Go to file

Mahdi Bazrafshan e1ca9f4127 docs(eval): add human evaluation report for fixed_size ±3

Why:
- Manager deliverable for human evaluation across 10 benchmark documents.

Changes:
- Report markdown, scored CSV, chart generator, and SVG assets
- Linked from docs/README.md

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-22 15:32:35 +03:30

backlog

docs: capture pdf domain language and deferred ingestion backlog

2026-08-02 16:59:42 +03:30

docs

docs(eval): add human evaluation report for fixed_size ±3

2026-08-22 15:32:35 +03:30

files

docs(data): add 21-question evaluation dataset for benchmarking

2026-07-26 13:48:36 +03:30

scripts

chore(scripts): add neighbor expansion benchmark sweep

2026-08-10 14:13:07 +03:30

src

feat(jobs): add background job support for benchmarks and processing

2026-08-22 15:32:33 +03:30

.env.example

chore(config): sync env example and context for ±3 defaults

2026-08-22 15:32:29 +03:30

.gitignore

Initial commit

2026-07-21 11:27:49 +03:30

CONTEXT.md

chore(config): sync env example and context for ±3 defaults

2026-08-22 15:32:29 +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