Hi maintainers,
I was looking at the current RAG memory path and wanted to ask whether you would be open to a small vector backend abstraction plus optional Milvus support.
From the current code, autoagent/memory/rag_memory.py appears to build directly on ChromaDB's PersistentClient. Chroma is a good local default, but a narrow backend interface could let users keep the same AutoAgent memory API while choosing different vector stores for different deployment sizes.
A possible scoped shape:
- Keep ChromaDB as the default backend.
- Introduce a small backend interface around document add/update/delete/search and metadata filtering.
- Add an optional Milvus backend behind configuration and an optional dependency.
- Support Milvus Lite for local development, and Milvus server / Zilliz Cloud for larger deployments.
- Add focused tests that cover backend selection and retrieval behavior without changing the higher-level agent flow.
Would this direction fit AutoAgent? If yes, would you prefer this as an optional backend in core, or as an external adapter/example package?
Hi maintainers,
I was looking at the current RAG memory path and wanted to ask whether you would be open to a small vector backend abstraction plus optional Milvus support.
From the current code,
autoagent/memory/rag_memory.pyappears to build directly on ChromaDB'sPersistentClient. Chroma is a good local default, but a narrow backend interface could let users keep the same AutoAgent memory API while choosing different vector stores for different deployment sizes.A possible scoped shape:
Would this direction fit AutoAgent? If yes, would you prefer this as an optional backend in core, or as an external adapter/example package?