-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Open
Labels
services[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc
Description
Description
Add Milvus as a vector database option for knowledge base RAG workflows, following the existing Spanner integration pattern.
Motivation
ADK currently supports Vertex AI RAG, LlamaIndex, and Spanner for vector-based retrieval. Milvus is a widely adopted open-source vector database purpose-built for AI applications. Adding Milvus support would give developers a lightweight, self-hosted (or cloud-managed via Zilliz) alternative for building RAG agents.
Proposed Solution
MilvusVectorStore: Utility class for collection setup, data ingestion, and similarity search.MilvusToolset:BaseToolsetimplementation exposing asimilarity_searchtool to LLM agents.MilvusToolSettings/MilvusVectorStoreSettings: Pydantic configuration classes.- Users provide their own embedding function (e.g., Google GenAI
gemini-embedding-001). pymilvus>=2.5.0as an optional dependency (google-adk[milvus]).
Related PR
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
services[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc