Rhubarb documentation

Rhubarb is a light-weight Python framework that makes it easy to build document understanding applications using Multi-modal Large Language Models (LLMs) and Embedding models. Rhubarb is created from the ground-up to work with Amazon Bedrock and Anthropic Claude V3 Multi-modal Language Models, and Amazon Titan Multi-modal Embedding model.

Quickstart

• Quickstart
  • Installation
  • Configuration
  • Using Rhubarb
• Contributing
  • Error installing pre-commit hook
  • Before committing

Usage

• Introduction
  • Features
  • Things to know
• Usage
  • Document Q&A
  • Change Default Model
  • Specify Document Pages
  • Named Entity Recognition (NER)
  • PII Recognition
  • Structured Data Extraction
  • Document Summarization
  • Chat with Documents
  • Working with images
  • Document Classification
  • See also:

Configuration

• Global Configuration
  • Class Definition
  • Available Configurations
  • Methods