AKSarav/pdfstract

PDFStract - The Extraction and Chunking Layer in Your RAG Pipeline - Available as CLI - WEBUI - API

58
/ 100
Established

Supports swappable extraction backends (Marker, Docling, PyMuPDF4LLM, PaddleOCR, Unstructured) alongside 10+ chunking strategies (semantic, token, code-aware, recursive) and multiple embedding providers—all configurable via single parameters without code changes. Provides a unified Python API, CLI, and Web UI with batch processing and async support, enabling direct experimentation across extraction/chunking/embedding combinations in RAG pipelines.

128 stars. Used by 1 other package. Available on PyPI.

Maintenance 10 / 25
Adoption 11 / 25
Maturity 24 / 25
Community 13 / 25

How are scores calculated?

Stars

128

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Mar 01, 2026

Commits (30d)

0

Dependencies

15

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/AKSarav/pdfstract"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.