Default search_docs to dense; make rerank opt-in (#17)

Co-authored-by: claude <[email protected]>
This commit was merged in pull request #17.
This commit is contained in:
2026-09-29 22:45:25 -04:00
committed by claude
parent 92219878d9
commit dc4a96e8d5
5 changed files with 60 additions and 32 deletions
+6 -6
View File
@@ -32,16 +32,16 @@ services:
# add that hostname here. "*" disables the rebind check entirely.
MCP_ALLOWED_HOSTS: "hvm-docs-mcp,localhost,127.0.0.1"
# Phase 6 — reranker sidecar (jina-reranker-v2-base via llama.cpp).
# Phase 6 — reranker sidecar is wired but off. Eval 2026-09-30
# (post nomic prefixes): dense MRR=0.966 vs bm25+rerank 0.827.
# Set RERANK_ENABLED=true to turn the sidecar back on.
RERANK_URL: http://hvm-rerank:8080
RERANK_POOL: "200"
RERANK_TIMEOUT: "30"
RERANK_ENABLED: "false"
# Phase 8 — hybrid retrieval (BM25 + dense + RRF).
# Eval on the HVM corpus (eval/results/baseline.md, 2026-05-22) shows
# BM25-default + reranker beats hybrid on every metric (MRR 0.920 vs
# 0.875). Leaving HYBRID_SEARCH off so search_docs runs BM25-first +
# reranker; dense is the fallback when BM25 finds nothing.
# Phase 8 — hybrid retrieval (BM25 + dense + RRF). Off: dense is
# the default (eval/results/post-prefix.md). BM25 is fallback only.
HYBRID_SEARCH: "false"
# Phase 10 — usage telemetry.