Easy-to-use and powerful LLM and SLM library with awesome model zoo.

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

ContextGem: Effortless LLM extraction from documents

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

A curated list of resources for Document Understanding (DU) topic

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community. Our intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction.

Local-first AI-powered document intelligence platform for investigative journalism

INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document intelligence.

Knwler is a lightweight, single-file Python tool that extracts structured knowledge graphs from documents using AI. Feed it a PDF or text file and receive a richly connected network of entities, relationships, and topics — complete with an interactive HTML report and exports ready for your favorite graph analytics platform.

A collection of samples demonstrating techniques for processing documents with Azure AI including AI Foundry, OpenAI, Document Intelligence, etc.

ReadingBank: A Benchmark Dataset for Reading Order Detection

World-class multimodal RAG system for financial document analysis. Built to production standards: async, observable, secure, multi-tenant, CI-gated.

The Doc Intelligence in-a-Box project leverages Azure AI Document Intelligence to extract data from PDF forms and store the data in a Azure Cosmos DB. This solution, part of the AI-in-a-Box framework by Microsoft Customer Engineers and Architects, ensures quality, efficiency, and rapid deployment of AI and ML solutions across various industries.

Course Website

XLSX parser for LLMs, RAG, LangChain, LangGraph, CrewAI, Claude, MCP — turns Excel (.xlsx) into citation-ready JSON with formulas, charts, dependency graphs, and token-counted chunks. Open-source Python library (MIT).

Knowing by reasoning, not vectors.

Open-source, self-hosted OSINT investigation platform: turn documents into a live, investigated entity graph. Autonomous agent, graph analytics (centrality, communities, pathfinding), keyless-first tool belt.

A curated list of resources on Table Structure Recognition