lazyFrogLOL/llmdocparser

A package for parsing PDFs and analyzing their content using LLMs.

47
/ 100
Emerging

Employs a layout analysis model to classify each PDF region (text, title, figure, table, equation, etc.) with precise coordinates and reading order, then extracts region images for multimodal LLM processing. Supports multiple LLM backends including Azure OpenAI, OpenAI, and Dashscope with configurable concurrency, optimized for RAG-friendly output that preserves document structure and semantic context.

269 stars and 43 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

269

Forks

8

Language

Python

License

MIT

Last pushed

Aug 06, 2024

Monthly downloads

43

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/lazyFrogLOL/llmdocparser"

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