Hybrid Search and Reranker for better tool search

[qdrddr]

A hybrid search of sparse BM25 and dense embedding model (openai text-embedding-3) typically can improve the quality of the semantic search.

Reranker models can also improve the final result.

[qdrddr]

Reranker with graphs
https://github.com/Bavalpreet/MediumBlogs/blob/main/Knowledgegraph%20Reranking/Knowledge_graph_re_ranking.ipynb

[gabornyergesX]

i'd like to see a PR from this feature 🚀

[qdrddr]

Suggested Embedding model: Codestral-Embed from mistral and Mxbai-rerank-v2 to improve performance for, code, MCP, and tool retrieval.

[qdrddr]

Suggested Embedded (In-Progress) VectorDBs:

https://github.com/tursodatabase/turso
https://github.com/chroma-core/chroma
https://github.com/lancedb/lancedb

[qdrddr]

Would appreciate if you vote for this improvement idea to standardize MCP Specification with Delegated Advanced Tool Search in my comment feature here.