google/langextract
Extracts structured data from documents with source grounding
View on index · View in 3D Map
Related repos
- AI tool for extracting structured data from PDFs
- extracts data from any document to markdown, csv, json, html
- on-premises toolkit for extracting and benchmarking info from documents
- AI-powered library for extracting and classifying data from docs with LLMs
- Extracts text from German documents via local or cloud processing
- extracts text and metadata from PDFs, Word, HTML, images, and more with fast Rust core and Python support
- extracts text from documents and images using OCR
- Scrapes documentation into a vector API
- Document parser for extracting content, structure, tables, and metadata from files
