Datalab

Open-source toolkit that turns documents into AI-ready Markdown and JSON.

A document-processing toolkit that converts PDF, DOCX, PPTX, XLSX, HTML, images, and audio into clean Markdown or JSON for LLM and RAG pipelines. It does advanced PDF understanding — page layout, reading order, table structure, and OCR for scans — and ships a hybrid chunker plus native LangChain and LlamaIndex integrations. Small enough to run on a laptop via a Python API or CLI; MIT-licensed and community-governed.

Agentic document parsing and extraction for AI teams, via one API.

A document-intelligence API that parses, splits, extracts, and edits PDFs, images, spreadsheets, and slides into clean, structured output for RAG and AI pipelines. It blends custom in-house models with frontier ones and bills via usage credits, automatically discounting pages it can parse without the heavier pipeline.

AI document-processing API that turns files into structured data.

Mindee is a developer-first document-AI platform that converts photos, PDFs, and scans — invoices, receipts, IDs, financial and mail documents — into structured JSON through a single REST API, with no model training required. Beyond extraction it handles document splitting, classification, and cropping, and ships SDKs for Python, Java, PHP, and more. Billing is credit-based per page processed.

ETL for LLMs — turn PDFs, decks, and emails into clean, structured data.

Ingests 64+ file types and partitions, chunks, enriches, and embeds them into LLM-ready output, handling OCR, tables, and document hierarchy. An open-source library plus a low-code platform and API; a staple preprocessing layer for production RAG.