PrototypeCommon
GiovanniPasq/chunky
Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.
- Owner
- GiovanniPasq (personal account)
- Stars
- Stars: 194
- Forks
- Forks: 21
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- chunkingragretrieval-augmented-generationchunk-validationdocument-processingmarkdownpdf-processingrag-evaluationrag-pipelinechonkie
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by GiovanniPasq
All 2 repos by GiovanniPasq- GiovanniPasq/agentic-rag-for-dummiesStars: 4,314Jupyter NotebookRC
Nearby in Python
All Python repos- jaredchu/context-docsStars: 194PythonPrototype
- orange2ai/podcast-to-articleStars: 194PythonPrototype
- JoasASantos/php2shell-exploitStars: 194PythonPrototype
- brosner/django-timezonesStars: 194PythonPrototype
- django-denorm/django-denormStars: 194PythonPrototype
- vincentbernat/snimpyStars: 194PythonPrototype