ayrisdev/yargi-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(semantic_search): make embedding model configurable (#22)

Browse Source 
google/gemini-embedding-001 became paid on OpenRouter, leaving
users without credit unable to run the semantic_search tool. The
old code hardcoded the model and 3072 dimensions in three places.

Make OpenRouterEmbedder accept model/dimension via constructor
args or OPENROUTER_EMBEDDING_MODEL / OPENROUTER_EMBEDDING_DIMENSION
env vars, with the previous values as backward-compatible defaults.
Switch the VectorStore and the response payload in mcp_server_main
to read embedder.dimension instead of the hardcoded 3072 so a
configured non-Gemini model does not produce shape mismatches.

Bad dimension input (non-int or non-positive) now raises a clear
ValueError instead of a downstream shape error.

Documented the new env vars in .env.example.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
saidsurucu
2026-05-03 01:46:33 +03:00
co-authored by Claude Opus 4.7
parent ae5d590cca
commit 42731a2c03
3 changed files with 60 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+7
View File
@@ -79,6 +79,13 @@ JWT_SECRET_KEY=your_jwt_secret_key_here
# If not set, semantic search tool will be disabled
OPENROUTER_API_KEY=sk-or-v1-your_openrouter_api_key_here
# Optional: override the embedding model and dimension.
# Defaults: google/gemini-embedding-001 at 3072 dims (paid on OpenRouter).
# Pick any embedding model from https://openrouter.ai/models?modality=embedding
# and set the dimension to that model's output size — they must match.
# OPENROUTER_EMBEDDING_MODEL=google/gemini-embedding-001
# OPENROUTER_EMBEDDING_DIMENSION=3072
# =============================================================================
# USAGE INSTRUCTIONS
# =============================================================================