opendatalab/OmniDocBench

benchmark dataset and tools for evaluating document parsing on diverse PDFs

View on index · View in 3D Map

Related repos

• extracts tables, formulas, and text from PDFs
• AI tool for extracting structured data from PDFs
• PDF processing toolkit for LLMs
• OCR app with PDF processing and document conversion
• Document processing toolkit for parsing and converting files like PDFs into formats ready for AI.
• OCR and document analysis tool for multiple languages
• on-premises toolkit for extracting and benchmarking info from documents
• open-source tool for parsing PDFs, Word, and PowerPoint for LLMs
• Organizes documents with machine learning and OCR