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 +1,15 @@
+# Choosing k on half of the queries and scoring it on the other half
+
+candidates per list: 20. The 60 queries are split by position into two folds of 30; k comes from {1, 10, 60, 200}.
+
+--- fold 1: train on 30, test on 30 ---
+k chosen on the training half (best MRR@10 0.872): 1
+held-out half, k=1   : 22/30  29/30  0.831
+held-out half, k=60  : 24/30  28/30  0.859
+held-out half, vector only: 21/30  30/30  0.831
+
+--- fold 2: train on 30, test on 30 ---
+k chosen on the training half (best MRR@10 0.859): 60
+held-out half, k=60  : 22/30  27/30  0.794
+held-out half, k=60  : 22/30  27/30  0.794
+held-out half, vector only: 20/30  25/30  0.733