mba/chunking_strategies_evaluation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
32 Commits 1 Branch 0 Tags
0ff9d8dd21c38d4a40aaeaa6bc03ce61a256a65a
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
Mahdi Bazrafshan 0ff9d8dd21 feat(storage): add app settings and model-scoped collections 
Why:
- Different Embedding Models must not share Qdrant collections; Admin needs persisted role defaults and Experiment provenance.

Changes:
- Scope collection names by model id; add app_settings, embedding provenance columns, and queries.expansion_tree.

Impact:
- Process/query write only Model Corpus collections; legacy unscoped names are read-only for Admin labeling.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-10 14:12:45 +03:30
backlog
docs: capture pdf domain language and deferred ingestion backlog
2026-08-02 16:59:42 +03:30
docs
feat(dashboard): add pdf workspace via shared format filter
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(storage): add app settings and model-scoped collections
2026-08-10 14:12:45 +03:30
.env.example
feat(chunking): add embedding model registry and ollama config
2026-08-10 14:12:36 +03:30
.gitignore
Initial commit
2026-07-21 11:27:49 +03:30
CONTEXT.md
docs: capture pdf domain language and deferred ingestion backlog
2026-08-02 16:59:42 +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%