Open-source platform for extracting structured data from documents using AI.

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

Generic framework for historical document processing

⚡ Cloud-native, AI-powered, document processing pipelines on AWS.

A full-featured Document Layer for your application, providing the functionality of a flexible document management system, including storage, discovery, processing, and retrieval. Deploys directly into your Amazon Web Services Cloud. 🌟 Star to support our work!

An include filter for Pandoc

Retrieval of fully structured data made easy. Use LLMs or custom models. Specialized on PDFs and HTML files. Extensive support of tabular data extraction and multimodal queries.

A Python framework for multi-modal document understanding with Amazon Bedrock

Unofficial mirror of git://git.lyx.org/lyx.git (updates daily. not affiliated with lyx.org.)

Enhanced Document Understanding on AWS delivers an easy-to-use web application that ingests and analyzes documents, extracts content, identifies and redacts sensitive customer information, and creates search indexes from the analyzed data.

Semantic extraction from conference proceedings.

A comprehensive list of annotated training datasets classified by use case.

This library builds a graph-representation of the content of PDFs. The graph is then clustered, resulting page segments are classified and returned. Tables are retrieved formatted as a CSV.

An advanced distributed knowledge fabric for intelligent document processing, featuring multi-document agents, optimized query handling, and semantic understanding.

tokyo, a REST API, when given any type of document 📄, Identifies mime-type 🧐. Suggests extension 🦔. Alas Extracts text 💪.

Conversion of PDF documents to structured Markdown, optimized for Retrieval Augmented Generation (RAG) and other NLP tasks. Extract text, tables, and images with preserved formatting for enhanced information retrieval and processing.

A module for creating stopword lists for any language, based on a set of documents.

A Python command-line utility intended for automating some copyediting tasks in documents. It allows editing zipped, XML-based files (e.g. docx, odt, or epub), through XSLT stylesheets. Can be rather easily extended with your own custom xsl stylesheets.

Text line detection for Urdu OCR (UTRNet)