Commit Graph

5 Commits

Author SHA1 Message Date
Kshitij 28bb4ca1de fix(parser): recover stolen scope text and truncate next-standard bleed
Add Pass 3 to recover scope text incorrectly placed in previous block, and Pass 4 to truncate bleed from the following standard. Regenerate standards.json and standards_chunks.json with the improved parser.
2026-05-04 00:18:17 +05:30
Kshitij 0440b76111 Revert "chore: remove unnecessary files from /data directory and move /data/processed/retrieval_results.json to /data/results.json"
This reverts commit 1efc0e3482.
2026-05-03 01:32:10 +05:30
Kshitij 1efc0e3482 chore: remove unnecessary files from /data directory and move /data/processed/retrieval_results.json to /data/results.json 2026-05-03 01:18:14 +05:30
Kshitij 29b32dfcac fix: complete requirements.txt and inference.py output correctness.
- Add faiss-cpu, rank-bm25, sentence-transformers, numpy to requirements.txt.
  (previously only pymupdf was listed; other deps were manual-install only)
- Cast score to float() before round() to avoid numpy type serialization errors.
- Pass expected_standards through _format_result for eval script compatibility.
- Update retrieval_results.json with expected_standards per query for eval.
2026-05-03 00:03:03 +05:30
Kshitij f65185b91e feat: add data processing outputs. 2026-04-28 23:55:59 +05:30