Welcome to ContextGem Documentation!

ContextGem logo

Welcome to ContextGem Documentation!#

ContextGem is a free, open-source LLM framework that makes it radically easier to extract structured data and insights from documents โ€” with minimal code.


๐Ÿ“š Project Description

Learn about the motivation behind ContextGem and how it works.

Why ContextGem?
๐Ÿš€ Getting Started

Instructions to install ContextGem and quickly start using it.

Installation
๐Ÿ“„ Documents

Learn how to create and configure documents to extract information (aspects and concepts) from.

Creating Documents
๐Ÿ“‹ Extracting Aspects

Learn how to identify and extract specific document sections like clauses, chapters, or terms using ContextGemโ€™s Aspects API.

Aspect Extraction
๐ŸŽฏ Extracting Concepts

Learn how to extract and infer structured data like JSON objects, strings, numbers, dates, booleans, ratings, and labels from documents using ContextGemโ€™s Concepts API.

Supported Concepts
๐Ÿ”€ Extraction Pipelines

Learn how to create reusable extraction pipelines that combine aspects and concepts for consistent document analysis across multiple files.

Extraction Pipelines
๐Ÿค– Large Language Models

Learn about supported cloud LLM providers and local models, and how to configure and use them for extraction.

Supported LLMs
โšก Advanced Usage

Explore advanced features and techniques for extracting data from documents.

Advanced usage examples
โš™๏ธ Optimization Guide

Learn how to optimize your extraction pipeline for accuracy, cost, and performance.

Choosing the Right LLM(s)
๐Ÿ’พ Serialization

Learn how to serialize and deserialize ContextGem objects for storage and transfer.

Serializing objects and results
๐Ÿ“– API Reference

Complete API documentation for all ContextGem modules and classes.

Documents

Indices and tables#