Data, search & knowledge

Document processing & OCR

1,074 agents · most starred first

Document processing & OCR, page 3 of 11

axetract★ 23

Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.

docray★ 23

X-ray for documents: lossless PDF & PPTX extraction to JSON with bounding boxes, fonts, and colors — CLI, HTTP API, and an in-browser playground. Rust + PDFium.

OmniParse★ 22

Transform unstructured documents into actionable, structured data with enterprise-grade precision and reliability, ready for large-scale production environments.

quarkus-docling★ 22

Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem

FlipScan★ 22

Turn a phone flip-through video, photos, or a PDF of a book into a clean, proofread EPUB/PDF/Markdown — local vision-LLM digitization with a web GUI you can drive from your phone.

qq-bak-chat-history-export★ 22

QQ bak文件聊天记录解码导出工具,将 QQ / NTQQ 聊天记录转换为 Agent 可读的 TXT、JSON、CSV。

stateful-ai-agent★ 21

Stateful AI Agent for Knowledge Extraction

Markdownify★ 21

Convert documents, images to high-quality Markdown using Vision LLMs. Built for RAG ingestion pipelines.

rag-document-viewer★ 21

RAG Document Viewer is an open-source library that generates high-fidelity file previews for seamless integration into your applications. It provides desktop-level file viewing capabilities for a wide range of document formats

dify-markdown-chunker★ 21

Advanced Markdown text chunker tool plugin for Dify RAG / knowledge bases

ComProScanner★ 21

A python package for extracting composition-property data from scientific articles for building databases

tender-extract★ 21

面向中文标书(MD)的混合抽取:规则/NER 优先,仅将低置信或冲突片段交给 LLM——可审计、低成本、高效率。Hybrid extraction for Chinese tender docs (MD): rules/NER first, LLM only for low-confidence/conflicts—auditable, lower cost, higher efficiency.

kreuzberg-lts★ 21

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

paperless-local-ai★ 21

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

rasgapdf★ 21

Blazing-fast 2D Spatial PDF Parser in Pure Rust (Python, Node.js, Go, C#). Extract exact [x0, y0, x1, y1] bounding boxes, text blocks, tables, images & vector paths in ~3-8ms/page for RAG & LLMs.

InsightGPT★ 20

InsightGPT is a project utilizing the power of Azure OpenAI Service to identify patterns and gain new insights from unstructured text.

PodcastNER-GPTJ★ 20

gradio region:us

wechat-db-decrypt-macos★ 20

Decrypt WeChat databases on macOS by extracting encryption keys to access and export chat records with support for searching and AI query integration.

vindex★ 20

Open-source video compiler that turns videos into structured knowledge for AI agents.

rdocdump★ 19

rdocdump: Dump ‘R’ Package Source, Documentation, and Vignettes into One File

nutrient-agent-skill★ 19

Universal Agent Skill for document processing with Nutrient DWS API — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents

human-interface-markdown★ 19

Apple Human Interface Guidelines archive (1980-2014) - 35 documents optimized for LLM consumption and human exploration. Spanning Lisa, Mac, NeXT, Newton, Aqua, and iOS eras.

kintara★ 19

Self-hosted document library and PWA reader for PDF, Markdown, and text files, with NAS folder watching, full-text search, sharing, annotations, and optional AI tools.

DocSense★ 18

An interactive web application for comparing PDF documents using cosine similarity scans and a chatbot interface to explore and interact with PDF content.

figure-extractor★ 18

Flask-based service using PDFFigures 2.0 to extract figures and tables from scholarly PDFs. Features REST API, CLI, Docker support, and JSON metadata output (~1.5s/page processing). Designed for document processing and RAG pipelines.

sample-badgers★ 18

Vision-aware document analysis on Amazon Bedrock AgentCore. BADGERS routes PDFs, Office files, images, and handwritten records through selective OCR and AI specialists to produce auditable, accessibility-oriented structured outputs.

GPT-Table★ 17

GPT Table Semantic Parsing with complex & non-intuitive structure.

patient-intake-extraction★ 17

Patient Intake Form Extraction using llm

ppu-pdf★ 17

Pdf utilities for text extraction in digital and convert scanned pdf into canvas.

construction-spec-assistant★ 17

This is an agentic AI system designed to help Construction Architects review construction documents and identify inconsistencies between original specifications/drawings and Contractor Submittals.

AI-Paperless-Organizer★ 17

AI-powered companion for Paperless-ngx: auto-classify documents, merge duplicate tags & correspondents, re-OCR with local vision models, chat with your archive (RAG), import from cloud drives and detect duplicates. Runs fully local with Ollama.

PageBridge★ 17

Native macOS/WIn PDF reading, translation, annotations and document assistant with OpenAlex and Sci-Hub search.

paperless-iq★ 16

Open-source AI add-on for Paperless-NGX: automatic metadata & tagging, RAG document search, and automation with Ollama, Bedrock, Anthropic, and OpenAI

dwg2png★ 16

Pure-Rust DWG -> multipage PNG renderer + lossless position-referenced text layer & metadata indexer for RAG/VLM ingestion of CAD drawings

gemini-ocr★ 15

PDF Screenshot OCR Analysis with Google Gemini Pro

book-capture★ 15

Claude Code plugin for capturing books from Kindle, Apple Books, or PDF — screenshot, OCR via macOS Vision + Claude agents, and structured Obsidian Markdown generation. 4 capture sources, 7 commands, 2 AI agents.

elephant-php★ 15

Convert .docx to Markdown or semantic HTML — no external dependencies.

dsh-docs★ 15

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件,支持 PDF、Office、图片与离线 OCR

rs-docmanager★ 14

R's AI DocManger: An AI Documenet Management System

NaiPosTagger★ 14

A part of speech tagger written in PHP.

structsense★ 14

A multi-agent system for extracting structured information from unstructured text and documents. It orchestrates a configurable pipeline of AI agents — extractor → alignment → judge → human feedback — each driven by a single YAML config file.

docker-docling★ 14

Docker image for a self-hosted Docling document parsing server. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/JSON. Powered by IBM Docling. Features sync/async conversion, chunking for RAG, NVIDIA GPU (CUDA) acceleration, optional web UI, offline mode, and persistent model cache. Multi-arch: amd64, arm64.

mineru★ 14

让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行! 本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码编译与部署方案,解析质量与速度对标 NVIDIA 旗舰显卡。

Document-Intelligence★ 14

Developed a Document Intelligence platform that automates document processing using OCR, NLP, and AI to extract, classify, and validate structured information from PDFs, invoices, forms, and scanned documents with high accuracy.

parsecrate★ 14

ParseCrate: self-hosted document processing API powered by Docling and docling-serve. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/JSON. Sync/async conversion, RAG chunking, optional web UI, offline mode with cached models, and persistent model caching. Docker deployment on CPU (amd64/arm64) or NVIDIA GPU (CUDA, amd64).

semantic-chunker-langchain★ 13

Token-aware, LangChain-compatible semantic chunker with PDF, markdown, and layout support

MCQ_GENERATOR★ 13

The "MCQ Generator with Streamlit" web app utilizes OpenAI's language models to create multiple-choice questions (MCQs) from uploaded PDF or text files. Users can customize question parameters like quantity, subject, and tone. The app offers real-time complexity feedback and presents MCQs in an easy-to-read tabular format.

DataSpeakGPT★ 13

Read files and images and retrieve data for LLM

Document-Intelligence★ 13

Developed a Document Intelligence platform that automates document processing using OCR, NLP, and AI to extract, classify, and validate structured information from PDFs, invoices, forms, and scanned documents with high accuracy.

job_extractor_template★ 12

Template for an AI application that extracts the job information from a job description using openAI functions and langchain

clearedge★ 12

Build a RAG preprocessing pipeline

ragtitles★ 12

Optimize Subtitles for RAG Ingestion

pgedge-docloader★ 12

A tool for converting HTML and RST docs into Markdown, and loading them into PostgreSQL.

InSight-doc★ 12

[EMNLP'26] Agentic Visual Perception for Long-Document Understanding

aTUNApy★ 12

Automatic Text-fishing, Unification, and Normalization Application in Python (aTUNApy)

structx★ 11

Type-safe structured data extraction from text using LLMs.

docsifer★ 11

Docsifer is a powerful tool for converting various data formats into Markdown for applications such as indexing, text analysis, and more. It supports PDF, PowerPoint, Word, Excel, Images, Audio, HTML, and other text-based formats, and leverages LLMs to enhance performance.

to-markdown★ 11

🔄 A versatile utility library for converting various file formats to Markdown

cat-llm★ 11

Classify, extract, and summarize open-ended text (survey responses, social media, academic papers, political text, web content) at scale with LLMs. Python, R, and Stata.

supermarkdown★ 10

High-performance HTML to Markdown converter with full GitHub Flavored Markdown support. Written in Rust, available for Node.js and as a native Rust crate.

PrivyDoc★ 10

A secure, on-device document analysis tool using Foundry Local & Microsoft Agent Framework

proj_textOpenAI★ 10

用于AI处理自然语言(非标准化数据)。调用OpenAi Api等进行自然语言处理,AI输出相应的内容。帮做dirty work

whatsapp-chat-viewer★ 10

Generate a WhatsApp-style HTML page from an exported chat, with support for images, videos, audio, PDFs, and optional audio transcription.

ai-pdf-autofiller★ 10

Automated PDF form filling with intelligent field mapping using AI-assisted semantic inference

decompose★ 10

The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

olga★ 10

Four formats. One engine. PDF, DOCX, XLSX, HTML → Markdown and typed JSON, 15–40× faster than equivalent-quality OSS. Rust core with strictly-typed Python bindings.

Pen2PDF★ 10

⚡ Pen2PDF Suite – an all-in-one 🚀 productivity platform ✨ with 🤖 AI-powered text extraction (PDF/Images → Markdown 📝), 📅 smart timetable management (CSV/Excel import 📊), ✅ todo lists with subtasks📈, 🧠 AI-generated notes library 📚 and 💬 Isabella AI assistant (OpenAI/Microsoft/llama/Mistral/LongCat/Gemini models 🔄)for context-aware help 🧩.

hbk-to-md★ 10

CLI converter from 1C .hbk help archives to Markdown vault with indexes and breadcrumbs

omnichunk★ 10

Structure-aware text chunking library for code, prose, and markup files. Intelligently splits files into context-rich chunks while preserving semantic boundaries. Supports 15+ programming languages, deterministic output, and zero external dependencies. Perfect for RAG systems, code analysis, and LLM context optimization.

OdinsList★ 10

Automated comic cataloging tool that identifies issues directly from cover images using a vision-language model, then cross-references results with the Grand Comics Database and the ComicVine API to generate structured, high-confidence collection data with minimal manual entry.

cv★ 10

The .cv open file format - spec, SDKs, viewer, CLI, server middleware

undocx★ 10

Extract clean, structured Markdown from DOCX for LLM and RAG contexts.

pdf-go★ 10

Pure Go PDF library for reading & writing PDF (Go 1.20+): xref & streams, catalog/pages, text extraction, PdfWriter merge & forms—stdlib-only at runtime, ISO 32000–oriented API.

slimsnap-schema★ 10

Open MIT JSON Schema 2020-12 spec for SlimSnap captures. Bounding boxes, OCR text, extracted colors, annotations with intent and target_ref.

DBtoMD★ 10

tool to make Databases easily readable by agents

Muku★ 10

Local-first Video-to-Markdown for Bilibili, YouTube, Douyin and audio. CLI, Web UI, Docker and AI Skill for searchable knowledge bases.

omcipcap★ 10

GPON/XGS-PON OMCI Semantic Analysis Framework for ITU-T G.988 protocols (ONT Management and Control Interface).

mineru-runpod★ 10

📄 Serverless MinerU 2.5 Pro PDF parser on RunPod. Scales to zero. PDF → Markdown + JSON.

llm-structured-extract★ 10

Reliable structured extraction from LLMs: Pydantic schemas, function/tool calling, ret/repair loop, JSON-schema validation and batch pipelines with cost tracking.

Journal-Utilities★ 10

Utilities and Documentation for creating contents for the Active Inference Journal

lexos★ 10

Event-driven AI document processing engine with offline RAG, summarization, speech transcription, SSE streaming, and self-hosted LLM inference.

EyeDataHub★ 10

Command-line tool for finding, inspecting, citing, and accessing 350+ ophthalmology datasets from official sources.

transcreve-ai★ 10

Multimodal video dossiers for agents: transcripts, frames, OCR, evidence, and RAG-ready knowledge.

fastdocparse★ 10

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

schematter★ 10

Validator for document-schema — JSON-Schema-style validation for markdown frontmatter and structure

AI-Paperless-Organizer★ 10

AI-powered companion for Paperless-ngx: auto-classify documents, merge duplicate tags & correspondents, re-OCR with local vision models, chat with your archive (RAG), import from cloud drives and detect duplicates. Runs fully local with Ollama.

PaperLab★ 10

Local-first PDF reader for researchers: notes anchored to the page, AI answers that cite it. Runs offline with Ollama.

Journal_Utilities★ 10

Utilities and Documentation for creating contents for the Active Inference Journal

im-looking-for★ 10

Find files by what's in them: photos, PDFs, docs, voice memos and video, on your own computer. EmbeddingGemma 2 + llama.cpp; CLI, app and MCP server for agents.

doc-compression-skill★ 10

Adaptive extractive text compression for AI agents. Shorten academic documents without paraphrasing, with traceable edits, semantic review and optional lightweight OCR.

complydoc★ 10

Get document loading right. Compare loaders, trace every step and evaluate what reaches your model.

pid-parser★ 10

Turn a P&ID drawing into data you can ask: SQL + graph for people and AI agents. Skill for coding agents and a LangChain Deep Agents version.

domq★ 10

A tiny, zero-dependency, never-panicking HTML parser with CSS selectors — for Rust, your shell, JavaScript (a ~58 KB gzipped WebAssembly module, ~80 KB with reader mode and extraction) and Python.

PDF2MD★ 10

Convert scans, PDFs, TIFFs and whole archives (ZIP/RAR/7z) to Markdown — and see where OCR may have lost text: missing pages, garbage, engine disagreement. Q&A over documents with citations.

markdown-regex★ 10

Set of constants that can help you to parse markdown content

chat_with_pdf_table★ 9

The contents of this repository showcase how to extract table data from a PDF file and preprocess it to facilitate word embedding. This preprocessing step enhances the readability of table data for language models and enables us to extract more contextual information from the tables.

MyColPali★ 9

The PyQt6 application using ColPali and OpenAI to show Efficient Document Retrieval with Vision Language Models

PDF-free-editor★ 9

AI powered free document analysis project including pdf free editor

cloudflare-journal★ 9
echomine★ 9

Library-first tool for parsing AI conversation exports with search, filtering, and markdown export

More in Data, search & knowledge