alnzng opened a new pull request, #165:
URL: https://github.com/apache/flink-agents/pull/165
<!--
* Thank you very much for contributing to Flink Agents.
* Please add the relevant components in the PR title. E.g., [api],
[runtime], [java], [python], [hotfix], etc.
-->
<!-- Please link the PR to the relevant issue(s). Hotfix doesn't need this.
-->
Linked issue: #130
### Purpose of change
This PR adds vector store support to Flink Agents by defining base
abstractions for vector store connections and setups, along with a complete
Chroma vector store implementation which provides both local(in-memory) mode
and server mode.
### Tests
Unit tests
### API
Core Vector Store Abstractions:
- BaseVectorStoreConnection - Abstract base for vector store connections
with raw embedding search
- BaseVectorStoreSetup - Abstract base coordinating embedding models with
vector stores
- VectorStoreQuery - Structured query object for text-based semantic search
- VectorStoreQueryResult - Standardized result containing retrieved
documents
- Document - Document model with content, metadata, and optional ID
- VectorStoreQueryMode - Enum for query types (currently SEMANTIC)
ChromaDB Implementation:
- ChromaVectorStoreConnection - Chroma-specific connection implementation
- ChromaVectorStoreSetup - Chroma-specific setup implementation
### Documentation
https://github.com/apache/flink-agents/discussions/143
--
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]
