Marky helps you convert things into Markdown 📝

Enhance GPT-3.5-Turbo output using Retrieval-Augmented Generation (RAG) with a user-friendly interface. Select between Wikipedia or integrate external documents to experience precise, context-aware responses.

This repo demonstrates how to use Document Loaders in LangChain to fetch data from sources like text, PDFs, directories, web pages, and CSV files, and convert it into a standard Document format with content and metadata for use with LLMs.

A comprehensive repository to learn and implement Retrieval-Augmented Generation (RAG) from scratch using LangChain. It covers the full RAG pipeline including Document Loaders, Text Splitters, Embeddings, Vector Databases, and Retrievers with practical examples and step-by-step explanations.

Step-by-step LangChain tutorials covering models, prompts, chains, retrievers, tools, and agents — theory to full implementation.

Load documents for RAG pipelines: PDF, DOCX, HTML, Markdown. Smart chunking, metadata extraction. LangChain compatible.

This repository covers all the code materials covered within Jose Portilla's Langchain with Python Bootcamp on Udemy.

Smart Quiz Generator is a Streamlit-based app that uses GPT-4 to create quizzes (MCQ, True/False, or Fill-in-the-Blank) from your own documents (PDF/TXT) or web pages. It processes content, stores it in a FAISS vector store for quick retrieval, and generates customized quizzes based on a chosen topic.

LangChain integration package for Synap DocuAnalyzer

RAG to talk to your code

A LangChain community document loader for Google Classroom. Extract coursework, materials, and Drive attachments for RAG pipelines.

Examples of top-used LangChain document loaders including CSVLoader, DirectoryLoader, PyPDFLoader, TextLoader, and WebBaseLoader. These loaders standardize raw data into LangChain Document objects for further processing, splitting, embeddings, and RAG workflows.

Successfully developed an LLM application which generates a summary, a list of citations and references and response to a user's query based on the research paper's content.

LangChain integration for Ujeebu Extract API - extract clean, structured content from web articles for use with LLM agents and RAG pipelines.

LangChain integration for Ujeebu web scraping and content extraction APIs

Successfully developed a Multi-Domain AI Personal Assistant using LangChain, OpenAI, and Streamlit. The application seamlessly integrates multiple specialized capabilities, including document-based question answering (QA), Python code execution, debugging, explanation and optimization, web search, latest news retrieval, and currency conversion.

A content navigator powered by GPT-3.5-Turbo to explore multiple documents uploaded using Streamlit UI. It uses `Document Array Memory` for small and `Pinecone` for large document pools and delivers concise, referenced search results.

Gen AI with framework Langchain

📄 Summarize research papers, extract citations, and answer queries with this AI-powered assistant built using LangChain and OpenAI's GPT model.