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

💡Why ContextGem?

Most LLM frameworks require repetitive boilerplate to extract even basic fields. ContextGem eliminates that with powerful abstractions that handle dynamic prompt generation, data validation, and reference tracking — so you can focus on what matters.

✨ Key Features

• Automated dynamic prompts

• Automatic data modeling & validation

• Granular reference mapping (paragraph/sentence level)

• Justification for every extraction

• Neural segmentation (SaT)

• Supports most LLM providers

📄 DOCX converter

v0.2.0 now provides native DOCX converter to easily transform DOCX files into LLM-ready data:

• Extracts information that other open-source tools often do not capture: misaligned tables, comments, footnotes, textboxes, headers/footers, and embedded images

• Preserves document structure with rich metadata for improved LLM analysis

👉 Explore all features in the README

If you find ContextGem useful, please support the project by sharing it with fellow developers and give it a ⭐