factory-rag / eval.py

Commit History

  1. feat: naive fixed-chunk baseline strategy (eval + Compare panel 0) - the honest before picture

    ML Assistant
    3a0dab2

  1. fix: nemotron build branch token-matrix bug (CPU roundtrip proof); eval k==5 double-count fix + MRR@5 metric; transformers>=4.57

    ML Assistant
    0dbf792
  2. feat: per-document summaries (grader scope injection + summary records) and quick-ingest mode

    ML Assistant
    dd64696
  3. feat(eval): real set in EVAL_SETS (--set real, TM-5-811-6 manifest)

    ML Assistant
    6b37b37
  4. feat(eval): --set hard with 16-row adversarial manifest (multi-column, tables, OCR scans, boilerplate)

    ML Assistant
    13e40ce

  1. fix(ingest): page-range attribution per chunk (page+page_end) so cross-page chunks match page-exact queries; advisor detects externally deleted vector store

    ML Assistant
    971549e
  2. chore: remove dead code in eval.py and retrieve.py (undefined-name line, unused prefetch)

    ML Assistant
    72cf4c7
  3. eval: doc_name hit() + KX-40 eval rows + clean exit

    8efaf2e
  4. factory-rag full rebuild: all modules, docs, smoke driver

    rebuild
    d3f418e