microsoft / microsoft/agent-framework
Python SDK : Add native vector database connectors and retrieval patterns
Open
@eavanvalkenburg is already working on this.
Since Feb 23, 2026.
memory
python
question
- Dominant language
- Python
- Stars
- 13.6k
- Forks
- 2.3k
- Avg merge
- 2d 45m
- Merged PRs (30d)
- 358
Description
Currently, the Agent Framework lacks built-in support for vector databases, which are essential for RAG patterns in production agent systems.
Proposed Enhancement:
Add first-class connectors for popular vector databases:
Azure AI Search (given Azure ecosystem focus)
Pinecone
Weaviate
Qdrant
Chroma
PostgreSQL with pgvector
Include built-in retrieval patterns:
Semantic search tools for agents
Hybrid search (vector + keyword)
Re-ranking capabilities
Metadata filtering
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.