awslabs/rhubarb

A Python framework for multi-modal document understanding with Amazon Bedrock

50
/ 100
Established

This project helps anyone who needs to quickly understand and extract information from documents or videos. You feed it a PDF, Word document, image file, or video, and it answers your questions, summarizes content, extracts specific data like names or PII, or even describes charts and actions. It's designed for professionals who need to get insights from unstructured data without writing complex code.

102 stars.

Use this if you regularly work with large volumes of documents or videos and need a fast, automated way to pull out key information, summarize content, or answer specific questions without manually reviewing everything.

Not ideal if your primary need is simple text search or if you require extremely high-accuracy extraction for highly sensitive, regulatory-critical tasks without human oversight.

document-analysis video-intelligence information-extraction content-summarization data-mining
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

102

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/awslabs/rhubarb"

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