Semantic Search MCP for Valkey

[Jonathan-Improving]

Summary

Changes

Provides a full semantic search MCP for Valkey, leveraging its VSS capabilities, and encapsulating vector embeddings so that agents can interop using pure natural language and/or keywords.

User experience

The role of a data scientist would first add documents to the Valkey database using the add_documents MCP, under a specifically named collection, that can be sought using semantic search. The role of researcher would leverage the semantic_search MCP to seek for documents added under a specifically named collection, or query the list_collections MCP to find out what named collections are available for searching.

Checklist

If your change doesn't seem to apply, please leave them unchecked.

• I have reviewed the contributing guidelines
• I have performed a self-review of this change
• Changes have been tested
• Changes are documented

Not a breaking change.

RFC issue number:

Checklist:

• Migration process documented
• Implement warnings (if it can live side by side)

Acknowledgment

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.

[vasigorc]

FWIW, there is a newer V2 version now: https://docs.aws.amazon.com/bedrock/latest/userguide/titan-embedding-models.html

[vasigorc]

We didn't tell in our docstring about this return structure. Could we rather return here a dict smilar to that from the happy path? Something like:

return {
     "status": "failure",
     "added": 0,
     "failure_reason": str(e)
  }

[Jonathan-Improving]

Yep, the other methods return a list, so they're keeping the union of list and string for now. Might be worth thinking about that further though, I just wanted to keep the return structure clutter-free.