mba/chunking_strategies_evaluation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
44 Commits 1 Branch 0 Tags
640691b8ab3d5eb5b1876c75ccb1831b2d81455e
Commit Graph

5 Commits

Author SHA1 Message Date
Mahdi Bazrafshan
2ac69c9944 docs: record decision board language and adr-0026 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-17 14:22:28 +03:30
Mahdi Bazrafshan
1401e46c9a docs: record embedding, neighbor, and inspect decisions 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-10 14:13:07 +03:30
Mahdi Bazrafshan
9ce2072c23 feat(dashboard): add pdf workspace via shared format filter 
Why:
- Avoid a forked PDF UI while scoping Word vs PDF workflows.

Changes:
- formatFilter on shared tabs, PDF Workspace accordion tab, word-only defaults elsewhere.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-02 16:59:42 +03:30
Mahdi Bazrafshan
55907a8dec feat(documents): add text pdf ingestion with heading reconstruction 
Why:
- Support Text PDFs in the same DocumentTree/markdown contract as DOCX.

Changes:
- PyMuPDF parser, text-layer gate, shared heading heuristics, upload dispatch for .pdf.

Impact:
- Scanned/image PDFs are rejected at upload; requires pymupdf installed.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-02 16:59:42 +03:30
Mahdi Bazrafshan
09f9bb53bf docs: add domain glossary and architectural decision records 
15 ADRs covering chunk model, failure handling, evaluation, parsing, directory structure, REST design, and strategy-specific decisions. 62 domain terms across 7 sections.
 2026-07-21 18:51:46 +03:30