emcf/thepipe

Extracts clean data from documents using vision-language models

View on index · View in 3D Map

Related repos

• Document retrieval with vision language models
• OCR pipeline with local LLM field extraction
• Extracts text from German documents via local or cloud processing
• turns documents into structured data with OCR and layout analysis
• extracts text from documents and images using OCR
• open-source RAG engine for deep document understanding
• Organizes documents with machine learning and OCR
• Framework for computer vision streams
• extracts text and metadata from PDFs, Word, HTML, images, and more with fast Rust core and Python support
• Translates files using language models