mba/chunking_strategies_evaluation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
27 Commits 1 Branch 0 Tags
55907a8dec586fc55b32cf9f5d9faba8b0b9479b
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
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
docs
feat(documents): add text pdf ingestion with heading reconstruction
2026-08-02 16:59:42 +03:30
files
docs(data): add 21-question evaluation dataset for benchmarking
2026-07-26 13:48:36 +03:30
src
feat(documents): add text pdf ingestion with heading reconstruction
2026-08-02 16:59:42 +03:30
.env.example
feat(documents): add text pdf ingestion with heading reconstruction
2026-08-02 16:59:42 +03:30
.gitignore
Initial commit
2026-07-21 11:27:49 +03:30
CONTEXT.md
docs: add project documentation and task tracking
2026-07-29 17:55:01 +03:30
LICENSE
Initial commit
2026-07-21 11:27:49 +03:30
pyproject.toml
build(deps): add pymupdf for text pdf extraction
2026-08-02 16:59:42 +03:30
README.md
Initial commit
2026-07-21 11:27:49 +03:30

README.md

chunking_strategies_evaluation

This repo is in order to reach multiple chunking strategies and evaulate them

Reference in New Issue View Git Blame Copy Permalink
Description
This repo is in order to reach multiple chunking strategies and evaulate them
Readme Unlicense 554 KiB
Languages
Python 62.4%
HTML 37.6%