Fetching metadata from the HF Docker repository...
-
docs: audit learning.md β remove 6 non-GenAI concepts, update stale data, add Concept 21 contextual retrieval
-
docs: add Concept 20 β semantic chunking recall vs precision tradeoff
-
docs: Stage 11 β contextual prod + dashboard polish + concepts 18-19
-
feat: multi-query retrieval + HyDE/MQ eval runs (v1.1.0, v1.2.0 Violet)β
benroshan +1: Claude Sonnet 4.6 - server/retriever.py: _multi_query_expand() generates 3 query phrasings via
Groq LLM; _get_relevant_documents() pools results across all phrasings,
deduplicates by best rank, RRF fuses wider pool before reranking
- config.yaml: multi_query_enabled toggle (default: false); reverted to
baseline (hyde=false, multi_query=false) after eval
- docs/learning.md: Concept 17 β Multi-Query Retrieval
- docs/evolution.md: Stage 9 + Phase 1 conclusion
Eval results:
v1.1.0 Violet (hyde=true): recall=0.545, p50=5883ms β 3Γ latency, not worth it
v1.2.0 Violet (multi_query=true): recall=0.517, p50=2620ms β negligible lift
Phase 1 exhausted. recall=0.51 is a chunking problem, not query formulation.
Next: Phase 2 β Contextual Retrieval (ingest-time LLM chunk augmentation).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>