Document Loaders

Managed AWS service that automatically extracts text, handwriting, tables, and form fields from scanned documents and PD...

Microsoft's cloud service for intelligent document processing — extracts structured data from forms, invoices, receipts,...

Python library that extracts tables from text-based PDF files into structured data formats. Offers two parsing methods (...

Open-source async web crawler that extracts clean markdown and structured data from web pages for LLM consumption. Diffe...

Open-source document parsing toolkit by IBM that converts PDFs, DOCX, PPTX, and images into structured JSON or Markdown ...

Google Cloud's document understanding platform with pre-trained processors for contracts, invoices, identity documents, ...

Proprietary document parser optimized for LLM ingestion with superior handling of complex PDFs, tables, and mixed media ...

Fast open-source PDF-to-Markdown converter that outperforms Nougat on most documents, supporting OCR, complex layouts, e...

High-performance Python binding for MuPDF — a lightweight PDF and XPS viewer — enabling fast text extraction, page rende...

API-first document parsing service designed for production RAG pipelines, offering high-accuracy extraction from complex...

Web scraping and crawling API that extracts structured data from any URL for AI agents, RAG pipelines, and LLMs. Differe...

ETL platform that ingests unstructured documents (PDFs, images, HTML, etc.) and transforms them into clean, structured d...

Open-source PDF OCR tool that uses vision-capable LLMs (GPT-4o, Claude) to convert any PDF page into clean Markdown via ...