Document Processing Open-Source Projects

Showing 21 indexable projects from the current snapshot.

• iOfficeAI/OfficeCLI

  A single, dependency-free CLI binary that lets AI agents and developers create, read, modify, and render Microsoft Office documents (Word, Excel, PowerPoint) without needing a local Office installation. It ships with a built-in HTML render…

• infiniflow/ragflow

  RAGFlow provides a retrieval-augmented generation workflow focused on deep document understanding, processing complex unstructured formats to extract knowledge with traceable citations. It requires external LLM and embedding services to op…

• PaddlePaddle/PaddleOCR

  PaddleOCR converts PDF documents, images, and Office files into structured formats including JSON, Markdown, and DOCX. The project features PaddleOCR-VL-1.6, a 0.9B parameter vision-language model, alongside PP-StructureV3 layout conversio…

• Unstructured-IO/unstructured

  This project provides open-source components for ingesting and pre-processing unstructured data into structured outputs for large language models. It offers modular document partitioning across multiple file types and includes a Model Cont…

• opendatalab/MinerU

  MinerU converts PDF, image, DOCX, PPTX, and XLSX files into Markdown and JSON for retrieval and extraction workflows. It runs locally across multiple backends via CLI or WebUI and requires at least 16GB of RAM, with optional GPU accelerati…

• tesseract-ocr/tesseract

  Tesseract is an open source OCR engine that converts images of text into machine-readable text using neural net (LSTM) line recognition and legacy character pattern matching. It supports over 100 languages and multiple output formats inclu…

• docling-project/docling

  docling-project/docling parses diverse document formats—including PDF, DOCX, PPTX, XLSX, HTML, images, and audio—and prepares them for generative AI applications. It provides advanced PDF understanding, a unified document representation fo…

• paperless-ngx/paperless-ngx

  Paperless-ngx transforms physical and digital documents into a searchable, indexed online archive. It is a community-supported document management system that runs locally and uses OCR to organize records.

• google/langextract

  This Python library extracts structured information from unstructured text documents such as clinical notes and reports. It provides source grounding for every extraction, processes large documents using chunking and parallel processing, a…

• PDFMathTranslate/PDFMathTranslate

  This project translates scientific PDF documents while preserving formulas, charts, tables of contents, and annotations. Users can run it locally via pip or binary, use a hosted demo, or interact through a web GUI, CLI, HTTP API, or MCP se…

• VectifyAI/PageIndex

  PageIndex is a vectorless, reasoning-based RAG system that uses a hierarchical tree index and LLM reasoning to provide traceable and context-aware retrieval over long documents. It is designed for developers who need to avoid chunking and…

• explosion/spaCy

  A Python library providing Natural Language Processing capabilities including tagging, parsing, named entity recognition, and text classification. It includes pretrained pipelines for over 70 languages and a training system designed for re…

• JaidedAI/EasyOCR

  EasyOCR is a Python library that provides ready-to-use optical character recognition for more than 80 languages. It accepts multiple image formats and returns structured text with bounding boxes, configurable via a Python API or command-li…

• HKUDS/RAG-Anything

  RAG-Anything is a Python library that processes and queries multimodal document content, combining vector similarity search and graph traversal to handle text, images, tables, and equations within a single framework.

• microsoft/unilm

  unilm is an open-source project that ships a large collection of pre-trained foundation models, architectures, and tools for diverse AI tasks spanning NLP, vision, speech, and document AI. It addresses the challenge of scaling self-supervi…

• DrewThomasson/ebook2audiobook

  This tool converts e-book files into audiobooks using text-to-speech technology across 1158 languages and dialects. It supports multiple TTS engines, optional voice cloning, and can run on low-resource hardware with a minimum of 2 GB RAM.

• allenai/olmocr

  olmocr converts PDF, PNG, and JPEG documents into clean Markdown text while preserving equations, tables, and reading order. It processes documents at a cost of less than $200 USD per million pages.

• pot-app/pot-desktop

  A cross-platform desktop application providing text translation, OCR, and text-to-speech through a graphical interface or local HTTP API. It aggregates built-in and external services including OpenAI, DeepL, Ollama, and Tesseract, and supp…

• AsyncFuncAI/deepwiki-open

  Automatically generates interactive wikis with documentation and visual diagrams for GitHub, GitLab, or BitBucket repositories by analyzing code structure.

• lukas-blecher/LaTeX-OCR

  A learning-based system that converts images of math equations into LaTeX code using a ViT encoder with a ResNet backbone and a Transformer decoder. It runs locally via CLI, GUI, or Python library.

• nashsu/llm_wiki

  llm_wiki is a desktop application that uses an LLM to incrementally build and maintain a persistent, interlinked knowledge wiki from your documents. It compiles knowledge into an organized structure rather than retrieving and answering fro…