Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Get your documents ready for gen AI

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Knowledge Agents and Management in the Cloud

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

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

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.

Eden AI: simplify the use and deployment of AI technologies by providing a unique API that connects to the best possible AI engines

Open-source spreadsheets platform for deep research and document processing

A comprehensive list of document parsers, covering PDF-to-text conversion and layout extraction. Each tested for support of tables, equations, handwriting, two-column layouts, and multi-column layouts.

Jupyter notebooks testing different OCR models for document parsing (Dolphin, MonkeyOCR, Marker, Nanonets, ...)

A Unified Toolkit for Deep Learning-Based Table Extraction

AI agent for security teams: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge base, OpenAI/Ollama. Risks, compliance gaps, remediations. MIT.

A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Docling4j brings the functionalities of Docling in document understanding to Java® projects

Document Filters is an SDK for applications like content indexing, e-discovery, data migration, and feeding data into AI/ML models by extracting data from unstructured sources. It gives the ability to perform deep inspection, data extraction, output manipulation, and conversion for virtually any type of document, in any programming language.

Applicant Tracking System (ATS): A powerful platform leveraging generative AI and soft-match algorithms to analyze resumes against job descriptions. Built with React and Node.js, it streamlines hiring insights. Future plans include expanding to investor pitches and other structured documents.

Official implementation of our ECCVW paper "μgat: Improving Single-Page Document Parsing by Providing Multi-Page Context"

Tool for converting First National Bank (FNB) bank statement PDFs into useful structured data

Transform your documents into intelligent conversations. This open-source RAG chatbot combines semantic search with fine-tuned language models (LLaMA, Qwen2.5VL-3B) to deliver accurate, context-aware responses from your own knowledge base. Join our community!

Document Intelligence Platform — Extract, refine, and query documents with vision LLMs and config-driven RAG.

The metadata and text content extractor for almost every file type.

Python scripts to parse and structure invoice data from PDFs using OpenAI, Anthropic and Invofox APIs

LangParse is a universal document parsing and text chunking engine for LLM or Agent applications — Documents In, Knowledge Out.

This is a collection of various document parsers and hands-on to construct structured data for your RAG applications.

Smart OCR application built with Tesseract and Streamlit that extracts structured data from Inputs

A high-performance Python library for extracting structured content from PDF documents with layout-aware text extraction. pdf_to_json preserves document structure including headings (H1-H6) and body text, outputting clean JSON format.

LeapRAG is an open-source platform that integrates advanced RAG technology with Google’s A2A protocol, enabling users to build context-aware, data-driven agents. These agents are automatically A2A-compliant and can be discovered and used by any compatible client without extra development.