awslabs/rhubarb
A Python framework for multi-modal document understanding with Amazon Bedrock
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.
Stars
102
Forks
14
Language
Python
License
Apache-2.0
Category
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.
Related tools
aws-samples/bedrock-access-gateway
OpenAI-Compatible RESTful APIs for Amazon Bedrock
awslabs/amazon-bedrock-agent-samples
Example Jupyter notebooks 📓 and code scripts 💻 for using Amazon Bedrock Agents 🤖 and its functionalities
aws-samples/well-architected-iac-analyzer
Sample Generative AI tool for evaluating Infrastructure as Code and architecture diagrams...
build-on-aws/building-gen-ai-whatsapp-assistant-with-amazon-bedrock-and-python
Build a genAI Whatsapp app that processes images, voice notes, videos, and documents with Amazon...
aws-samples/sample-connector-for-bedrock
Seamlessly invoke Amazon Bedrock or your custom models, enabling a smooth experience with AWS...