AI applications
indra
datalab-to/indra
A lightweight CPU OCR and document-parsing application that turns PDFs and images into Markdown, text, or JSON with layout, language, and handwriting support.
Topics
Related projects
opendataloader-pdf30.3kAn open-source PDF parser for AI-ready data and accessibility, extracting structured Markdown, JSON and HTML with bounding boxes, OCR and automatic tagged-PDF generation.
ade-cli2.4kADE CLI is LandingAI's official command-line client for Agentic Document Extraction, parsing documents and extracting schema-shaped fields with evidence.
docling70.3kA document parsing and conversion framework that turns PDFs, Office files, HTML and more into structured Markdown or JSON, with LangChain, MCP and API-server integrations.
lift1.3kA 9B vision model for document intelligence that extracts schema-aligned JSON from PDFs and images. It ships with local vLLM and Hugging Face inference options, a CLI, and a schema-building studio.
mineru83.4kAn AI-powered document parsing app that converts PDFs and Office files into clean LLM-ready Markdown and JSON.
magika18.8kAn AI-powered file-type detection tool with CLI and APIs that identifies hundreds of formats in milliseconds.