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 +1,7 @@
+# The answer sits at the end of a long passage
+
+question + passage = 224 tokens
+score with max length 512 : -1.50
+score with max length  64 : -11.03   (the answer was cut off before the model saw it)
+score of the answer alone : 2.46
+passages in this corpus longer than 256 tokens: 0 of 94