Add hybrid-search module: vector, tsvector and BM25 fused with Reciprocal Rank Fusion in Java and SQL over one PostgreSQL table; quality by query type, held-out k check, plans and latency at 50k rows

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_0146opDKBYtADXvkc39zdiyw
2026-10-22 18:04:49 +00:00
parent d7e68a14af
commit 2ccf1d8d19
26 changed files with 1508 additions and 0 deletions
@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+# Regenerates every file in output/ by running the test suite.
+# Needs: JDK 25, Maven, internet for the first run (about 90 MB for the MiniLM model, cached in ~/.cache/minilm),
+# and a PostgreSQL 16 with pgvector 0.8 on localhost:5432 (database ragdemo, user demo / demo).
+# Set HYBRID_DB_URL to point somewhere else. ScaleTest inserts 50,000 rows and builds an HNSW index (about two minutes).
+set -euo pipefail
+cd "$(dirname "$0")/.."
+rm -rf output
+mvn -B -q test
+ls output