LangExtract Web

Acerca de

LangExtract Web provides a comprehensive solution for extracting structured information from various text sources leveraging the power of Large Language Models (LLMs). It acts as a web UI, API, and Model Context Protocol (MCP) wrapper for Google's LangExtract library, enabling users to define extraction tasks with few-shot examples, handle long documents with chunking, and utilize various LLM providers like Gemini, OpenAI, Claude, and Ollama. Its intuitive web interface supports file uploads, URL fetching, and offers detailed API documentation.

Características Principales

• Precise Source Grounding: Maps extractions back to exact text positions.
• Few-shot Learning: Defines extraction tasks with minimal examples, no fine-tuning required.
• Web UI & REST API: Provides a modern web interface and a fully documented REST API.
• LiteLLM Compatible: Supports various LLM providers (Gemini, OpenAI, Claude, Ollama, etc.).
• 1 GitHub stars
• Long Document Optimization: Uses chunking and multi-pass extraction for high recall.

Casos de Uso

• Automating data extraction from unstructured text documents.
• Integrating LLM-powered information extraction into custom applications via API.
• Building AI assistants that require structured data from text for conversational contexts.