feat: two-stage RRF for fair wiki vs web ranking
Build and Push / build (release) Successful in 28s

- Merge vector+graph into single wiki source before RRF with web
- Wiki pages no longer get 2x advantage from dual retrieval
- Add vector similarity threshold (0.7 default)
- Skip synonyms in graph search to reduce noise
- Fix duplicate entity links bug in graph search

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-15 17:49:31 +01:00
co-authored by Claude Opus 4.5
parent 464ec5380c
commit c359fcbcd8
6 changed files with 213 additions and 81 deletions
+1
View File
@@ -72,6 +72,7 @@ class Settings(BaseSettings):
hybrid_rag_vector_limit: int = Field(default=10, ge=1, le=50, description="Vector search limit")
hybrid_rag_graph_limit: int = Field(default=10, ge=1, le=50, description="Graph search limit")
hybrid_rag_web_limit: int = Field(default=5, ge=1, le=20, description="Web search limit")
vector_similarity_threshold: float = Field(default=0.7, ge=0.0, le=1.0, description="Minimum similarity score for vector results")
# Entity Linking Fuzzy Matching Configuration
entity_linking_min_confidence: float = Field(default=0.70, ge=0.0, le=1.0, description="Minimum confidence for entity-document matching")