yunfengzhou-hub commented on issue #740:
URL: https://github.com/apache/flink-agents/issues/740#issuecomment-4642499080
Verification completed. All documented features work as described.
**What I verified:**
- Chroma in-memory mode: add, query, get, delete, metadata
- Chroma persistent mode: `persist_directory`, data survives agent restart
- Filter DSL: equality shorthand `filters={"key": "value"}`
- ContextRetrievalRequestEvent / ContextRetrievalResponseEvent built-in
action flow
- Custom provider: `BaseVectorStore` subclassing with `_query_embedding`,
`_add_embedding`, `_update_embedding`, `store_kwargs`
- Java compilation: Elasticsearch `@VectorStore` annotation, Document /
VectorStoreQuery construction
- Source code review: Amazon OpenSearch, Amazon S3 Vectors, Milvus (I don't
have these resources)
**Not verified (environment limitation):**
- Elasticsearch / Milvus E2E (Docker images crash with SIGILL on Apple
Silicon ARM64)
- Chroma server / cloud mode (no Chroma server or cloud account)
- Cross-language wrapper (the only Java vector stores are ES/Milvus, both
have the same ARM64 limitation)
**Issues found:** None.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
