AKSarav/pdfstract

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

58
/ 100
Established

This tool helps AI engineers and data scientists prepare PDF documents for use in AI applications like chatbots or semantic search. It takes PDF files as input, extracts the text and structure, breaks it into manageable pieces, and converts these pieces into numerical representations (embeddings). This output can then be directly fed into a Retrieval Augmented Generation (RAG) system or similar AI models.

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

Use this if you need a flexible way to extract, chunk, and embed information from PDFs for your AI applications, allowing you to easily swap between different processing methods.

Not ideal if you only need a simple PDF viewer or editor and don't plan to use the extracted content for advanced AI processing.

AI-engineering data-preparation RAG-pipelines document-intelligence LLM-data-prep
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.