Add rerank module: bi-encoder retrieval plus an ONNX Runtime cross-encoder reranker behind a Spring AI DocumentPostProcessor; hit@k and MRR by pool size and question kind, latency by candidates, batch size, threads and int8, and five reproduced traps. Local MiniLM models, no database or API key.

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cfo2K4u4rF18QsPXPFnytf
2026-10-24 18:00:05 +00:00
parent 2ccf1d8d19
commit a429aa40f6
34 changed files with 1617 additions and 0 deletions
@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Regenerates every file in output/ by running the test suite.
+# Needs: JDK 25, Maven, and internet on the first run (about 250 MB of models from Hugging Face, cached in ~/.cache/rerank).
+# No database, no API key. Latency files (06, 07) depend on your machine; every other file is deterministic.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+rm -rf output
+mvn -B -q test
+ls output