998021,\n", + " -0.06043405,\n", + " -0.07097224,\n", + " -0.018178217,\n", + " 0.007255711,\n", + " 0.05574352,\n", + " 0.03521836,\n", + " -0.008382421,\n", + " -0.0054113218,\n", + " -0.038427114,\n", + " -0.038553275,\n", + " -0.03860179,\n", + " 0.06459174,\n", + " 0.029251965,\n", + " -0.009218864,\n", + " -0.01445029,\n", + " 0.046301886,\n", + " -0.010660837,\n", + " 0.030970545,\n", + " 0.02029129,\n", + " -0.07135827,\n", + " -0.013141149,\n", + " 0.052297823,\n", + " -0.014865988,\n", + " -0.015496633,\n", + " -0.016228134,\n", + " -0.021733683,\n", + " 0.019089619,\n", + " -0.016229896,\n", + " -0.052840963,\n", + " -0.008882637,\n", + " -0.006283083,\n", + " 0.0034171198,\n", + " -0.009800554,\n", + " -0.00035290318,\n", + " -0.025829503,\n", + " 0.02211951,\n", + " -0.071032286,\n", + " -0.021045374,\n", + " -0.025188517,\n", + " -0.048652653,\n", + " 0.07619293,\n", + " -0.010589923,\n", + " -0.059194453,\n", + " 0.053808484,\n", + " 0.041753646,\n", + " 0.0038279262,\n", + " 0.027524192,\n", + " 0.059054792,\n", + " -0.0120413685,\n", + " 0.008316597,\n", + " 0.031715844,\n", + " 0.03668256,\n", + " -0.01620795,\n", + " 0.00094534125,\n", + " 0.1083495,\n", + " 0.030639175,\n", + " -0.029737566,\n", + " -0.057788074,\n", + " 0.027845988,\n", + " -0.009652855,\n", + " 0.055340156,\n", + " 0.0663029,\n", + " 0.04380604,\n", + " -0.011622515,\n", + " 0.06322969,\n", + " -0.019971412,\n", + " 0.003166246,\n", + " 0.022834063,\n", + " -0.018897917,\n", + " -0.0016617388,\n", + " -0.02413109,\n", + " 0.0017157173,\n", + " 0.010872734,\n", + " -0.011352978,\n", + " 0.006001529,\n", + " 0.015488254,\n", + " 0.0011707869,\n", + " 0.018522937,\n", + " -0.018514102,\n", + " 0.02900784,\n", + " 0.020825073,\n", + " 0.022771334,\n", + " -0.04606071,\n", + " 0.030873852,\n", + " 0.032193057,\n", + " -0.010461426,\n", + " 0.062585354,\n", + " 0.015402362,\n", + " -0.013989444,\n", + " 0.023873847,\n", + " -0.0001557276,\n", + " 0.028785564,\n", + " 0.082039945,\n", + " -0.04562552,\n", + " -0.040299766,\n", + " -0.027677026,\n", + " 0.018488018,\n", + " 0.041104753,\n", + " -0.03979478,\n", + " -0.030792084,\n", + " -0.043800704,\n", + " -0.07498492,\n", + " -0.009120495,\n", + " 0.009481535,\n", + " -0.006981507,\n", + " -0.019725543,\n", + " -0.033017475,\n", + " -0.011190301,\n", + " 0.008700168,\n", + " 0.030437404,\n", + " 0.0058765025,\n", + " 0.03509147,\n", + " 0.04839477,\n", + " -0.04233951,\n", + " -0.0050839223,\n", + " -0.00681981,\n", + " 0.03836845,\n", + " 0.004685588,\n", + " -0.03892133,\n", + " 0.006600561,\n", + " -0.0019655793,\n", + " 0.039389588,\n", + " -0.01809466,\n", + " 0.011489714,\n", + " -0.025835218,\n", + " -0.018884161,\n", + " -0.03204627,\n", + " 0.048295826,\n", + " 0.019568602,\n", + " 0.0053548636,\n", + " 0.033916872,\n", + " -0.015454683,\n", + " 0.05538897,\n", + " -0.033823296,\n", + " -0.0039371606,\n", + " 0.0037781983,\n", + " -0.0023951076,\n", + " 0.031877134,\n", + " -0.028111735,\n", + " -0.015856108,\n", + " 0.038164444,\n", + " 0.012281067,\n", + " 0.011310771,\n", + " 0.004349233,\n", + " -0.014538568,\n", + " -0.029191358,\n", + " -0.006300531,\n", + " 0.019091565,\n", + " -0.056574304,\n", + " 0.06351933,\n", + " 0.0007920405,\n", + " -0.00020863887,\n", + " -0.01369187,\n", + " 0.014471601,\n", + " 0.0048121824,\n", + " -0.06280206,\n", + " -0.0026793373,\n", + " 0.067380674,\n", + " 0.007164001,\n", + " -0.038997144,\n", + " 0.054033946,\n", + " -0.0022533264,\n", + " 0.013708685,\n", + " 0.038419407,\n", + " -0.015276563,\n", + " -0.004239497,\n", + " -0.026898738,\n", + " 0.005635743,\n", + " 0.03847782,\n", + " 0.022422716,\n", + " -0.030474218,\n", + " 0.0047512124,\n", + " -0.04953256,\n", + " 0.015068766,\n", + " 0.020016206,\n", + " 0.042567335,\n", + " 0.0028769623,\n", + " -0.03851735,\n", + " 0.046420325,\n", + " 0.011925669,\n", + " -0.022733988,\n", + " 0.026839085,\n", + " -0.07413135,\n", + " -0.0020509947,\n", + " 0.012577789,\n", + " -0.01844622,\n", + " 0.05583869,\n", + " 0.051888652,\n", + " -0.0048309774,\n", + " 0.009347729,\n", + " -0.049620014,\n", + " 0.047792498,\n", + " -0.01790054,\n", + " -0.0583071,\n", + " -0.021284584,\n", + " 0.06689755,\n", + " 0.004781726,\n", + " -0.012770478,\n", + " 0.07697373,\n", + " 0.03392616,\n", + " 0.014641257,\n", + " 0.008315434,\n", + " 0.004641932,\n", + " 0.057688177,\n", + " -0.00011591461,\n", + " -0.05162363,\n", + " 0.0132949175,\n", + " 0.054461304,\n", + " 0.04132465,\n", + " -0.05228104,\n", + " -0.008330981,\n", + " 0.024090331,\n", + " 0.0035575673,\n", + " 0.020221887,\n", + " 0.0046284744,\n", + " -0.08109927,\n", + " -0.08293294,\n", + " -0.0143710505,\n", + " -0.00088063197,\n", + " -0.066603884,\n", + " -0.05854246,\n", + " 0.023163913,\n", + " -0.048908163,\n", + " 0.016917551,\n", + " 0.0307055,\n", + " 0.006515332,\n", + " 0.0063499426,\n", + " -0.03967575,\n", + " -0.04001876,\n", + " -0.05907809,\n", + " 0.03273935,\n", + " 0.01719176,\n", + " 0.02424203,\n", + " -0.072151884,\n", + " -0.016568365,\n", + " -0.013442307,\n", + " 0.0270092,\n", + " -0.034306023,\n", + " -0.03671066,\n", + " -0.0067472355,\n", + " 0.019714633,\n", + " 0.057815082,\n", + " -0.012577134,\n", + " -0.013382564,\n", + " -0.03911529,\n", + " 0.050835066,\n", + " -0.0037874833,\n", + " -0.008278123,\n", + " 0.042883575,\n", + " -0.052752126,\n", + " -0.0025583908,\n", + " 0.033462517,\n", + " -0.00065002317,\n", + " 0.04533471,\n", + " -0.0154035175,\n", + " 0.031390563,\n", + " -0.0136398645,\n", + " 0.05136288,\n", + " -0.005182816,\n", + " 0.063051686,\n", + " 0.0050854594,\n", + " 0.035023358,\n", + " -0.083840184,\n", + " 0.006783878,\n", + " -0.08204774,\n", + " 0.007304815,\n", + " 0.063131176,\n", + " 0.007564634,\n", + " -0.054168995,\n", + " -0.04331101,\n", + " 0.011824145,\n", + " -0.03706767,\n", + " -0.013556429,\n", + " 0.040878236,\n", + " 0.0807747,\n", + " 0.055227622,\n", + " -0.018239543,\n", + " 0.012912111,\n", + " -0.022989053,\n", + " -0.0028701182,\n", + " -0.031126976,\n", + " -0.0047545466,\n", + " 0.029136088,\n", + " -0.017281001,\n", + " 0.01922514,\n", + " -0.012010304,\n", + " -0.04137593,\n", + " 0.034444544,\n", + " -0.02019,\n", + " 0.019743202,\n", + " 0.011670469,\n", + " -0.007273119,\n", + " 0.013197889,\n", + " 0.028474236,\n", + " -0.01086087,\n", + " 0.021434411,\n", + " 0.024562098,\n", + " -0.04574378,\n", + " 0.0064201616,\n", + " 0.0066477978,\n", + " -0.011263019,\n", + " -0.053637076,\n", + " -0.038792353,\n", + " -0.027472662,\n", + " 0.028990641,\n", + " 0.048245337,\n", + " 0.033630706,\n", + " 0.0068463734,\n", + " -0.008434694,\n", + " 0.05721538,\n", + " 0.032129478,\n", + " 0.00040128073,\n", + " 0.012669716,\n", + " 0.05994472,\n", + " -0.0030158863,\n", + " 0.0371618,\n", + " -0.0053152503,\n", + " -0.016319215,\n", + " 0.11017134,\n", + " -0.0046604937,\n", + " 0.0047023036,\n", + " -0.010484685,\n", + " -0.011737418,\n", + " -0.029090436,\n", + " 0.017523576,\n", + " -0.03561854,\n", + " -0.015012307,\n", + " -0.043565813,\n", + " -0.0042169513,\n", + " -0.015257499,\n", + " -0.0013578214,\n", + " -0.020777592,\n", + " -0.0026453973,\n", + " -0.037206873,\n", + " 0.01621471,\n", + " -0.033481725,\n", + " 0.023214078,\n", + " 0.07240724,\n", + " 0.038964514,\n", + " -0.10446012,\n", + " -0.024342356,\n", + " -0.012709968,\n", + " 0.06211316,\n", + " 0.028951973,\n", + " -0.017876118,\n", + " 0.033162788,\n", + " -0.01688093,\n", + " -0.0017007018,\n", + " -0.06386243,\n", + " -0.06569357,\n", + " -0.019704562,\n", + " 0.0058997083,\n", + " 0.02682609,\n", + " 0.0019023331,\n", + " 0.0017976766,\n", + " 0.047627747,\n", + " -0.0009570554,\n", + " 0.003511069,\n", + " -0.028590811,\n", + " 0.008931729,\n", + " 0.0056299744,\n", + " -0.045468964,\n", + " -0.015844844,\n", + " 0.024054134,\n", + " -0.027469898,\n", + " 0.022173349,\n", + " 0.08148612,\n", + " -0.019955546,\n", + " 0.071963444,\n", + " 0.017910395,\n", + " -0.03124338,\n", + " -0.025000984,\n", + " 0.0054683266,\n", + " -0.043931495,\n", + " 0.0008234161,\n", + " -0.088591345,\n", + " 0.000479956,\n", + " -0.060126673,\n", + " -0.03357947,\n", + " -0.056410566,\n", + " -0.032589775,\n", + " -0.061390713,\n", + " 0.023527699,\n", + " 0.06446886,\n", + " -0.007932508,\n", + " -0.0031587793,\n", + " -0.038047824,\n", + " -0.016549844,\n", + " -0.020477492,\n", + " -0.075683415,\n", + " -0.012110268,\n", + " -0.04891436,\n", + " 0.026568849,\n", + " -0.029075945,\n", + " 0.088291675,\n", + " 0.05912708,\n", + " 0.015805336,\n", + " -0.049823914,\n", + " 0.024532974,\n", + " 0.045406923,\n", + " 0.0095926905,\n", + " -0.020348761,\n", + " -0.027956523,\n", + " 0.030030653,\n", + " 0.04987238,\n", + " -0.032793604,\n", + " -0.011533045,\n", + " -0.023860402,\n", + " 0.062345207,\n", + " -0.019582005,\n", + " -0.031335227,\n", + " 0.04970386,\n", + " -0.023734426,\n", + " -0.021209128,\n", + " 0.026652478,\n", + " 0.030278446,\n", + " 0.0072057345,\n", + " 0.015214752,\n", + " 0.030629016,\n", + " -0.038683932,\n", + " -0.019320292,\n", + " -0.002425624,\n", + " 0.027636893,\n", + " 0.061737496,\n", + " 0.024350017,\n", + " 0.056657396,\n", + " -0.026632559,\n", + " 0.031648163,\n", + " 0.017482013,\n", + " -0.0008389236,\n", + " 0.059907097,\n", + " -0.02123141,\n", + " -0.0025512732,\n", + " 0.0016537616,\n", + " 0.013569981,\n", + " 0.0036193815,\n", + " 0.0020932176,\n", + " -0.024130942,\n", + " 0.0026975519,\n", + " -0.0041695293,\n", + " 0.04122382,\n", + " -0.011495905,\n", + " -0.008079376,\n", + " -0.0057473094,\n", + " 0.039514784,\n", + " -0.04971112,\n", + " 0.038069297,\n", + " -0.026460811,\n", + " -0.09403351,\n", + " 0.0051518404,\n", + " 0.041077457,\n", + " -0.02429841,\n", + " 0.030635186,\n", + " 0.023150187,\n", + " -0.015075604,\n", + " 0.018495653,\n", + " -0.015820375,\n", + " 0.06806306,\n", + " -0.041917916,\n", + " -0.0020552087,\n", + " -0.03989304,\n", + " 0.0018853423,\n", + " -0.03138397,\n", + " 0.043138567,\n", + " 0.03781449,\n", + " -0.022061005,\n", + " 0.05022614,\n", + " -0.024115918,\n", + " 0.060577173,\n", + " -0.015132834,\n", + " -0.036388364,\n", + " -0.008102943,\n", + " 0.04300946,\n", + " -0.06315613,\n", + " 0.0036877454,\n", + " 0.01845251,\n", + " -0.01958063,\n", + " 0.020833353,\n", + " 0.04074978,\n", + " -0.016953025,\n", + " -0.022429537,\n", + " 0.014793756,\n", + " -0.040389486,\n", + " -0.013773572,\n", + " -0.009218371,\n", + " 0.005113001,\n", + " -0.05334978,\n", + " -0.017054679,\n", + " 0.0047935587,\n", + " 0.008970996,\n", + " 0.090954326,\n", + " 0.040972985,\n", + " -0.012958875,\n", + " -0.048973564,\n", + " 0.036145844,\n", + " -0.014689881,\n", + " -0.019061541,\n", + " 0.011643549,\n", + " 0.0013238543,\n", + " 0.010562913,\n", + " 0.05699919,\n", + " -0.033291608,\n", + " -0.038737576,\n", + " 0.033350945,\n", + " 0.004073598,\n", + " -0.0031493988,\n", + " 0.064587645,\n", + " 0.0049619107,\n", + " -0.033150792,\n", + " 0.009891267,\n", + " -0.05739713,\n", + " 0.037735194,\n", + " 0.062099792,\n", + " -0.0033623695,\n", + " 0.07860333,\n", + " 0.009854467,\n", + " -0.06447139,\n", + " 0.031053409,\n", + " -0.058900006,\n", + " -0.05029678,\n", + " -0.027897462,\n", + " 0.056934282,\n", + " -0.023755403,\n", + " -0.02699664,\n", + " 0.0148529,\n", + " -0.01666892,\n", + " -0.0018880437,\n", + " -0.0457452,\n", + " 0.053869832,\n", + " -0.017661236,\n", + " 0.041393574,\n", + " -0.029723926,\n", + " 0.035513297,\n", + " -0.033740062,\n", + " 0.017888788,\n", + " 0.025985245,\n", + " 0.04350399,\n", + " -0.005232885,\n", + " -0.0005693812,\n", + " -0.0033883732,\n", + " -0.037065566,\n", + " -0.02527872,\n", + " -0.0013861161,\n", + " -0.009989347,\n", + " 0.017875295,\n", + " -0.024106601,\n", + " 0.019750569,\n", + " -0.010035022,\n", + " 0.023742517,\n", + " -0.011065428,\n", + " 0.033420607,\n", + " 0.010958177,\n", + " -0.01141841,\n", + " 0.004739421,\n", + " 0.09271151,\n", + " 0.058798864,\n", + " 0.052398294,\n", + " 0.024582228,\n", + " 0.031933635,\n", + " -0.005510293,\n", + " -0.055356447,\n", + " 0.04904649,\n", + " -0.016862152,\n", + " -0.057705753,\n", + " 0.024840772,\n", + " -0.00048015165,\n", + " -0.10546246,\n", + " 0.033585515,\n", + " 0.054793786,\n", + " -0.0070182765,\n", + " -0.031317633,\n", + " 0.034208145,\n", + " 0.015181784,\n", + " -0.062814064,\n", + " -0.019155085,\n", + " -0.03985083,\n", + " -0.0043001687,\n", + " -0.027612321,\n", + " 0.025576307,\n", + " 0.020972272,\n", + " -0.015960751,\n", + " -0.03785616,\n", + " -0.03439213,\n", + " -0.035648625,\n", + " 0.03173273,\n", + " 0.030685507,\n", + " -0.018922847,\n", + " 0.067803204,\n", + " -0.0148015395,\n", + " 0.044523258,\n", + " 0.0061558536,\n", + " 0.0054381737,\n", + " 0.016035475,\n", + " -0.07147066,\n", + " -0.04419202,\n", + " 0.07741728,\n", + " -0.045105446,\n", + " 0.03828778,\n", + " 0.0073140706,\n", + " -0.05118925,\n", + " 0.061084356,\n", + " 0.05001082,\n", + " -0.041532677,\n", + " -0.0016793367,\n", + " 0.019244568,\n", + " 0.005559429,\n", + " 0.017637422,\n", + " -0.012980126,\n", + " 0.013700538,\n", + " 0.04216373,\n", + " 0.026694974,\n", + " 0.043757316,\n", + " 0.012165836,\n", + " 0.023159562,\n", + " -0.056082647,\n", + " -0.030905947,\n", + " 0.016382935,\n", + " -0.0074324473,\n", + " -0.016718535,\n", + " -0.0066933725,\n", + " 0.07567363,\n", + " -0.009259794,\n", + " 0.019372217,\n", + " 0.014743861,\n", + " 0.020617943,\n", + " 0.057029292,\n", + " 0.0050983094,\n", + " -0.032250557,\n", + " 0.013374774,\n", + " 0.047974505,\n", + " -0.049952496,\n", + " 0.012993495,\n", + " 0.02056461,\n", + " -0.0057155536,\n", + " 0.021704368,\n", + " -0.0010753982,\n", + " 0.03720598,\n", + " -0.062292766,\n", + " -0.03158331,\n", + " 0.04137522,\n", + " 0.013299325,\n", + " 0.0049977377,\n", + " 0.04511127,\n", + " -0.013574835,\n", + " -0.033320617,\n", + " 0.0153828645,\n", + " 0.05682976,\n", + " -0.015472821,\n", + " -0.0013420929,\n", + " -0.054665994,\n", + " -0.0047995877,\n", + " 0.056595206,\n", + " -0.03133152,\n", + " 0.08055057,\n", + " -0.019866763,\n", + " -0.008866304,\n", + " 0.10177134,\n", + " -0.035269864,\n", + " -0.027235541,\n", + " 0.04055463,\n", + " -0.0308909,\n", + " 0.08752392,\n", + " 0.036332566,\n", + " 0.022787439,\n", + " -0.036100462,\n", + " -0.08477476,\n", + " -0.059534717,\n", + " 0.03207563,\n", + " 0.013661438,\n", + " 0.013927431,\n", + " 0.025811398,\n", + " -0.025891041,\n", + " 0.030257259,\n", + " -0.020082533,\n", + " -0.010865357,\n", + " -0.07682985,\n", + " -0.08710289,\n", + " 0.026793221,\n", + " -0.03599497,\n", + " 0.036737897,\n", + " 0.038387842,\n", + " -0.067557946,\n", + " -0.018947005,\n", + " -0.020812513,\n", + " 0.04308112,\n", + " 0.0135874795,\n", + " -0.026089147,\n", + " -0.00018917858,\n", + " -0.033624545,\n", + " 0.038969826,\n", + " 0.027176073,\n", + " 0.034541093,\n", + " -0.0001338307,\n", + " 0.009559905,\n", + " ],\n", + " },\n", + " {\n", + " \"_id\": \"54635\",\n", + " \"content\": \"Employee number 54635, name John Smith, department Engineering, location San Francisco, salary 150000\",\n", + " \"embedding\": [\n", + " 0.02751842,\n", + " -0.035257466,\n", + " -0.017211914,\n", + " -0.00021509113,\n", + " 0.065513395,\n", + " 0.015236125,\n", + " 0.046573777,\n", + " -0.027342448,\n", + " 0.013279674,\n", + " 0.015880402,\n", + " -0.0026871182,\n", + " -0.020755854,\n", + " -0.028976398,\n", + " -0.025017332,\n", + " -0.02915205,\n", + " 0.03748723,\n", + " 0.026784075,\n", + " -0.008561052,\n", + " 0.0061514685,\n", + " -0.08216181,\n", + " -0.012679269,\n", + " -0.019104697,\n", + " -0.035561316,\n", + " -0.013733142,\n", + " -0.002272582,\n", + " -0.014719888,\n", + " 0.030248245,\n", + " -0.08619838,\n", + " -0.03771919,\n", + " 0.018865846,\n", + " -0.063968174,\n", + " 0.03219376,\n", + " -0.035308257,\n", + " 0.036639687,\n", + " -0.04739701,\n", + " 0.01655839,\n", + " -0.025951466,\n", + " 0.019777248,\n", + " 0.008441114,\n", + " 0.0397848,\n", + " -0.007323799,\n", + " -0.010856907,\n", + " -0.015435451,\n", + " -0.024571002,\n", + " 0.0608382,\n", + " -0.001076124,\n", + " -0.01160508,\n", + " 0.027767012,\n", + " 0.020741891,\n", + " -0.08319567,\n", + " 0.04286476,\n", + " -0.0065871845,\n", + " 0.030671211,\n", + " -0.008211031,\n", + " -0.05312356,\n", + " -0.07651591,\n", + " -0.013340908,\n", + " -0.012418467,\n", + " -0.02554261,\n", + " -0.027668754,\n", + " -0.028723458,\n", + " 0.0072301184,\n", + " 0.018877236,\n", + " 0.03554761,\n", + " -0.004688246,\n", + " -0.07433135,\n", + " -0.0035417427,\n", + " -0.006659041,\n", + " 0.04192288,\n", + " -0.0207361,\n", + " -0.006254261,\n", + " -0.024812873,\n", + " 0.059861075,\n", + " -0.03134214,\n", + " -0.07463872,\n", + " -0.11254215,\n", + " -0.007414231,\n", + " 0.01804921,\n", + " 0.057197362,\n", + " 0.02665551,\n", + " 0.0064427084,\n", + " -0.013575005,\n", + " -0.029392047,\n", + " -0.012261425,\n", + " -0.030408913,\n", + " 0.074111775,\n", + " 0.016163299,\n", + " -0.017348083,\n", + " -0.027919967,\n", + " 0.040365145,\n", + " 0.016613623,\n", + " 0.0008838358,\n", + " 0.035404228,\n", + " -0.07160502,\n", + " -0.014951479,\n", + " 0.06784549,\n", + " 0.0066313925,\n", + " -0.052722607,\n", + " -0.029260378,\n", + " -0.053105693,\n", + " -0.0045598387,\n", + " -0.05004554,\n", + " -0.052556243,\n", + " -0.0067943437,\n", + " 0.019090641,\n", + " 0.007432553,\n", + " -0.020073954,\n", + " -0.0042186803,\n", + " -0.005367988,\n", + " 0.018064711,\n", + " -0.073992364,\n", + " -0.017997328,\n", + " -0.032181244,\n", + " -0.04996697,\n", + " 0.06846196,\n", + " -0.03522803,\n", + " -0.035346393,\n", + " 0.07071394,\n", + " 0.041346475,\n", + " 0.007324973,\n", + " 0.08921032,\n", + " 0.068063006,\n", + " 0.020346623,\n", + " 0.040123172,\n", + " -0.010046104,\n", + " 0.025201118,\n", + " -0.003961309,\n", + " 0.023122495,\n", + " 0.09587856,\n", + " 0.05031979,\n", + " -0.01057047,\n", + " -0.04394514,\n", + " 0.034751166,\n", + " -0.014335325,\n", + " 0.03341888,\n", + " 0.05706479,\n", + " 0.05054945,\n", + " 0.004166189,\n", + " 0.061515614,\n", + " -0.022616953,\n", + " -0.0050968137,\n", + " 0.0010603444,\n", + " -0.030782396,\n", + " 0.008184928,\n", + " -0.011474374,\n", + " 0.003339862,\n", + " -0.0067458292,\n", + " -0.010549199,\n", + " 0.027625475,\n", + " -0.0020265754,\n", + " 0.006763103,\n", + " 0.009542199,\n", + " -0.03164191,\n", + " 0.027494777,\n", + " 0.015781684,\n", + " 0.010094312,\n", + " -0.026690045,\n", + " 0.027364649,\n", + " 0.020415021,\n", + " -0.0379163,\n", + " 0.032620024,\n", + " 0.040363166,\n", + " -0.005355615,\n", + " 0.02923704,\n", + " 0.0073294668,\n", + " 0.008268878,\n", + " 0.046909377,\n", + " -0.035831597,\n", + " -0.037963904,\n", + " -0.05067842,\n", + " -0.023855058,\n", + " 0.031068098,\n", + " -0.060321517,\n", + " -0.017361106,\n", + " -0.03714339,\n", + " -0.052008033,\n", + " -0.017402591,\n", + " -0.0000853109,\n", + " -0.01522777,\n", + " 0.004505938,\n", + " -0.035380103,\n", + " -0.04122089,\n", + " 0.017592149,\n", + " 0.017477088,\n", + " 0.009680622,\n", + " 0.0601484,\n", + " 0.053315826,\n", + " -0.04279214,\n", + " 0.009589118,\n", + " -0.010029888,\n", + " 0.020045798,\n", + " 0.024653148,\n", + " -0.023524566,\n", + " 0.011961308,\n", + " 0.0017022899,\n", + " 0.029609565,\n", + " 0.028629072,\n", + " 0.021015882,\n", + " 0.00012135336,\n", + " -0.04946617,\n", + " -0.034740772,\n", + " 0.031152897,\n", + " 0.027573282,\n", + " -0.017018853,\n", + " 0.020141952,\n", + " -0.020575022,\n", + " 0.08574167,\n", + " -0.025361745,\n", + " 0.0000718993,\n", + " 0.07202345,\n", + " -0.035066936,\n", + " 0.042211156,\n", + " -0.02737654,\n", + " -0.007903302,\n", + " 0.055386215,\n", + " 0.03386666,\n", + " 0.007098444,\n", + " -0.0011916764,\n", + " -0.0077267145,\n", + " -0.039679147,\n", + " 0.0109159555,\n", + " 0.013889261,\n", + " -0.020267498,\n", + " 0.057652816,\n", + " -0.01675666,\n", + " -0.01046991,\n", + " 0.0063280216,\n", + " 0.036489647,\n", + " 0.014317979,\n", + " -0.04359035,\n", + " -0.0038247926,\n", + " 0.03433474,\n", + " 0.0046200114,\n", + " -0.028734986,\n", + " 0.033694655,\n", + " -0.0072179954,\n", + " 0.0065697636,\n", + " 0.0035546091,\n", + " -0.018106835,\n", + " 0.0008928709,\n", + " -0.04377693,\n", + " 0.015936524,\n", + " 0.026221775,\n", + " 0.004182328,\n", + " -0.055179127,\n", + " 0.010751439,\n", + " -0.038998943,\n", + " 0.039809167,\n", + " -0.015138335,\n", + " 0.009765969,\n", + " -0.0081632165,\n", + " -0.05567452,\n", + " 0.05554104,\n", + " 0.026053185,\n", + " -0.05740401,\n", + " 0.03465235,\n", + " -0.076469,\n", + " 0.0015592162,\n", + " 0.009639975,\n", + " -0.030025609,\n", + " 0.05954854,\n", + " 0.021440376,\n", + " -0.006658576,\n", + " 0.02273896,\n", + " -0.031426214,\n", + " 0.040050857,\n", + " -0.021161372,\n", + " -0.068565525,\n", + " -0.028184833,\n", + " 0.068864435,\n", + " -0.005223995,\n", + " -0.006345874,\n", + " 0.07794489,\n", + " 0.046531476,\n", + " 0.035680976,\n", + " -0.010769412,\n", + " -0.006249256,\n", + " 0.041365553,\n", + " 0.003833638,\n", + " -0.058614638,\n", + " -0.0052710325,\n", + " 0.07343842,\n", + " 0.03782047,\n", + " -0.046215393,\n", + " -0.029175224,\n", + " 0.011108449,\n", + " -0.0022866763,\n", + " 0.010857836,\n", + " 0.008042948,\n", + " -0.07578336,\n", + " -0.09506901,\n", + " 0.0028703813,\n", + " -0.017622843,\n", + " -0.05017095,\n", + " -0.06601734,\n", + " 0.016744547,\n", + " -0.030435143,\n", + " 0.010448069,\n", + " 0.023559375,\n", + " 0.003017711,\n", + " -0.010440744,\n", + " -0.051503733,\n", + " -0.031850483,\n", + " -0.06224817,\n", + " 0.03302146,\n", + " 0.0022398247,\n", + " 0.012647616,\n", + " -0.05779213,\n", + " -0.012409115,\n", + " -0.01943723,\n", + " 0.027941398,\n", + " -0.022145638,\n", + " -0.015692553,\n", + " -0.0011641445,\n", + " 0.026432425,\n", + " 0.05613625,\n", + " 0.010688817,\n", + " -0.014724717,\n", + " -0.029040305,\n", + " 0.07541772,\n", + " -0.0038578296,\n", + " 0.0063860323,\n", + " 0.028974347,\n", + " -0.048377227,\n", + " -0.0020083082,\n", + " 0.061093163,\n", + " -0.0015345091,\n", + " 0.04327932,\n", + " -0.006280553,\n", + " -0.004461047,\n", + " -0.004969216,\n", + " 0.079298794,\n", + " 0.005280641,\n", + " 0.075993665,\n", + " -0.00903695,\n", + " 0.01402909,\n", + " -0.088527754,\n", + " 0.007002133,\n", + " -0.06112628,\n", + " -0.025775367,\n", + " 0.035340235,\n", + " 0.011317101,\n", + " -0.058157604,\n", + " -0.057730775,\n", + " -0.030742848,\n", + " -0.024909437,\n", + " -0.01292577,\n", + " 0.025219142,\n", + " 0.07330923,\n", + " 0.04195776,\n", + " 0.0330579,\n", + " 0.027340477,\n", + " -0.018308474,\n", + " -0.040544774,\n", + " -0.043364618,\n", + " -0.017788624,\n", + " 0.024081899,\n", + " -0.02448898,\n", + " 0.025725441,\n", + " -0.014032703,\n", + " -0.03716917,\n", + " 0.030908864,\n", + " 0.0046337834,\n", + " -0.017839137,\n", + " 0.025155617,\n", + " -0.005961568,\n", + " 0.0017926248,\n", + " 0.010721402,\n", + " 0.008076512,\n", + " 0.000014950954,\n", + " 0.03687499,\n", + " -0.080296755,\n", + " -0.0022581385,\n", + " 0.0135227805,\n", + " -0.007616169,\n", + " -0.059810784,\n", + " -0.06190626,\n", + " -0.022344204,\n", + " 0.04095455,\n", + " 0.024678344,\n", + " 0.040884405,\n", + " 0.01146623,\n", + " -0.010222091,\n", + " 0.023510607,\n", + " 0.013003448,\n", + " -0.024498258,\n", + " 0.01566375,\n", + " 0.03966229,\n", + " -0.013284801,\n", + " 0.05625292,\n", + " 0.0035774496,\n", + " -0.041765593,\n", + " 0.075709105,\n", + " 0.0025806301,\n", + " 0.002827293,\n", + " -0.0127510615,\n", + " 0.0076297605,\n", + " -0.018482147,\n", + " 0.0195352,\n", + " -0.008572333,\n", + " -0.023895975,\n", + " -0.022642754,\n", + " -0.021384051,\n", + " -0.025655594,\n", + " 0.011634965,\n", + " -0.040602997,\n", + " -0.0025013296,\n", + " -0.019177016,\n", + " 0.025949784,\n", + " -0.044972513,\n", + " 0.036257338,\n", + " 0.07511653,\n", + " 0.036459416,\n", + " -0.115887314,\n", + " -0.03673168,\n", + " -0.027124275,\n", + " 0.06939686,\n", + " 0.022735972,\n", + " -0.017979583,\n", + " 0.03082303,\n", + " -0.017964998,\n", + " -0.002043333,\n", + " -0.045927435,\n", + " -0.083149225,\n", + " -0.023609241,\n", + " 0.008159602,\n", + " -0.0014957677,\n", + " -0.019364858,\n", + " 0.017326526,\n", + " 0.03703413,\n", + " 0.021754017,\n", + " -0.024310483,\n", + " 0.012974437,\n", + " 0.0025437805,\n", + " 0.009190147,\n", + " -0.03622636,\n", + " -0.025097648,\n", + " 0.03175117,\n", + " -0.060564324,\n", + " 0.025262883,\n", + " 0.045786444,\n", + " -0.03756287,\n", + " 0.077972464,\n", + " 0.014882087,\n", + " -0.035983026,\n", + " -0.03335668,\n", + " 0.012810578,\n", + " -0.05117928,\n", + " 0.016779415,\n", + " -0.09439797,\n", + " -0.0063598235,\n", + " -0.046981793,\n", + " -0.0028302062,\n", + " -0.058332726,\n", + " -0.025126418,\n", + " -0.0774988,\n", + " -0.005797502,\n", + " 0.051930707,\n", + " -0.031145284,\n", + " -0.017120061,\n", + " -0.019712316,\n", + " -0.03858973,\n", + " -0.0066188793,\n", + " -0.07773236,\n", + " 0.014307085,\n", + " -0.027230764,\n", + " 0.0331902,\n", + " -0.057089612,\n", + " 0.057789687,\n", + " 0.06540567,\n", + " 0.022184646,\n", + " -0.048069406,\n", + " 0.015343113,\n", + " 0.0558476,\n", + " 0.0001679844,\n", + " -0.019582808,\n", + " -0.026129218,\n", + " 0.030448413,\n", + " 0.03634036,\n", + " -0.041653648,\n", + " -0.03448554,\n", + " -0.023397086,\n", + " 0.076667525,\n", + " -0.009382471,\n", + " -0.03721751,\n", + " 0.023369618,\n", + " -0.014296145,\n", + " -0.008192296,\n", + " -0.009530903,\n", + " 0.03565617,\n", + " 0.017519575,\n", + " 0.02974625,\n", + " 0.003261011,\n", + " -0.048980772,\n", + " -0.011459121,\n", + " -0.020589355,\n", + " 0.00025388523,\n", + " 0.05537085,\n", + " 0.03211041,\n", + " 0.020657161,\n", + " -0.008744432,\n", + " 0.022239113,\n", + " 0.03172477,\n", + " -0.012103961,\n", + " 0.06935857,\n", + " -0.030093772,\n", + " -0.022945607,\n", + " 0.006408147,\n", + " 0.020852357,\n", + " 0.028491085,\n", + " -0.0023250037,\n", + " -0.002611426,\n", + " -0.017636396,\n", + " -0.02044602,\n", + " 0.03541466,\n", + " -0.016902495,\n", + " -0.006867505,\n", + " -0.00012285702,\n", + " 0.017117904,\n", + " -0.020677648,\n", + " 0.0557191,\n", + " -0.015488911,\n", + " -0.10235103,\n", + " -0.0028210408,\n", + " 0.010193204,\n", + " -0.032251876,\n", + " 0.01060267,\n", + " 0.03557713,\n", + " -0.0063216602,\n", + " 0.009259219,\n", + " 0.0051827505,\n", + " 0.038854543,\n", + " -0.031460393,\n", + " -0.0076761693,\n", + " -0.026699234,\n", + " 0.018988753,\n", + " -0.0137761375,\n", + " 0.046094075,\n", + " 0.016433887,\n", + " -0.003973164,\n", + " 0.063081056,\n", + " -0.029332547,\n", + " 0.054982897,\n", + " -0.03574009,\n", + " -0.053488664,\n", + " -0.0065793497,\n", + " 0.04935732,\n", + " -0.07006432,\n", + " 0.02812001,\n", + " 0.00647268,\n", + " -0.0075788135,\n", + " 0.022446249,\n", + " 0.0481543,\n", + " -0.028088065,\n", + " -0.00019163998,\n", + " 0.0115054725,\n", + " -0.045824103,\n", + " -0.0041767946,\n", + " 0.0011554541,\n", + " -0.010604986,\n", + " -0.00820998,\n", + " -0.015158567,\n", + " 0.006710291,\n", + " 0.027485032,\n", + " 0.0827062,\n", + " 0.035160348,\n", + " -0.0056700693,\n", + " -0.06100241,\n", + " 0.03775862,\n", + " -0.055310618,\n", + " 0.0020003193,\n", + " 0.003878855,\n", + " 0.0039324365,\n", + " 0.021707052,\n", + " 0.056594085,\n", + " -0.023516221,\n", + " -0.051027056,\n", + " 0.02914387,\n", + " -0.01747557,\n", + " -0.00048578077,\n", + " 0.06910575,\n", + " -0.02813352,\n", + " -0.0067434846,\n", + " 0.02015622,\n", + " -0.030215016,\n", + " 0.013908208,\n", + " 0.0559234,\n", + " 0.007264178,\n", + " 0.07277442,\n", + " -0.0056195944,\n", + " -0.07750021,\n", + " 0.050576977,\n", + " -0.06140354,\n", + " -0.045618854,\n", + " -0.020566126,\n", + " 0.039101325,\n", + " -0.025846323,\n", + " -0.014014278,\n", + " -0.010953099,\n", + " 0.0053575314,\n", + " 0.01853153,\n", + " -0.059806224,\n", + " 0.079701826,\n", + " -0.026566066,\n", + " 0.040181253,\n", + " -0.02266395,\n", + " 0.0054217833,\n", + " -0.027931219,\n", + " 0.04334095,\n", + " 0.03031099,\n", + " 0.02989241,\n", + " -0.00061276584,\n", + " -0.013604992,\n", + " 0.008013184,\n", + " -0.03547994,\n", + " -0.01926322,\n", + " -0.007489133,\n", + " -0.0029699102,\n", + " -0.010580029,\n", + " -0.018646544,\n", + " 0.0047476776,\n", + " -0.020718446,\n", + " 0.009074871,\n", + " -0.0027520477,\n", + " 0.0387986,\n", + " -0.023973802,\n", + " -0.01189377,\n", + " 0.013701782,\n", + " 0.068496615,\n", + " 0.04820877,\n", + " 0.019212667,\n", + " 0.045648925,\n", + " 0.0318747,\n", + " -0.028331727,\n", + " -0.025103705,\n", + " 0.0328582,\n", + " -0.03484345,\n", + " -0.05530036,\n", + " 0.011778919,\n", + " -0.005664444,\n", + " -0.113750234,\n", + " 0.018433394,\n", + " 0.03918017,\n", + " -0.012234621,\n", + " -0.016486265,\n", + " 0.017421383,\n", + " 0.024043733,\n", + " -0.04742088,\n", + " 0.020483378,\n", + " -0.038147032,\n", + " -0.009845963,\n", + " -0.006499819,\n", + " 0.028929604,\n", + " 0.025346762,\n", + " -0.012089239,\n", + " -0.032945115,\n", + " -0.04614911,\n", + " -0.028733844,\n", + " 0.03818017,\n", + " 0.04198492,\n", + " -0.024049556,\n", + " 0.06125142,\n", + " -0.008327446,\n", + " 0.030352222,\n", + " 0.015361837,\n", + " -0.013292321,\n", + " 0.006475574,\n", + " -0.072518654,\n", + " -0.036767293,\n", + " 0.0740501,\n", + " -0.06637531,\n", + " 0.043207835,\n", + " 0.034058686,\n", + " -0.03576254,\n", + " 0.047720406,\n", + " 0.037699528,\n", + " -0.023285469,\n", + " 0.025489798,\n", + " 0.002287648,\n", + " -0.008411476,\n", + " 0.02260013,\n", + " -0.020512147,\n", + " 0.008027023,\n", + " 0.029532177,\n", + " 0.0059477957,\n", + " 0.04624887,\n", + " 0.021156397,\n", + " 0.036551874,\n", + " -0.041027997,\n", + " -0.049307615,\n", + " 0.02526815,\n", + " -0.02010938,\n", + " -0.019960264,\n", + " -0.014263981,\n", + " 0.079093084,\n", + " 0.010921492,\n", + " 0.018967591,\n", + " -0.008221532,\n", + " 0.0058250814,\n", + " 0.07463721,\n", + " -0.03572568,\n", + " -0.013496767,\n", + " -0.00042068915,\n", + " 0.019645795,\n", + " -0.049485173,\n", + " 0.03608238,\n", + " -0.01177695,\n", + " 0.0020465946,\n", + " 0.012326075,\n", + " -0.0023621495,\n", + " 0.049434356,\n", + " -0.078708716,\n", + " -0.048812617,\n", + " 0.015036083,\n", + " 0.020805584,\n", + " -0.0033854137,\n", + " 0.0066305967,\n", + " 0.015715208,\n", + " -0.027279327,\n", + " 0.03890442,\n", + " 0.028212277,\n", + " -0.025578374,\n", + " -0.0042159823,\n", + " -0.04713265,\n", + " 0.0012227457,\n", + " 0.07078375,\n", + " -0.028477665,\n", + " 0.05951706,\n", + " -0.0190399,\n", + " -0.026970295,\n", + " 0.06499598,\n", + " -0.034548096,\n", + " -0.036340587,\n", + " 0.0422616,\n", + " -0.03698566,\n", + " 0.0678964,\n", + " 0.012707417,\n", + " 0.03466419,\n", + " -0.015625846,\n", + " -0.08137007,\n", + " -0.045645062,\n", + " 0.023715043,\n", + " 0.0023143874,\n", + " 0.008170114,\n", + " 0.041747324,\n", + " -0.022417393,\n", + " 0.011471595,\n", + " -0.020469397,\n", + " -0.02913878,\n", + " -0.07025473,\n", + " -0.07867984,\n", + " 0.025465682,\n", + " -0.026013091,\n", + " -0.011840964,\n", + " 0.047041006,\n", + " -0.058210913,\n", + " -0.027502269,\n", + " -0.01028805,\n", + " 0.029465359,\n", + " 0.03936156,\n", + " -0.028816642,\n", + " 0.022757342,\n", + " -0.002236254,\n", + " 0.035480563,\n", + " 0.0058484883,\n", + " 0.026348954,\n", + " -0.016547782,\n", + " 0.018939447,\n", + " ],\n", + " },\n", + " {\n", + " \"_id\": \"54637\",\n", + " \"content\": \"Employee number 54637, name John Johnson, department HR, location Miami, salary 110000\",\n", + " \"embedding\": [\n", + " 0.0151990615,\n", + " -0.018385835,\n", + " -0.031483263,\n", + " 0.0082740635,\n", + " 0.047831737,\n", + " 0.022178285,\n", + " 0.042604085,\n", + " -0.015300213,\n", + " 0.0052842684,\n", + " 0.04275969,\n", + " -0.031947587,\n", + " -0.055677623,\n", + " -0.01569269,\n", + " -0.016129037,\n", + " -0.044204526,\n", + " 0.0340167,\n", + " 0.0040199882,\n", + " -0.014162755,\n", + " 0.011139275,\n", + " -0.018563714,\n", + " -0.03279649,\n", + " 0.0037455678,\n", + " -0.01916476,\n", + " -0.02534246,\n", + " 0.020670477,\n", + " -0.010130891,\n", + " 0.028611206,\n", + " -0.084460564,\n", + " -0.04089965,\n", + " -0.006191601,\n", + " -0.059610564,\n", + " 0.07042831,\n", + " -0.0019582002,\n", + " 0.040124465,\n", + " -0.010672403,\n", + " 0.00023288652,\n", + " -0.036172427,\n", + " 0.019273408,\n", + " 0.022685157,\n", + " 0.019930484,\n", + " -0.0069136596,\n", + " -0.018724103,\n", + " -0.027178712,\n", + " 0.0102139255,\n", + " 0.060994297,\n", + " 0.01205306,\n", + " 0.008931071,\n", + " 0.030500712,\n", + " 0.039762385,\n", + " -0.0844163,\n", + " 0.03557818,\n", + " 0.016239291,\n", + " 0.011505173,\n", + " 0.016626962,\n", + " -0.051115632,\n", + " -0.089058846,\n", + " 0.006736814,\n", + " 0.0016996651,\n", + " -0.018498152,\n", + " -0.02900407,\n", + " -0.037330467,\n", + " -0.0019586603,\n", + " -0.006318982,\n", + " 0.011514259,\n", + " -0.020778127,\n", + " -0.060733095,\n", + " -0.03416104,\n", + " 0.003209011,\n", + " 0.037856832,\n", + " -0.02291265,\n", + " -0.02566606,\n", + " -0.04075286,\n", + " 0.06387488,\n", + " -0.013900549,\n", + " -0.06662302,\n", + " -0.11717324,\n", + " -0.021233523,\n", + " 0.03737273,\n", + " 0.062059958,\n", + " 0.018934567,\n", + " -0.0021977667,\n", + " -0.017087216,\n", + " -0.03001248,\n", + " -0.029826604,\n", + " -0.053601734,\n", + " 0.07904818,\n", + " -0.0050950386,\n", + " -0.027237581,\n", + " -0.009588286,\n", + " 0.02798285,\n", + " -0.015427634,\n", + " 0.010472741,\n", + " -0.019344417,\n", + " -0.0884872,\n", + " -0.03772547,\n", + " 0.07433684,\n", + " -0.005178444,\n", + " -0.04721746,\n", + " 0.016155189,\n", + " -0.020898396,\n", + " 0.027348634,\n", + " -0.03220877,\n", + " -0.039294083,\n", + " 0.025916431,\n", + " 0.03894846,\n", + " 0.0050957613,\n", + " 0.011876476,\n", + " 0.009665685,\n", + " -0.0010955081,\n", + " -0.0035323082,\n", + " -0.056610696,\n", + " 0.0042955126,\n", + " 0.004623993,\n", + " -0.047537014,\n", + " 0.065262586,\n", + " -0.045530386,\n", + " -0.043586448,\n", + " 0.08124031,\n", + " 0.0058494746,\n", + " 0.017003875,\n", + " 0.06947752,\n", + " 0.045389757,\n", + " -0.00809288,\n", + " 0.003066964,\n", + " 0.024357231,\n", + " 0.05353458,\n", + " 0.0041651297,\n", + " 0.015048914,\n", + " 0.09423512,\n", + " 0.059014294,\n", + " -0.01673688,\n", + " -0.025130406,\n", + " 0.030101426,\n", + " 0.00313877,\n", + " 0.05056692,\n", + " 0.05799128,\n", + " 0.06417359,\n", + " 0.0070831957,\n", + " 0.061689373,\n", + " -0.025019836,\n", + " -0.013782963,\n", + " -0.006486025,\n", + " -0.04184629,\n", + " 0.0021818338,\n", + " -0.0029972838,\n", + " -0.0069409898,\n", + " -0.008351021,\n", + " -0.009658322,\n", + " 0.048463274,\n", + " -0.029926352,\n", + " 0.024303105,\n", + " -0.017629249,\n", + " -0.014122519,\n", + " 0.006829436,\n", + " 0.015102068,\n", + " 0.02918675,\n", + " -0.047867116,\n", + " 0.017428437,\n", + " 0.004246343,\n", + " -0.02182751,\n", + " 0.05868468,\n", + " -0.0012855188,\n", + " -0.005099442,\n", + " 0.001516126,\n", + " -0.002746483,\n", + " -0.0103094075,\n", + " 0.009653553,\n", + " -0.03586081,\n", + " -0.042287398,\n", + " -0.060810238,\n", + " 0.007971088,\n", + " 0.030602243,\n", + " -0.07896841,\n", + " -0.019366264,\n", + " -0.059197318,\n", + " -0.040017575,\n", + " -0.0060959007,\n", + " 0.0067164223,\n", + " -0.031493124,\n", + " -0.024010602,\n", + " -0.037667226,\n", + " -0.03403944,\n", + " -0.00097576715,\n", + " 0.027220456,\n", + " -0.0021284383,\n", + " 0.06373505,\n", + " 0.041661903,\n", + " -0.025651291,\n", + " -0.0026189024,\n", + " -0.026962018,\n", + " 0.04662318,\n", + " 0.029713636,\n", + " -0.0072639524,\n", + " -0.008331813,\n", + " -0.013575179,\n", + " 0.030916931,\n", + " 0.015517671,\n", + " 0.028786736,\n", + " 0.0042063724,\n", + " -0.029553477,\n", + " -0.016450562,\n", + " 0.060844745,\n", + " -0.0013221892,\n", + " -0.0055684242,\n", + " 0.04769308,\n", + " -0.038562633,\n", + " 0.04191216,\n", + " -0.07439696,\n", + " -0.013617095,\n", + " 0.04565873,\n", + " 0.0075634466,\n", + " 0.04673023,\n", + " -0.041626494,\n", + " -0.03232615,\n", + " 0.04359808,\n", + " 0.024681205,\n", + " 0.024057476,\n", + " 0.007089288,\n", + " -0.00020997692,\n", + " -0.05840243,\n", + " 0.0011099685,\n", + " 0.012605227,\n", + " -0.020300457,\n", + " 0.072397396,\n", + " 0.0029569077,\n", + " -0.012561521,\n", + " -0.0031120302,\n", + " 0.04246921,\n", + " 0.019347874,\n", + " -0.016595539,\n", + " 0.008932043,\n", + " 0.038021155,\n", + " 0.022360448,\n", + " -0.041870937,\n", + " 0.03759141,\n", + " 0.017054925,\n", + " 0.023967758,\n", + " 0.017783063,\n", + " -0.02351047,\n", + " 0.023144009,\n", + " -0.054543506,\n", + " 0.012925695,\n", + " 0.08040064,\n", + " 0.007308367,\n", + " -0.08529201,\n", + " -0.0056034215,\n", + " -0.028788855,\n", + " 0.00034720462,\n", + " 0.014641983,\n", + " 0.024667779,\n", + " -0.028710028,\n", + " -0.041735,\n", + " 0.08198758,\n", + " 0.041555718,\n", + " -0.04926944,\n", + " 0.052032072,\n", + " -0.086632214,\n", + " -0.00159897,\n", + " -0.009663495,\n", + " -0.0071806083,\n", + " 0.051270913,\n", + " 0.024380185,\n", + " -0.01310986,\n", + " 0.021249343,\n", + " -0.032247756,\n", + " 0.040103268,\n", + " -0.0109099755,\n", + " -0.07212998,\n", + " -0.018791035,\n", + " 0.047924884,\n", + " -0.01295749,\n", + " -0.00022769881,\n", + " 0.08965714,\n", + " 0.056537516,\n", + " 0.039999932,\n", + " 0.011153844,\n", + " -0.0015653945,\n", + " 0.052498676,\n", + " 0.0031664725,\n", + " -0.04293477,\n", + " -0.018758398,\n", + " 0.045290086,\n", + " 0.025194753,\n", + " -0.036377974,\n", + " -0.013312391,\n", + " -0.004944805,\n", + " -0.0059067444,\n", + " -0.019272402,\n", + " 0.011710215,\n", + " -0.06544868,\n", + " -0.08821586,\n", + " 0.017618323,\n", + " -0.025412118,\n", + " -0.053164277,\n", + " -0.046637923,\n", + " 0.004189994,\n", + " -0.029162928,\n", + " 0.016743293,\n", + " 0.017788872,\n", + " 0.02451719,\n", + " 0.011813669,\n", + " -0.014297119,\n", + " 0.0047462014,\n", + " -0.0604839,\n", + " 0.030824589,\n", + " -0.011509641,\n", + " 0.030518167,\n", + " -0.06083328,\n", + " -0.008108362,\n", + " -0.010405061,\n", + " 0.0279155,\n", + " -0.030137705,\n", + " -0.037425663,\n", + " -0.003826426,\n", + " 0.045524806,\n", + " 0.04506571,\n", + " -0.0003876464,\n", + " -0.025874265,\n", + " -0.035840876,\n", + " 0.04633308,\n", + " 0.015148351,\n", + " 0.02118069,\n", + " 0.022964032,\n", + " -0.015708314,\n", + " -0.012418845,\n", + " 0.017429173,\n", + " -0.011633802,\n", + " 0.026676752,\n", + " 0.016578717,\n", + " 0.00702841,\n", + " -0.030563941,\n", + " 0.028610306,\n", + " 0.014839663,\n", + " 0.079686195,\n", + " -0.004785117,\n", + " 0.027001834,\n", + " -0.06591138,\n", + " 0.008991921,\n", + " -0.08665218,\n", + " -0.024576634,\n", + " 0.042076416,\n", + " -0.002764758,\n", + " -0.037591983,\n", + " -0.06974853,\n", + " -0.008148083,\n", + " -0.0010839726,\n", + " -0.03883453,\n", + " 0.029932331,\n", + " 0.07715753,\n", + " 0.0428311,\n", + " 0.00048389743,\n", + " 0.02941479,\n", + " -0.023215424,\n", + " -0.021311667,\n", + " -0.029051634,\n", + " -0.0078097307,\n", + " 0.05971781,\n", + " -0.0003501407,\n", + " 0.020407172,\n", + " -0.020588633,\n", + " -0.045638587,\n", + " 0.05452016,\n", + " -0.033031806,\n", + " 0.0018599117,\n", + " 0.021753361,\n", + " -0.017417207,\n", + " 0.011331878,\n", + " 0.025535421,\n", + " -0.012881257,\n", + " 0.0020049305,\n", + " 0.027690342,\n", + " -0.05566046,\n", + " -0.009303709,\n", + " 0.02051795,\n", + " -0.0012120871,\n", + " -0.05989722,\n", + " -0.05193341,\n", + " -0.03752882,\n", + " 0.0151110515,\n", + " 0.04022004,\n", + " 0.059206907,\n", + " -0.0004753494,\n", + " -0.015862446,\n", + " 0.008765484,\n", + " 0.002500967,\n", + " -0.024079999,\n", + " 0.037471678,\n", + " 0.04361219,\n", + " -0.009226066,\n", + " 0.06009437,\n", + " -0.0072968435,\n", + " -0.03503233,\n", + " 0.12823524,\n", + " -0.019953987,\n", + " 0.022029717,\n", + " -0.03506259,\n", + " -0.0069630756,\n", + " -0.010650351,\n", + " 0.00024113746,\n", + " -0.005909056,\n", + " -0.026001915,\n", + " -0.05297878,\n", + " -0.019525815,\n", + " -0.011212167,\n", + " -0.0011330652,\n", + " -0.029903706,\n", + " -0.013018626,\n", + " -0.04529402,\n", + " 0.022067638,\n", + " -0.042428583,\n", + " 0.011411191,\n", + " 0.07941165,\n", + " 0.046710193,\n", + " -0.09081757,\n", + " -0.020232175,\n", + " -0.021946874,\n", + " 0.04843305,\n", + " 0.025839098,\n", + " -0.029347481,\n", + " 0.052311007,\n", + " -0.019753845,\n", + " 0.015101981,\n", + " -0.02324361,\n", + " -0.06853173,\n", + " -0.013895659,\n", + " -0.027288755,\n", + " 0.014830132,\n", + " -0.019731691,\n", + " -0.012770851,\n", + " 0.047408056,\n", + " 0.010517912,\n", + " -0.018772654,\n", + " 0.008655169,\n", + " 0.004405761,\n", + " 0.028954867,\n", + " -0.043041132,\n", + " -0.005176918,\n", + " -0.01609051,\n", + " -0.028849607,\n", + " 0.05003634,\n", + " 0.029869856,\n", + " -0.050169658,\n", + " 0.08384437,\n", + " 0.01797906,\n", + " -0.01214695,\n", + " -0.027093818,\n", + " 0.025474763,\n", + " -0.035368394,\n", + " -0.0013650756,\n", + " -0.10130171,\n", + " -0.019761328,\n", + " -0.058286637,\n", + " -0.031827793,\n", + " -0.018027933,\n", + " -0.020658895,\n", + " -0.06964426,\n", + " 0.015475856,\n", + " 0.06776502,\n", + " -0.014362135,\n", + " -0.002891477,\n", + " -0.024214484,\n", + " -0.019469662,\n", + " -0.038628835,\n", + " -0.05970077,\n", + " 0.013868974,\n", + " -0.041725248,\n", + " 0.018331435,\n", + " -0.027626732,\n", + " 0.047414143,\n", + " 0.048645236,\n", + " 0.015711607,\n", + " -0.019731916,\n", + " 0.02018027,\n", + " 0.037067145,\n", + " 0.015580378,\n", + " -0.02074777,\n", + " -0.037656497,\n", + " 0.0315254,\n", + " 0.027829327,\n", + " -0.04953328,\n", + " -0.008974909,\n", + " -0.036621064,\n", + " 0.08268924,\n", + " -0.000099023084,\n", + " -0.010808362,\n", + " 0.017444545,\n", + " -0.036837447,\n", + " -0.033786334,\n", + " 0.024554044,\n", + " 0.038338773,\n", + " 0.0015833074,\n", + " -0.016416071,\n", + " 0.026449595,\n", + " -0.032863718,\n", + " 0.020646136,\n", + " -0.005101266,\n", + " 0.003269877,\n", + " 0.043449853,\n", + " 0.026952377,\n", + " 0.0030762502,\n", + " -0.043083463,\n", + " 0.011685804,\n", + " 0.02702897,\n", + " -0.019786451,\n", + " 0.09016056,\n", + " -0.019395946,\n", + " 0.00547562,\n", + " 0.00805198,\n", + " 0.027644351,\n", + " 0.013978436,\n", + " -0.01701422,\n", + " 0.0027872338,\n", + " 0.0068438747,\n", + " -0.034153488,\n", + " 0.041465588,\n", + " 0.0065093203,\n", + " -0.010097714,\n", + " -0.008133783,\n", + " 0.033143714,\n", + " -0.017333148,\n", + " 0.043355733,\n", + " -0.00871402,\n", + " -0.08563055,\n", + " -0.0106432075,\n", + " 0.035572823,\n", + " -0.023785846,\n", + " -0.004012492,\n", + " 0.042794853,\n", + " -0.031091385,\n", + " 0.0576266,\n", + " 0.0070195203,\n", + " 0.0765921,\n", + " -0.043606408,\n", + " -0.023182996,\n", + " -0.04500981,\n", + " 0.0025196855,\n", + " -0.015288511,\n", + " 0.031438597,\n", + " 0.051824644,\n", + " -0.042258043,\n", + " 0.03338895,\n", + " -0.025437905,\n", + " 0.031160489,\n", + " -0.0072392435,\n", + " -0.031922713,\n", + " 0.029755816,\n", + " 0.012957701,\n", + " -0.10024418,\n", + " 0.032848,\n", + " -0.007295161,\n", + " -0.0035617317,\n", + " 0.028405763,\n", + " 0.061833233,\n", + " -0.04108825,\n", + " -0.020171262,\n", + " 0.020549063,\n", + " -0.026362132,\n", + " -0.023915224,\n", + " 0.007996089,\n", + " -0.030391349,\n", + " -0.0028575344,\n", + " -0.018893851,\n", + " 0.02560692,\n", + " 0.008163355,\n", + " 0.087368175,\n", + " 0.008817629,\n", + " -0.00850316,\n", + " -0.059040304,\n", + " 0.041495502,\n", + " -0.040280342,\n", + " 0.0068111503,\n", + " 0.0021893613,\n", + " 0.0022273697,\n", + " 0.005985552,\n", + " 0.0505196,\n", + " -0.04750377,\n", + " -0.03359202,\n", + " 0.020417644,\n", + " 0.0044759694,\n", + " -0.0035043096,\n", + " 0.048957326,\n", + " -0.011384678,\n", + " 0.008479551,\n", + " 0.025835814,\n", + " 0.0014910818,\n", + " 0.039479405,\n", + " 0.057871632,\n", + " 0.016251555,\n", + " 0.06249111,\n", + " -0.019609375,\n", + " -0.04390419,\n", + " 0.017925067,\n", + " -0.055957958,\n", + " -0.019112395,\n", + " -0.04754885,\n", + " 0.026070505,\n", + " -0.019006608,\n", + " -0.030362992,\n", + " -0.0067993933,\n", + " -0.006561339,\n", + " 0.026431026,\n", + " -0.03405452,\n", + " 0.057274282,\n", + " -0.026786203,\n", + " 0.063958324,\n", + " -0.04453278,\n", + " 0.027547128,\n", + " -0.03851104,\n", + " 0.01796476,\n", + " 0.031259652,\n", + " 0.04863174,\n", + " -0.024669012,\n", + " -0.034748323,\n", + " -0.018997308,\n", + " -0.05671984,\n", + " -0.021414421,\n", + " 0.020377612,\n", + " -0.030505922,\n", + " -0.0050755935,\n", + " -0.033292443,\n", + " 0.002657024,\n", + " -0.038488954,\n", + " 0.009190322,\n", + " -0.049295817,\n", + " 0.041600667,\n", + " 0.0049329526,\n", + " 0.0032398892,\n", + " -0.027688216,\n", + " 0.060459703,\n", + " 0.03917895,\n", + " 0.05121542,\n", + " 0.011903356,\n", + " 0.0094349375,\n", + " -0.01939282,\n", + " -0.040036276,\n", + " 0.019289287,\n", + " 0.007947662,\n", + " -0.05668005,\n", + " 0.01639571,\n", + " 0.013513371,\n", + " -0.10730804,\n", + " 0.011741851,\n", + " 0.052281383,\n", + " 0.0060147797,\n", + " -0.0016338177,\n", + " 0.016279288,\n", + " 0.012750764,\n", + " -0.04507693,\n", + " -0.00013838317,\n", + " -0.020932881,\n", + " 0.0028839025,\n", + " -0.0015208381,\n", + " 0.0013958535,\n", + " 0.023533827,\n", + " -0.010494416,\n", + " -0.061766583,\n", + " -0.02134274,\n", + " -0.022852637,\n", + " 0.054971635,\n", + " 0.026075963,\n", + " -0.021454506,\n", + " 0.02648363,\n", + " -0.030089613,\n", + " 0.028793827,\n", + " 0.004582815,\n", + " -0.021465372,\n", + " -0.017831849,\n", + " -0.06147862,\n", + " -0.05767438,\n", + " 0.09083923,\n", + " -0.05611259,\n", + " 0.017855838,\n", + " 0.009335081,\n", + " -0.045156814,\n", + " 0.06599881,\n", + " 0.018773748,\n", + " -0.05827166,\n", + " 0.016615061,\n", + " -0.006753534,\n", + " 0.01607565,\n", + " 0.027570006,\n", + " -0.020239603,\n", + " -0.03056045,\n", + " 0.046354145,\n", + " 0.03691325,\n", + " 0.031975202,\n", + " 0.022407934,\n", + " 0.025474546,\n", + " -0.045023665,\n", + " -0.040520623,\n", + " 0.0005759944,\n", + " -0.03525117,\n", + " -0.009240973,\n", + " -0.011385803,\n", + " 0.08493358,\n", + " 0.018094597,\n", + " 0.035135623,\n", + " 0.016993279,\n", + " 0.01320788,\n", + " 0.07891705,\n", + " -0.020045092,\n", + " -0.033938758,\n", + " -0.0056153582,\n", + " 0.03615839,\n", + " -0.031113567,\n", + " 0.057805743,\n", + " -0.001218427,\n", + " -0.021837134,\n", + " 0.029644802,\n", + " -0.0033356778,\n", + " 0.040365815,\n", + " -0.018033424,\n", + " -0.02393337,\n", + " 0.05093956,\n", + " 0.030515084,\n", + " -0.037502967,\n", + " 0.009851229,\n", + " 0.0072234045,\n", + " -0.048626166,\n", + " 0.037203453,\n", + " 0.05917087,\n", + " -0.03617051,\n", + " 0.00980295,\n", + " -0.038709767,\n", + " 0.02074771,\n", + " 0.03775127,\n", + " -0.03192831,\n", + " 0.05048824,\n", + " -0.001492862,\n", + " -0.021132791,\n", + " 0.08444902,\n", + " -0.03443452,\n", + " -0.040238414,\n", + " 0.048974395,\n", + " -0.027845262,\n", + " 0.07948588,\n", + " 0.0208495,\n", + " 0.026636329,\n", + " -0.02487519,\n", + " -0.029094454,\n", + " -0.05993427,\n", + " 0.03780091,\n", + " -0.012249043,\n", + " 0.0028786385,\n", + " 0.043765884,\n", + " -0.028861433,\n", + " 0.009502931,\n", + " -0.030093342,\n", + " -0.026304517,\n", + " -0.05845765,\n", + " -0.0392811,\n", + " 0.029583348,\n", + " -0.01641044,\n", + " -0.005475869,\n", + " 0.04321726,\n", + " -0.06391988,\n", + " -0.025680711,\n", + " -0.0030519557,\n", + " 0.030743454,\n", + " -0.0007805563,\n", + " -0.04256318,\n", + " -0.005030573,\n", + " -0.0041211224,\n", + " 0.021191673,\n", + " 0.04913769,\n", + " 0.027602818,\n", + " -0.014373903,\n", + " 0.03175012,\n", + " ],\n", + " },\n", + " {\n", + " \"_id\": \"54638\",\n", + " \"content\": \"Employee number 54638, name Jane Johnson, department Operations, location Seattle, salary 140000\",\n", + " \"embedding\": [\n", + " 0.026050478,\n", + " -0.048555247,\n", + " -0.008828629,\n", + " 0.019901045,\n", + " 0.034666445,\n", + " 0.010111517,\n", + " 0.06873206,\n", + " -0.030538522,\n", + " 0.009940293,\n", + " 0.0339663,\n", + " -0.03364418,\n", + " -0.03269781,\n", + " -0.029471608,\n", + " -0.0027008695,\n", + " -0.02049043,\n", + " -0.0029114042,\n", + " 0.010917951,\n", + " -0.028362973,\n", + " -0.0075063263,\n", + " -0.06207452,\n", + " -0.021798516,\n", + " 0.0039276425,\n", + " 0.00055708154,\n", + " -0.02095584,\n", + " 0.01713003,\n", + " -0.01722649,\n", + " 0.008000153,\n", + " -0.08242634,\n", + " -0.028559122,\n", + " 0.018734612,\n", + " -0.066623494,\n", + " 0.034287848,\n", + " -0.03751501,\n", + " 0.03244232,\n", + " -0.03420307,\n", + " 0.023143344,\n", + " -0.03240853,\n", + " -0.023571912,\n", + " -0.00683183,\n", + " 0.03096674,\n", + " -0.014259085,\n", + " -0.011342896,\n", + " -0.026998486,\n", + " 0.014940984,\n", + " 0.050578054,\n", + " -0.028980328,\n", + " 0.023303777,\n", + " -0.004296986,\n", + " 0.0293136,\n", + " -0.061096653,\n", + " 0.03287692,\n", + " 0.015354411,\n", + " 0.021088544,\n", + " -0.0015228266,\n", + " 0.0029424573,\n", + " -0.082046166,\n", + " 0.0040660985,\n", + " 0.0074269758,\n", + " -0.010958359,\n", + " -0.035012763,\n", + " -0.018889561,\n", + " -0.0059276978,\n", + " 0.002083359,\n", + " 0.036374025,\n", + " -0.004819571,\n", + " -0.04908644,\n", + " -0.017455256,\n", + " -0.009606802,\n", + " 0.06495625,\n", + " 0.0032073925,\n", + " -0.052301414,\n", + " -0.041856,\n", + " 0.05783131,\n", + " -0.017050996,\n", + " -0.061963696,\n", + " -0.06982274,\n", + " -0.03540072,\n", + " 0.03466075,\n", + " 0.055206526,\n", + " 0.011832436,\n", + " 0.0021956502,\n", + " -0.007684086,\n", + " -0.020636348,\n", + " -0.018782893,\n", + " -0.047240626,\n", + " 0.047610387,\n", + " -0.0076809353,\n", + " -0.0100567825,\n", + " -0.025776941,\n", + " 0.04181693,\n", + " -0.0046912674,\n", + " -0.012204287,\n", + " 0.014001371,\n", + " -0.063043125,\n", + " -0.036930084,\n", + " 0.059859123,\n", + " -0.010818763,\n", + " -0.045730297,\n", + " -0.0075380807,\n", + " -0.019068131,\n", + " 0.019801125,\n", + " -0.049903613,\n", + " -0.05432268,\n", + " -0.0071445843,\n", + " 0.0057908674,\n", + " -0.002666185,\n", + " -0.0075345123,\n", + " -0.019908248,\n", + " -0.00643323,\n", + " -0.00071061886,\n", + " -0.0838654,\n", + " -0.008257412,\n", + " -0.038826358,\n", + " -0.0513455,\n", + " 0.072962046,\n", + " -0.020993974,\n", + " -0.049816236,\n", + " 0.070966154,\n", + " 0.00079034764,\n", + " 0.015203719,\n", + " 0.05684234,\n", + " 0.03761177,\n", + " 0.016545977,\n", + " 0.020625291,\n", + " 0.0210726,\n", + " 0.02898525,\n", + " -0.0033419074,\n", + " 0.0032714924,\n", + " 0.11322761,\n", + " 0.054507524,\n", + " -0.04121643,\n", + " -0.039163385,\n", + " 0.040570177,\n", + " -0.0072572003,\n", + " 0.038773507,\n", + " 0.0637184,\n", + " 0.069037475,\n", + " -0.028668208,\n", + " 0.07188595,\n", + " -0.02913201,\n", + " 0.0063090385,\n", + " 0.007426714,\n", + " -0.03193378,\n", + " -0.006524865,\n", + " -0.0127412435,\n", + " 0.015498198,\n", + " -0.020522788,\n", + " -0.011274028,\n", + " 0.028620226,\n", + " 0.005763184,\n", + " 0.022521585,\n", + " 0.0072611654,\n", + " -0.048059847,\n", + " -0.01234606,\n", + " 0.04490082,\n", + " 0.03871421,\n", + " -0.044477567,\n", + " 0.027942147,\n", + " -0.0066905613,\n", + " -0.014890972,\n", + " 0.048969653,\n", + " 0.019693347,\n", + " -0.021390632,\n", + " 0.033437464,\n", + " -0.015723728,\n", + " -0.011988548,\n", + " 0.0554776,\n", + " -0.03956305,\n", + " -0.07680316,\n", + " -0.031703744,\n", + " -0.01612956,\n", + " 0.04235391,\n", + " -0.070821315,\n", + " 0.011926204,\n", + " -0.053500686,\n", + " -0.050267965,\n", + " 0.00074491126,\n", + " -0.008569316,\n", + " -0.027631104,\n", + " 0.0061910404,\n", + " -0.033930015,\n", + " -0.007472883,\n", + " 0.0026893707,\n", + " 0.0384716,\n", + " 0.018170964,\n", + " 0.050014913,\n", + " 0.05871329,\n", + " -0.044597052,\n", + " -0.014061176,\n", + " -0.003683495,\n", + " 0.025531424,\n", + " 0.017034912,\n", + " -0.027470706,\n", + " -0.006491179,\n", + " -0.009489945,\n", + " 0.017133964,\n", + " -0.015572295,\n", + " 0.0139110815,\n", + " -0.02003761,\n", + " -0.037344135,\n", + " -0.030428719,\n", + " 0.06549211,\n", + " 0.010248525,\n", + " 0.0028726796,\n", + " 0.033761874,\n", + " -0.015765324,\n", + " 0.046935823,\n", + " -0.04185924,\n", + " -0.006468727,\n", + " 0.050379142,\n", + " 0.007927611,\n", + " 0.03851822,\n", + " 0.008543064,\n", + " 0.0078075267,\n", + " 0.039120134,\n", + " 0.03586357,\n", + " 0.04638511,\n", + " -0.010768516,\n", + " -0.0067371903,\n", + " -0.025532754,\n", + " -0.0051189596,\n", + " 0.02152079,\n", + " -0.04576048,\n", + " 0.04305608,\n", + " -0.026554907,\n", + " -0.018880805,\n", + " -0.01480849,\n", + " 0.026723232,\n", + " 0.001033573,\n", + " -0.037126005,\n", + " -0.0020229125,\n", + " 0.040790092,\n", + " 0.0018653974,\n", + " -0.049913183,\n", + " 0.04781728,\n", + " 0.027713154,\n", + " 0.010776397,\n", + " 0.01318502,\n", + " -0.026499385,\n", + " -0.009594083,\n", + " -0.03862901,\n", + " 0.016218811,\n", + " 0.06014656,\n", + " 0.025734013,\n", + " -0.0347474,\n", + " 0.0116609605,\n", + " -0.038452834,\n", + " 0.0052867737,\n", + " 0.010370307,\n", + " 0.027156852,\n", + " -0.0015308461,\n", + " -0.06445644,\n", + " 0.050907042,\n", + " 0.022530565,\n", + " -0.048766818,\n", + " 0.05991084,\n", + " -0.09708642,\n", + " -0.009711094,\n", + " 0.015859898,\n", + " -0.029318294,\n", + " 0.050506905,\n", + " 0.00735409,\n", + " -0.0138486065,\n", + " 0.024359517,\n", + " -0.034031246,\n", + " 0.024766166,\n", + " -0.01821558,\n", + " -0.06686822,\n", + " -0.0487108,\n", + " 0.052032128,\n", + " 0.016451957,\n", + " -0.03551824,\n", + " 0.08024126,\n", + " 0.051618367,\n", + " 0.013979535,\n", + " 0.010763741,\n", + " -0.023814084,\n", + " 0.04610131,\n", + " 0.008492314,\n", + " -0.06802373,\n", + " -0.015461633,\n", + " 0.055361446,\n", + " 0.0074120234,\n", + " -0.04642445,\n", + " -0.028934892,\n", + " 0.01169551,\n", + " -0.030712495,\n", + " 0.0039937347,\n", + " 0.008349997,\n", + " -0.06625405,\n", + " -0.08341982,\n", + " 0.013278654,\n", + " -0.026365193,\n", + " -0.039572082,\n", + " -0.064723566,\n", + " 0.0052512945,\n", + " -0.02465726,\n", + " 0.025906282,\n", + " 0.005685407,\n", + " 0.006141651,\n", + " 0.0044314065,\n", + " -0.039461534,\n", + " -0.032410044,\n", + " -0.074979536,\n", + " 0.05221336,\n", + " -0.010037091,\n", + " -0.00015792609,\n", + " -0.070082806,\n", + " -0.0063522724,\n", + " -0.036909256,\n", + " 0.024703242,\n", + " -0.025880957,\n", + " -0.03181115,\n", + " 0.025542444,\n", + " 0.020821305,\n", + " 0.05083042,\n", + " 0.00440165,\n", + " -0.017547268,\n", + " -0.038332768,\n", + " 0.06295742,\n", + " -0.003380332,\n", + " 0.0017819487,\n", + " 0.031406853,\n", + " -0.03936085,\n", + " -0.014774891,\n", + " 0.05555366,\n", + " 0.0013044683,\n", + " 0.071219094,\n", + " 0.0027098448,\n", + " 0.0090771,\n", + " 0.004294718,\n", + " 0.04097738,\n", + " 0.0038274624,\n", + " 0.09351304,\n", + " 0.01993581,\n", + " 0.03123765,\n", + " -0.062362995,\n", + " 0.017761108,\n", + " -0.06349266,\n", + " -0.023149393,\n", + " 0.041712813,\n", + " 0.023032729,\n", + " -0.046279017,\n", + " -0.059766676,\n", + " 0.013576986,\n", + " -0.035526287,\n", + " 0.0009959425,\n", + " 0.042815145,\n", + " 0.052038774,\n", + " 0.047260206,\n", + " -0.015755137,\n", + " 0.011777429,\n", + " -0.013718928,\n", + " -0.018773504,\n", + " -0.041940242,\n", + " -0.016540648,\n", + " 0.056323376,\n", + " -0.009581614,\n", + " 0.012827593,\n", + " 0.002802622,\n", + " -0.047416028,\n", + " 0.06029572,\n", + " -0.026624044,\n", + " -0.0059878556,\n", + " -0.01112658,\n", + " 0.0064357584,\n", + " 0.015744798,\n", + " 0.0027346082,\n", + " -0.013077302,\n", + " 0.027371943,\n", + " 0.028480768,\n", + " -0.029083466,\n", + " -0.016170066,\n", + " 0.018732633,\n", + " -0.02920547,\n", + " -0.049596816,\n", + " -0.050539367,\n", + " -0.023739604,\n", + " -0.016439682,\n", + " 0.023610277,\n", + " 0.03793149,\n", + " -0.01936672,\n", + " 0.00054942124,\n", + " 0.03477947,\n", + " 0.022074739,\n", + " -0.008824361,\n", + " -0.016267285,\n", + " 0.032433596,\n", + " -0.026371641,\n", + " 0.06440936,\n", + " 0.016472073,\n", + " -0.012704358,\n", + " 0.12420736,\n", + " -0.0101508675,\n", + " 0.023653913,\n", + " -0.036456037,\n", + " -0.009319963,\n", + " -0.02745349,\n", + " 0.011565427,\n", + " -0.016726809,\n", + " -0.00910894,\n", + " -0.027309556,\n", + " -0.020953115,\n", + " -0.0004489086,\n", + " -0.017622823,\n", + " -0.026881404,\n", + " -0.016441276,\n", + " -0.028333068,\n", + " 0.051373687,\n", + " -0.06849969,\n", + " 0.048643496,\n", + " 0.06129681,\n", + " 0.043112013,\n", + " -0.10503493,\n", + " -0.032169662,\n", + " -0.016303875,\n", + " 0.038900618,\n", + " 0.017744469,\n", + " -0.0078635495,\n", + " 0.011909131,\n", + " -0.02633716,\n", + " 0.012839195,\n", + " -0.034210175,\n", + " -0.049735658,\n", + " -0.012025739,\n", + " 0.024162453,\n", + " -0.017275587,\n", + " -0.027206033,\n", + " -0.01216894,\n", + " 0.056151856,\n", + " -0.002266644,\n", + " -0.017719636,\n", + " -0.024023125,\n", + " 0.012112513,\n", + " 0.035618242,\n", + " -0.066973604,\n", + " -0.038296815,\n", + " 0.046060294,\n", + " -0.03857978,\n", + " 0.04528379,\n", + " 0.043774627,\n", + " -0.025222767,\n", + " 0.08498407,\n", + " 0.0023034313,\n", + " -0.007176461,\n", + " -0.018639492,\n", + " 0.023903845,\n", + " -0.040975634,\n", + " 0.014675711,\n", + " -0.08696412,\n", + " -0.0012359321,\n", + " -0.060993966,\n", + " -0.024204629,\n", + " -0.045965314,\n", + " -0.05470206,\n", + " -0.0545379,\n", + " 0.031496808,\n", + " 0.059156094,\n", + " 0.009160291,\n", + " 0.0072219935,\n", + " -0.006173258,\n", + " -0.03295994,\n", + " -0.01801206,\n", + " -0.057803974,\n", + " 0.041660473,\n", + " -0.039624795,\n", + " 0.028510751,\n", + " -0.030607404,\n", + " 0.06521628,\n", + " 0.06455515,\n", + " 0.013236343,\n", + " -0.013641919,\n", + " 0.03251663,\n", + " 0.019429607,\n", + " 0.020611761,\n", + " -0.047394972,\n", + " -0.033903588,\n", + " 0.030801337,\n", + " 0.03389709,\n", + " -0.033200398,\n", + " -0.00968848,\n", + " -0.042483523,\n", + " 0.062307518,\n", + " -0.024104252,\n", + " -0.038019832,\n", + " 0.037520684,\n", + " -0.02434741,\n", + " -0.015609218,\n", + " 0.0065647936,\n", + " 0.043396086,\n", + " 0.014070153,\n", + " 0.0043344726,\n", + " 0.024882345,\n", + " -0.022135641,\n", + " -0.01799605,\n", + " 0.00038329684,\n", + " -0.01741619,\n", + " 0.044463806,\n", + " 0.031136844,\n", + " 0.032308206,\n", + " 0.0007304428,\n", + " 0.035526954,\n", + " 0.028219154,\n", + " -0.021445524,\n", + " 0.059003815,\n", + " -0.0415958,\n", + " -0.0043805623,\n", + " -0.0006041634,\n", + " 0.028271,\n", + " 0.038045794,\n", + " -0.007856862,\n", + " -0.0030909725,\n", + " -0.032664094,\n", + " -0.017286232,\n", + " 0.024400914,\n", + " -0.013834741,\n", + " -0.02652701,\n", + " 0.029634649,\n", + " 0.01700266,\n", + " -0.03734089,\n", + " 0.038840823,\n", + " -0.016492758,\n", + " -0.093306154,\n", + " -0.0044792993,\n", + " 0.04936495,\n", + " -0.016763058,\n", + " 0.024115685,\n", + " 0.05415202,\n", + " -0.04315434,\n", + " 0.015969714,\n", + " -0.021037051,\n", + " 0.05564539,\n", + " -0.055493116,\n", + " -0.02337645,\n", + " -0.025281547,\n", + " -0.0065010595,\n", + " 0.008250707,\n", + " 0.055807795,\n", + " 0.02414763,\n", + " -0.022564175,\n", + " 0.02834781,\n", + " -0.040628407,\n", + " 0.026874747,\n", + " -0.01892121,\n", + " -0.035771616,\n", + " 0.0018971186,\n", + " 0.030991131,\n", + " -0.058407318,\n", + " 0.022544177,\n", + " -0.0099294195,\n", + " -0.003015739,\n", + " 0.009533158,\n", + " 0.06220805,\n", + " -0.0018919198,\n", + " -0.015758067,\n", + " 0.0045811604,\n", + " -0.022871247,\n", + " -0.026954936,\n", + " -0.007922866,\n", + " -0.015751228,\n", + " -0.024009718,\n", + " -0.019846817,\n", + " 0.00086579495,\n", + " 0.007355841,\n", + " 0.07742838,\n", + " 0.039498612,\n", + " 0.0018927547,\n", + " -0.049126364,\n", + " 0.035092838,\n", + " -0.038997784,\n", + " 0.014563989,\n", + " 0.0014772905,\n", + " -0.0058927247,\n", + " 0.0004669789,\n", + " 0.054502,\n", + " -0.0101958765,\n", + " -0.06462403,\n", + " 0.030232383,\n", + " 0.015468133,\n", + " 0.008747526,\n", + " 0.058180943,\n", + " 0.009895715,\n", + " -0.023807824,\n", + " 0.016150286,\n", + " -0.033176575,\n", + " 0.03896909,\n", + " 0.07366637,\n", + " -0.02589846,\n", + " 0.081121355,\n", + " 0.012857258,\n", + " -0.0320698,\n", + " 0.026557323,\n", + " -0.05475815,\n", + " -0.045223676,\n", + " -0.006914698,\n", + " 0.059804097,\n", + " -0.030856598,\n", + " -0.02270003,\n", + " -0.006721817,\n", + " 0.007834129,\n", + " 0.014207969,\n", + " -0.04459566,\n", + " 0.060735647,\n", + " -0.004343931,\n", + " 0.06916978,\n", + " -0.025479676,\n", + " 0.001981753,\n", + " -0.049986716,\n", + " 0.019160662,\n", + " 0.019025618,\n", + " 0.03463173,\n", + " -0.0051061907,\n", + " -0.039971903,\n", + " -0.009554134,\n", + " -0.051973134,\n", + " -0.02322696,\n", + " 0.000666707,\n", + " 0.0076026963,\n", + " 0.0070748134,\n", + " -0.027127214,\n", + " 0.0021439027,\n", + " -0.0380424,\n", + " 0.019361308,\n", + " -0.021825459,\n", + " 0.024104213,\n", + " -0.001751936,\n", + " 0.020918885,\n", + " -0.0037656801,\n", + " 0.053490546,\n", + " 0.072466716,\n", + " 0.06307481,\n", + " 0.025220444,\n", + " 0.030272197,\n", + " -0.011731547,\n", + " -0.056140322,\n", + " 0.048621643,\n", + " -0.022496052,\n", + " -0.06380631,\n", + " 0.038866386,\n", + " -0.010590717,\n", + " -0.108824804,\n", + " 0.006726385,\n", + " 0.050433647,\n", + " 0.0057739234,\n", + " -0.01420325,\n", + " 0.023737092,\n", + " 0.042579204,\n", + " -0.053798538,\n", + " -0.018823216,\n", + " -0.03827396,\n", + " -0.015979653,\n", + " -0.0069397204,\n", + " 0.02125115,\n", + " 0.0033473414,\n", + " -0.013927182,\n", + " -0.05654852,\n", + " -0.019954465,\n", + " -0.035381112,\n", + " 0.056015182,\n", + " 0.0065556956,\n", + " -0.023087364,\n", + " 0.043700524,\n", + " 0.0027661035,\n", + " 0.025146691,\n", + " 0.012687644,\n", + " -0.027370248,\n", + " -0.0010651633,\n", + " -0.06115836,\n", + " -0.029139342,\n", + " 0.08521571,\n", + " -0.042291123,\n", + " 0.030378494,\n", + " 0.014432462,\n", + " -0.046826813,\n", + " 0.050151218,\n", + " 0.045153998,\n", + " -0.04796362,\n", + " 0.022682115,\n", + " 0.011545504,\n", + " 0.020556057,\n", + " -0.0042003356,\n", + " -0.021686615,\n", + " -0.0012217021,\n", + " 0.019806935,\n", + " 0.047820672,\n", + " 0.05978573,\n", + " 0.01758219,\n", + " 0.02204856,\n", + " -0.039568268,\n", + " -0.021229789,\n", + " 0.014548975,\n", + " -0.034249913,\n", + " -0.023128428,\n", + " -0.011201689,\n", + " 0.07169892,\n", + " 0.026005901,\n", + " 0.028781159,\n", + " 0.0130280135,\n", + " 0.03135926,\n", + " 0.0843804,\n", + " -0.0062047434,\n", + " -0.061045166,\n", + " 0.010564766,\n", + " 0.018106297,\n", + " -0.043597803,\n", + " 0.02699747,\n", + " -0.0120446915,\n", + " -0.024967365,\n", + " 0.034383804,\n", + " 0.0030797508,\n", + " 0.03732648,\n", + " -0.06742948,\n", + " -0.041975114,\n", + " 0.036880396,\n", + " 0.025295557,\n", + " 0.016465476,\n", + " 0.028427439,\n", + " -0.004287951,\n", + " -0.008966516,\n", + " 0.03698348,\n", + " 0.05051995,\n", + " -0.024159456,\n", + " 0.0052558105,\n", + " -0.04339689,\n", + " 0.009192153,\n", + " 0.045353524,\n", + " -0.049608096,\n", + " 0.06556983,\n", + " 0.0049719103,\n", + " 0.000014385518,\n", + " 0.06860882,\n", + " -0.03174607,\n", + " -0.0073257447,\n", + " 0.0044105197,\n", + " -0.03662372,\n", + " 0.09250486,\n", + " 0.04256795,\n", + " 0.031364053,\n", + " 0.0016935823,\n", + " -0.0680488,\n", + " -0.07860276,\n", + " 0.024094777,\n", + " 0.016591892,\n", + " 0.022528214,\n", + " 0.029432567,\n", + " -0.02577635,\n", + " 0.013138877,\n", + " -0.021803275,\n", + " -0.030736644,\n", + " -0.064376354,\n", + " -0.0935471,\n", + " 0.018339334,\n", + " -0.040749416,\n", + " 0.036033116,\n", + " 0.040105127,\n", + " -0.059686333,\n", + " -0.028928738,\n", + " -0.0044766283,\n", + " 0.030114502,\n", + " 0.018945087,\n", + " -0.029741868,\n", + " 0.0052247434,\n", + " -0.013826671,\n", + " 0.06707814,\n", + " 0.0406519,\n", + " 0.03318739,\n", + " 0.010909002,\n", + " 0.029758368,\n", + " ],\n", + " },\n", + " ]\n", + ")" ] }, { @@ -5459,8 +5463,6 @@ }, "outputs": [], "source": [ - "\n", - "\n", "from langchain_google_genai import GoogleGenerativeAIEmbeddings\n", "from langchain.vectorstores import MongoDBAtlasVectorSearch\n", "import os\n", @@ -5468,20 +5470,24 @@ "# Assuming you have set your MongoDB connection string as an environment variable\n", "embeddings = GoogleGenerativeAIEmbeddings(model=\"models/embedding-001\")\n", "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n", - " connection_string=MONGO_URI,\n", - " namespace=\"google-ai.embedded_docs\",\n", - " embedding_key=\"embedding\",\n", - " text_key=\"content\",\n", - " index_name=\"vector_index\",\n", - " embedding=embeddings\n", - " )\n", + " connection_string=MONGO_URI,\n", + " namespace=\"google-ai.embedded_docs\",\n", + " embedding_key=\"embedding\",\n", + " text_key=\"content\",\n", + " index_name=\"vector_index\",\n", + " embedding=embeddings,\n", + ")\n", + "\n", + "\n", "def atlas_search(query: str, k: int = 5):\n", " \"\"\"\n", " Perform a vector similarity search using MongoDB Vector Search.\n", " \"\"\"\n", " try:\n", "\n", - " vector_search_results = vector_store.similarity_search_with_score(query=query, k=k)\n", + " vector_search_results = vector_store.similarity_search_with_score(\n", + " query=query, k=k\n", + " )\n", " ## Remove \"embedding\" key\n", " modified_results = []\n", " for doc, score in vector_search_results:\n", @@ -5518,33 +5524,26 @@ "teams_collection = db[\"team\"]\n", "\n", "\n", - "\n", "@retry.Retry()\n", "def create_team(name, people):\n", - " \"\"\"\n", - " Creates a new team in the teams collection.\n", + " \"\"\"\n", + " Creates a new team in the teams collection.\n", "\n", - " Args:\n", - " name : Name of the team\n", - " people : A list of people in the team.\n", + " Args:\n", + " name : Name of the team\n", + " people : A list of people in the team.\n", "\n", - " Returns:\n", - " A message indicating whether the order was successfully created or an error message.\n", - " \"\"\"\n", - " try:\n", - " result = teams_collection.insert_one({'name': name,\n", - " 'people' : people\n", + " Returns:\n", + " A message indicating whether the order was successfully created or an error message.\n", + " \"\"\"\n", + " try:\n", + " result = teams_collection.insert_one({\"name\": name, \"people\": people})\n", + " return f\"Team created successfully with ID: {result.inserted_id}\"\n", + " except Exception as e:\n", + " return f\"Error creating order: {e}\"\n", "\n", - " })\n", - " return f\"Team created successfully with ID: {result.inserted_id}\"\n", - " except Exception as e:\n", - " return f\"Error creating order: {e}\"\n", "\n", - "tool_calls = {\n", - " 'atlas_search_tool': atlas_search,\n", - " 'create_order': create_team\n", - "}\n", - "\n" + "tool_calls = {\"atlas_search_tool\": atlas_search, \"create_order\": create_team}" ] }, { @@ -5574,54 +5573,40 @@ " \"type\": \"object\",\n", " \"description\": \"A dictionary containing the team details.\",\n", " \"properties\": {\n", - " \"name\": {\n", - " \"type\": \"string\",\n", - " \"description\": \"team name\"\n", - " },\n", + " \"name\": {\"type\": \"string\", \"description\": \"team name\"},\n", " \"people\": {\n", " \"type\": \"array\",\n", " \"description\": \"A list of people in the team.\",\n", " \"items\": {\n", " \"type\": \"string\",\n", - " \"description\": \"A person in the team.\"\n", - " }\n", - " }\n", + " \"description\": \"A person in the team.\",\n", + " },\n", + " },\n", " },\n", - " \"required\": [\"name\",\"people\"]\n", + " \"required\": [\"name\", \"people\"],\n", " }\n", " },\n", - " \"required\": [\"team_data\"]\n", - " }\n", + " \"required\": [\"team_data\"],\n", + " },\n", "}\n", "\n", "atlas_search_tool = {\n", " \"name\": \"atlas_search_tool\",\n", - " \"description\": \" Perform a vector similarity search for employees using MongoDB Atlas Vector\",\n", + " \"description\": \" Perform a vector similarity search for employees using MongoDB Vector Store\",\n", " \"parameters\": {\n", " \"type\": \"object\",\n", " \"properties\": {\n", - " \"query\": {\n", - " \"type\": \"string\",\n", - " \"description\": \"The search query.\"\n", - " },\n", - " \"k\": {\n", - " \"type\": \"integer\",\n", - " \"description\": \"The number of results to return.\"\n", - " }\n", + " \"query\": {\"type\": \"string\", \"description\": \"The search query.\"},\n", + " \"k\": {\"type\": \"integer\", \"description\": \"The number of results to return.\"},\n", " },\n", - " \"required\": [\"query\"]\n", - " }\n", + " \"required\": [\"query\"],\n", + " },\n", "}\n", "\n", "\n", - "tools = [\n", - " {'function_declarations': [team_tool, atlas_search_tool]}\n", - "]\n", + "tools = [{\"function_declarations\": [team_tool, atlas_search_tool]}]\n", "\n", - "tool_calls = {\n", - " 'atlas_search_tool': atlas_search,\n", - " 'create_team': create_team\n", - "}" + "tool_calls = {\"atlas_search_tool\": atlas_search, \"create_team\": create_team}" ] }, { @@ -5649,7 +5634,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "before client invoke [{'function_declarations': [{'name': 'create_team', 'description': 'Creates a new team in the teams collection.', 'parameters': {'type': 'object', 'properties': {'team_data': {'type': 'object', 'description': 'A dictionary containing the team details.', 'properties': {'name': {'type': 'string', 'description': 'team name'}, 'people': {'type': 'array', 'description': 'A list of people in the team.', 'items': {'type': 'string', 'description': 'A person in the team.'}}}, 'required': ['name', 'people']}}, 'required': ['team_data']}}, {'name': 'atlas_search_tool', 'description': ' Perform a vector similarity search for employees using MongoDB Atlas Vector', 'parameters': {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query.'}, 'k': {'type': 'integer', 'description': 'The number of results to return.'}}, 'required': ['query']}}]}]\n" + "before client invoke [{'function_declarations': [{'name': 'create_team', 'description': 'Creates a new team in the teams collection.', 'parameters': {'type': 'object', 'properties': {'team_data': {'type': 'object', 'description': 'A dictionary containing the team details.', 'properties': {'name': {'type': 'string', 'description': 'team name'}, 'people': {'type': 'array', 'description': 'A list of people in the team.', 'items': {'type': 'string', 'description': 'A person in the team.'}}}, 'required': ['name', 'people']}}, 'required': ['team_data']}}, {'name': 'atlas_search_tool', 'description': ' Perform a vector similarity search for employees using MongoDB Vector Store', 'parameters': {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query.'}, 'k': {'type': 'integer', 'description': 'The number of results to return.'}}, 'required': ['query']}}]}]\n" ] }, { @@ -5709,8 +5694,7 @@ "\"\"\"\n", "\n", "\n", - "\n", - "await run(prompt, tools=tools, modality = \"AUDIO\")" + "await run(prompt, tools=tools, modality=\"AUDIO\")" ] }, { @@ -5738,7 +5722,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "before client invoke [{'code_execution': {}}, {'function_declarations': [{'name': 'create_team', 'description': 'Creates a new team in the teams collection.', 'parameters': {'type': 'object', 'properties': {'team_data': {'type': 'object', 'description': 'A dictionary containing the team details.', 'properties': {'name': {'type': 'string', 'description': 'team name'}, 'people': {'type': 'array', 'description': 'A list of people in the team.', 'items': {'type': 'string', 'description': 'A person in the team.'}}}, 'required': ['name', 'people']}}, 'required': ['team_data']}}, {'name': 'atlas_search_tool', 'description': ' Perform a vector similarity search for employees using MongoDB Atlas Vector', 'parameters': {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query.'}, 'k': {'type': 'integer', 'description': 'The number of results to return.'}}, 'required': ['query']}}]}]\n" + "before client invoke [{'code_execution': {}}, {'function_declarations': [{'name': 'create_team', 'description': 'Creates a new team in the teams collection.', 'parameters': {'type': 'object', 'properties': {'team_data': {'type': 'object', 'description': 'A dictionary containing the team details.', 'properties': {'name': {'type': 'string', 'description': 'team name'}, 'people': {'type': 'array', 'description': 'A list of people in the team.', 'items': {'type': 'string', 'description': 'A person in the team.'}}}, 'required': ['name', 'people']}}, 'required': ['team_data']}}, {'name': 'atlas_search_tool', 'description': ' Perform a vector similarity search for employees using MongoDB Vector Store', 'parameters': {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The search query.'}, 'k': {'type': 'integer', 'description': 'The number of results to return.'}}, 'required': ['query']}}]}]\n" ] }, { @@ -6007,9 +5991,10 @@ } ], "source": [ - "tools = [ {'code_execution': {}},\n", - " {'function_declarations': [team_tool, atlas_search_tool]}\n", - " ]\n", + "tools = [\n", + " {\"code_execution\": {}},\n", + " {\"function_declarations\": [team_tool, atlas_search_tool]},\n", + "]\n", "\n", "prompt = \"\"\"Search for \"marketing\" in the database and use thier names to create a team :\n", "1. Search for \"marketing\"\n", @@ -6018,8 +6003,7 @@ "\"\"\"\n", "\n", "\n", - "\n", - "await run(prompt, tools=tools, modality = \"TEXT\")" + "await run(prompt, tools=tools, modality=\"TEXT\")" ] }, { diff --git a/notebooks/agents/MongoDB_Haystack_self_reflecting_Cooking_agent.ipynb b/notebooks/agents/MongoDB_Haystack_self_reflecting_Cooking_agent.ipynb index 216e3d53..9a22ca66 100644 --- a/notebooks/agents/MongoDB_Haystack_self_reflecting_Cooking_agent.ipynb +++ b/notebooks/agents/MongoDB_Haystack_self_reflecting_Cooking_agent.ipynb @@ -17,7 +17,7 @@ "source": [ "# Haystack and MongoDB Atlas Agentic RAG pipelines\n", "\n", - "Haystack and MongoDB enhanced example building on top of the basic RAG pipeline demonstrated on the following [notebook](https://github.com/mongodb-developer/GenAI-Showcase/blob/main/notebooks/rag/haystack_mongodb_cooking_advisor_pipeline.ipynb). Here the pipelines uses advanced technics of self reflection to advise on reciepes considering prices associated from the MongoDB Atlas vector store.\n", + "Haystack and MongoDB enhanced example building on top of the basic RAG pipeline demonstrated on the following [notebook](https://github.com/mongodb-developer/GenAI-Showcase/blob/main/notebooks/rag/haystack_mongodb_cooking_advisor_pipeline.ipynb). Here the pipelines uses advanced technics of self reflection to advise on reciepes considering prices associated from the MongoDB Vector Store.\n", "\n", "Install dependencies:" ] diff --git a/notebooks/agents/airbnb_agent_openai_llamaindex_mongodb.ipynb b/notebooks/agents/airbnb_agent_openai_llamaindex_mongodb.ipynb index 3278687a..316babb6 100644 --- a/notebooks/agents/airbnb_agent_openai_llamaindex_mongodb.ipynb +++ b/notebooks/agents/airbnb_agent_openai_llamaindex_mongodb.ipynb @@ -829,7 +829,7 @@ "id": "dC7CDZGhzPLn" }, "source": [ - "## Create MongoDB Atlas Vector Store" + "## Create MongoDB Vector Store" ] }, { diff --git a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb index 360871f3..c5a76fbd 100644 --- a/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb +++ b/notebooks/agents/mongodb_as_a_toolbox_for_llamaindex_agents.ipynb @@ -165,9 +165,9 @@ "id": "b6f3012b" }, "source": [ - "## Download and store policy documents into MongoDB Atlas vector store\n", + "## Download and store policy documents into MongoDB Vector Store\n", "\n", - "This cell downloads policy documents and stores them in a MongoDB Atlas vector store. It initializes a vector store, checks if the collection is empty, downloads PDF documents, loads them, adds metadata, initializes embedding and node parsing, parses documents into nodes, creates a storage context, creates a vector index, and ingests the documents." + "This cell downloads policy documents and stores them in a MongoDB Vector Store. It initializes a vector store, checks if the collection is empty, downloads PDF documents, loads them, adds metadata, initializes embedding and node parsing, parses documents into nodes, creates a storage context, creates a vector index, and ingests the documents." ] }, { diff --git a/notebooks/agents/self_reflecting_gift_agent_haystack.ipynb b/notebooks/agents/self_reflecting_gift_agent_haystack.ipynb index cc2fe933..0880d38f 100644 --- a/notebooks/agents/self_reflecting_gift_agent_haystack.ipynb +++ b/notebooks/agents/self_reflecting_gift_agent_haystack.ipynb @@ -9,7 +9,7 @@ "# Self-Reflecting Gift Agent with Haystack and MongoDB Atlas\n", "This notebook demonstrates how to build a self-reflecting gift selection agent using [Haystack](https://haystack.deepset.ai/) and MongoDB Atlas!\n", "\n", - "The agent will help optimize gift selections based on children's wishlists and budget constraints, using MongoDB Atlas vector search for semantic matching and implementing self-reflection to ensure the best possible gift combinations.\n", + "The agent will help optimize gift selections based on children's wishlists and budget constraints, using MongoDB Vector Search for semantic matching and implementing self-reflection to ensure the best possible gift combinations.\n", "\n", "**Components to use in this notebook:**\n", "- [`OpenAITextEmbedder`](https://docs.haystack.deepset.ai/docs/openaitextembedder) for query embedding\n", diff --git a/notebooks/evals/Patronus_MongoDB.ipynb b/notebooks/evals/Patronus_MongoDB.ipynb index 4802ba12..30775714 100644 --- a/notebooks/evals/Patronus_MongoDB.ipynb +++ b/notebooks/evals/Patronus_MongoDB.ipynb @@ -8,7 +8,7 @@ "\n", "## How to Query and Retrieve Results from Atlas Vector Store\n", "\n", - "To query and retrieve results from MongoDB Atlas vector store, follow these three steps:\n", + "To query and retrieve results from MongoDB Vector Store, follow these three steps:\n", "\n", "### Set Up the Database on Atlas\n", "First, you need to create an account on MongoDB Atlas. This involves signing in to your MongoDB Atlas account, creating a new cluster, and adding a database and collection. You can skip this step if you have already have your collection for vector search.\n", diff --git a/notebooks/evals/ragas-evaluation.ipynb b/notebooks/evals/ragas-evaluation.ipynb index 2f4b85b8..c71d00fa 100644 --- a/notebooks/evals/ragas-evaluation.ipynb +++ b/notebooks/evals/ragas-evaluation.ipynb @@ -33,7 +33,7 @@ "

\n", "- **langchain**: Python library to develop LLM applications using LangChain\n", "

\n", - "- **langchain-mongodb**: Python package to use MongoDB Atlas vector Search with LangChain\n", + "- **langchain-mongodb**: Python package to use MongoDB Vector Search with LangChain\n", "

\n", "- **langchain-openai**: Python package to use OpenAI models in LangChain\n", "

\n", diff --git a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb index cf1b73a0..eb4d646d 100644 --- a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb +++ b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb @@ -32,7 +32,7 @@ "\n", "* Building a Trader Joe’s AI party planner using Playwright, LlamaIndex, and MongoDB MongoDB Vector Search\n", "* Scraping Trader Joe’s fall items with Playwright and formatting them for chatbot use\n", - "* Setting up and embedding product data in MongoDB Atlas Vector Store for semantic search\n", + "* Setting up and embedding product data in MongoDB Vector Store for semantic search\n", "* Creating a Retrieval-Augmented Generation (RAG) chatbot to answer party planning questions\n", "* Adding interactive Chat Engine functionality for back-and-forth Q&A about fall party items\n", "\n", diff --git a/notebooks/rag/openai_text_3_emebdding.ipynb b/notebooks/rag/openai_text_3_emebdding.ipynb index 288cd587..a35e1c91 100644 --- a/notebooks/rag/openai_text_3_emebdding.ipynb +++ b/notebooks/rag/openai_text_3_emebdding.ipynb @@ -17,7 +17,7 @@ "source": [ "# Using OpenAI Latest Embeddings In A RAG System With MongoDB\n", "\n", - "OpenAI recently released new embeddings and moderation models. This article explores the step-by-step implementation process of utilizing one of the new embedding models: text-embedding-3-small within a Retrieval Augmented Generation(RAG) System powered by MongoDB Atlas Vector Database.\n" + "OpenAI recently released new embeddings and moderation models. This article explores the step-by-step implementation process of utilizing one of the new embedding models: text-embedding-3-small within a Retrieval Augmented Generation(RAG) System powered by MongoDB Vector Store.\n" ] }, { diff --git a/notebooks/rag/rag_chunking_strategies.ipynb b/notebooks/rag/rag_chunking_strategies.ipynb index 403fd13b..d94d483a 100644 --- a/notebooks/rag/rag_chunking_strategies.ipynb +++ b/notebooks/rag/rag_chunking_strategies.ipynb @@ -495,13 +495,13 @@ "source": [ "def create_vector_store(docs: List[Document]) -> MongoDBAtlasVectorSearch:\n", " \"\"\"\n", - " Create MongoDB Atlas vector store\n", + " Create MongoDB Vector Store\n", "\n", " Args:\n", " docs (List[Document]): List of documents to create the vector store\n", "\n", " Returns:\n", - " MongoDBAtlasVectorSearch: MongoDB Atlas vector store\n", + " MongoDBAtlasVectorSearch: MongoDB Vector Store\n", " \"\"\"\n", " vector_store = MongoDBAtlasVectorSearch.from_documents(\n", " documents=docs,\n", diff --git a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb index 4ca4d92f..c3054ebf 100644 --- a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb +++ b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb @@ -66,7 +66,7 @@ "- ✅ Designing agentic workflows with tool integration\n", "- ✅ Evaluating and improving AI system quality\n", "\n", - "**Key topics explored:** Multi-modal RAG architecture, MongoDB Atlas vector search, embeddings, hybrid search with RankFusion, AI hallucination detection using Galileo, agentic workflows with LangGraph, GitHub repository processing with GitIngest, quality evaluation frameworks, tool development and integration, and production-ready AI observability patterns." + "**Key topics explored:** Multi-modal RAG architecture, MongoDB Vector Search, embeddings, hybrid search with RankFusion, AI hallucination detection using Galileo, agentic workflows with LangGraph, GitHub repository processing with GitIngest, quality evaluation frameworks, tool development and integration, and production-ready AI observability patterns." ] }, { From cc1a6e1712d9998463e9ce4f73e072ae0e32ba0a Mon Sep 17 00:00:00 2001 From: ajosh0504 Date: Fri, 22 May 2026 10:42:10 -0700 Subject: [PATCH 21/22] Removing stray file --- entries.json | 2 -- 1 file changed, 2 deletions(-) delete mode 100644 entries.json diff --git a/entries.json b/entries.json deleted file mode 100644 index d6c9c0b8..00000000 --- a/entries.json +++ /dev/null @@ -1,2 +0,0 @@ -{"_id":{"$oid":"694447bbe08fda8e5bb9b311"},"user_id":"Apoorva","title":"17/12/2025","version":2,"created_at":{"$date":"2025-12-17T00:00:00Z"},"sentiment":"positive","themes":["nature","appreciation","beauty"]} -{"_id":{"$oid":"694448f66d70d639dc47434c"},"user_id":"Apoorva","title":"17/12/2025","version":1,"created_at":{"$date":"2025-12-17T00:00:00Z"}} From a6e60505ef80c0634f1f3c8b496d721a9c32430e Mon Sep 17 00:00:00 2001 From: ajosh0504 Date: Fri, 22 May 2026 10:47:22 -0700 Subject: [PATCH 22/22] Removing references of MongoDB MongoDB --- notebooks/performance_guidance/README.md | 8 ++++---- ...orkload_database_architecture_mongodb_elastic.ipynb | 4 ++-- ...tabase_performance_guidance_mongondb_pgvector.ipynb | 10 +++++----- notebooks/rag/README.md | 2 +- ...PartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb | 2 +- .../rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb | 2 +- .../self_querying_mongodb_unstructured_langgraph.ipynb | 6 +++--- .../ai_hallucination_detection_and_reduction.ipynb | 2 +- ...y_Chain_Management_for_International_Shipping.ipynb | 2 +- .../agentic_knowledge_discovery_notebook.ipynb | 4 ++-- 10 files changed, 21 insertions(+), 21 deletions(-) diff --git a/notebooks/performance_guidance/README.md b/notebooks/performance_guidance/README.md index 0fc0b79a..2ddc0743 100644 --- a/notebooks/performance_guidance/README.md +++ b/notebooks/performance_guidance/README.md @@ -1,8 +1,8 @@ -Performance guidance showing how MongoDB MongoDB Vector Search compares against other vector databases. +Performance guidance showing how MongoDB Vector Search compares against other vector databases. -Jupyter Notebooks comparing MongoDB MongoDB Vector Search with other vector databases and search engines. +Jupyter Notebooks comparing MongoDB Vector Search with other vector databases and search engines. | Title | Notebook | |-------|-------| -| Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb) | -| AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb) | +| Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb) | +| AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB Vector Search | [![View Notebook](https://img.shields.io/badge/view-notebook-orange?logo=jupyter)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb) | diff --git a/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb b/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb index c29d7f83..92b93326 100644 --- a/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb +++ b/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb @@ -6,7 +6,7 @@ "id": "0ioUyhIh4VMe" }, "source": [ - "# Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB MongoDB Vector Search\n", + "# Vector Database Comparison For AI Workloads: Elasticsearch vs MongoDB Vector Search\n", "\n", "\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/ai_workload_database_architecture_mongodb_elastic.ipynb)\n", @@ -1049,7 +1049,7 @@ "id": "KZTYPIn34VMi" }, "source": [ - "## Part 3: Search with MongoDB MongoDB Vector Search" + "## Part 3: Search with MongoDB Vector Search" ] }, { diff --git a/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb b/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb index 42b9a58d..1a665812 100644 --- a/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb +++ b/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB MongoDB Vector Search\n", + "# AI Database Performance Comparison For AI Workloads: PostgreSQL/PgVector vs MongoDB Vector Search\n", "\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mongodb-developer/GenAI-Showcase/blob/main/notebooks/performance_guidance/vector_database_performance_guidance_mongondb_pgvector.ipynb)\n", "-----\n", @@ -35,14 +35,14 @@ "- PostgreSQL with pgvector:\n", " - How to set up a PostgreSQL database with the pgvector extension.\n", " - How to run text, vector, and hybrid searches on PostgreSQL.\n", - "- MongoDB MongoDB Vector Search:\n", + "- MongoDB Vector Search:\n", " - How to set up a MongoDB Atlas database with native Vector Search capabilities.\n", " - How to execute text, vector, and hybrid searches on MongoDB Atlas.\n", "- AI Workload Overview:\n", " - This notebook showcases a standard AI workload involving vector embeddings and the retrieval of semantically similar documents. \n", " - The system leverages two different vector search solutions:\n", " - PostgreSQL with pgvector: A powerful extension that integrates vector search capabilities directly into PostgreSQL.\n", - " - MongoDB MongoDB Vector Search: A native vector search feature built into MongoDB, optimized for modern, document-based applications.\n", + " - MongoDB Vector Search: A native vector search feature built into MongoDB, optimized for modern, document-based applications.\n", "- AI Workload Metrics:\n", " - Latency: The time it takes to retrieve the top n results\n", " - Throughput: The number of queries processed per second\n", @@ -2774,7 +2774,7 @@ "\n", "This notebook implements and benchmarks a standard AI workload that involves vector embeddings and the retreival of semantically similar documents from a database. The system uses two different vector databases:\n", "- PostgreSQL with pgvector: A vector database extension for PostgreSQL that enables vector search on the database.\n", - "- MongoDB MongoDB Vector Search: A vector search feature for MongoDB Database that enables vector search on the database.\n" + "- MongoDB Vector Search: A vector search feature for MongoDB Database that enables vector search on the database.\n" ] }, { @@ -4151,7 +4151,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Part 3: Semantic Search with MongoDB MongoDB Vector Search" + "## Part 3: Semantic Search with MongoDB Vector Search" ] }, { diff --git a/notebooks/rag/README.md b/notebooks/rag/README.md index a34cdca5..bea8b235 100644 --- a/notebooks/rag/README.md +++ b/notebooks/rag/README.md @@ -1,4 +1,4 @@ -Jupyter Notebooks demonstrating various Retrieval Augmented Generation (RAG) implementations using LLM providers, frameworks and MongoDB MongoDB Vector Search. +Jupyter Notebooks demonstrating various Retrieval Augmented Generation (RAG) implementations using LLM providers, frameworks and MongoDB Vector Search. | Title | Stack | Notebook | |-------|-------|----------| diff --git a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb index eb4d646d..47c0dd75 100644 --- a/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb +++ b/notebooks/rag/TraderJoesFallAIPartyPlanner_PlaywrightLlamaIndexVectorSearch.ipynb @@ -30,7 +30,7 @@ "\n", "What's Covered\n", "\n", - "* Building a Trader Joe’s AI party planner using Playwright, LlamaIndex, and MongoDB MongoDB Vector Search\n", + "* Building a Trader Joe’s AI party planner using Playwright, LlamaIndex, and MongoDB Vector Search\n", "* Scraping Trader Joe’s fall items with Playwright and formatting them for chatbot use\n", "* Setting up and embedding product data in MongoDB Vector Store for semantic search\n", "* Creating a Retrieval-Augmented Generation (RAG) chatbot to answer party planning questions\n", diff --git a/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb b/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb index 3e80bb2d..10b1a179 100644 --- a/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb +++ b/notebooks/rag/deepseek_r1_rag_pipeline_with_mongodb.ipynb @@ -908,7 +908,7 @@ "source": [ "# The field containing the text embeddings on each document within the shipping_data collection\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB MongoDB Vector Search index name\n", + "# MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, diff --git a/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb b/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb index b3137cbe..c2e726ae 100644 --- a/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb +++ b/notebooks/rag/self_querying_mongodb_unstructured_langgraph.ipynb @@ -621,7 +621,7 @@ "Next, let's add the graph nodes. Nodes in LangGraph are functions or tools that your system has access to in order to complete the task. Each node updates one or more attributes in the graph state with its return value after it executes. Our assistant has four nodes:\n", "1. **Metadata Extractor**: Extract metadata from a natural language query\n", "2. **Filter Generator**: Generate a MongoDB Query API filter definition\n", - "3. **MongoDB MongoDB Vector Search**: Retrieve documents from MongoDB using semantic search\n", + "3. **MongoDB Vector Search**: Retrieve documents from MongoDB using semantic search\n", "4. **Answer Generator**: Generate an answer to the user question\n", "\n", "\n" @@ -823,7 +823,7 @@ "id": "U1nFUwqbtGtS" }, "source": [ - "### MongoDB MongoDB Vector Search" + "### MongoDB Vector Search" ] }, { @@ -886,7 +886,7 @@ "source": [ "def vector_search(state: Dict) -> Dict:\n", " \"\"\"\n", - " Get relevant information using MongoDB MongoDB Vector Search\n", + " Get relevant information using MongoDB Vector Search\n", "\n", " Args:\n", " state (Dict): The current graph state\n", diff --git a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb index c3054ebf..a87853c2 100644 --- a/partners/galileo/ai_hallucination_detection_and_reduction.ipynb +++ b/partners/galileo/ai_hallucination_detection_and_reduction.ipynb @@ -1410,7 +1410,7 @@ " 'functions\\n'\n", " '- 👤 **Persona System**: Create consistent, specialized agent '\n", " 'personalities\\n'\n", - " '- 📊 **Vector Search**: MongoDB MongoDB Vector Search for efficient '\n", + " '- 📊 **Vector Search**: MongoDB Vector Search for efficient '\n", " 'retrieval\\n'\n", " '\\n'\n", " '## Key Features\\n'\n", diff --git a/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb b/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb index b0e5fc7b..37d92a82 100644 --- a/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb +++ b/partners/gravity9/Agentic_System_Enhanced_Contract_and_Supply_Chain_Management_for_International_Shipping.ipynb @@ -1393,7 +1393,7 @@ "source": [ "# The field containing the text embeddings on each document within the shipping_data collection\n", "embedding_field_name = \"embedding\"\n", - "# MongoDB MongoDB Vector Search index name\n", + "# MongoDB Vector Search index name\n", "vector_search_index_name = \"vector_index\"" ] }, diff --git a/partners/langchain/agentic_knowledge_discovery_notebook.ipynb b/partners/langchain/agentic_knowledge_discovery_notebook.ipynb index be3a48f7..0525481c 100644 --- a/partners/langchain/agentic_knowledge_discovery_notebook.ipynb +++ b/partners/langchain/agentic_knowledge_discovery_notebook.ipynb @@ -35,7 +35,7 @@ "* **Mobilizing knowledge resources**: Retrieving relevant technical procedures, best practices, and previous incident documentation.\n", "* **Orchestrating coordinated response**: Generating comprehensive response plans with prioritized action items, team assignments, and communication protocols.\n", "\n", - "Built on `MongoDB MongoDB Vector Search` for high-performance semantic search and document retrieval, `LangChain` and `LangGraph` for agentic workflow orchestration, this approach delivers an intelligent emergency response system that dramatically reduces incident resolution time and business impact.\n" + "Built on `MongoDB Vector Search` for high-performance semantic search and document retrieval, `LangChain` and `LangGraph` for agentic workflow orchestration, this approach delivers an intelligent emergency response system that dramatically reduces incident resolution time and business impact.\n" ] }, { @@ -124,7 +124,7 @@ "\n", "**Key Components:**\n", "\n", - "- MongoDB MongoDB Vector Search: Dense vector indexing for semantic relevance.\n", + "- MongoDB Vector Search: Dense vector indexing for semantic relevance.\n", "\n", "- Voyage AI: State of the art embedding models and rerankers\n", "\n",