Document processing & OCR
1,074 agents · most starred first
Document processing & OCR, page 2 of 11
Transform and optimize your markdown documentation for Large Language Models (LLMs) and RAG systems. Generate llms.txt automatically.
Get your documents ready for gen AI, in pure Go. A Go alternative to anydoc & Docling — 纯 Go 实现的文档解析库:PDF/Word/PPT/Excel/HTML/Markdown/EML/图片等 12 种格式统一解析为 Docling 协议(Markdown/JSON/content_list),表格还原·多栏阅读顺序·图表数据回填,OCR 收敛为一个大模型接口,单二进制零依赖,快 34~153 倍。联犀物联网平台知识库同款引擎。
🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐
Hugging Face recipes: run OCR, transcription, classification, embeddings and more over a Hub dataset in one command, locally or on HF Jobs. Built for people and coding agents.
Ultra lightweight API server to convert files (.pdf, .docx, .xlsx) into formatted markdown.
Self-contained UV scripts for data & ML tasks. Includes OCR, vision, audio & more. Run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.
DeepParseX 是一个强大的多模态文档解析与知识管理平台,支持 PDF、Word、Excel、PPT、图片、视频、音频 等多种文件格式的智能解析,自动提取关键信息,并构建 检索增强生成(RAG) 和 知识图谱(Knowledge Graph) 系统,实现结构化数据的智能检索与推理。
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
:surfer: 依存关系分析,NLP,自然语言处理
Schema-first structured extraction from LLMs — validated JSON from one call or a 150-page document.
Paperless-ngx with local or cloud LLMs: titles, correspondents, types, tags, custom fields and vision OCR, all set up in a web UI
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).
A Rust library designed to facilitate the conversion of various document formats into markdown text.
Recognize, transcribe and typeset math formulas locally: natural language / image / broken TeX → valid LaTeX with preview
Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.
Turn a video — or an animated GIF, APNG, or WebP — into a timeline of still frames so an LLM can "watch" it as a series of images.
AI Document Assistant for PSPDFKit Demo showcases how to interact with PDFs using natural language commands powered by AI, integrated with PSPDFKit for Web.
Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants
A comprehensive toolkit that provides building blocks for LLM-based named entity recognition, attribute extraction, and relation extraction pipelines.
PDF Parsing Tool: GOT's vLLM acceleration implementation, MinerU for layout recognition, and GOT for table formula parsing.
A tool for fast and accurate summarizing of variant calling format (VCF) files
Turn any document into clean, AI-ready Markdown — locally on your machine. Desktop app for Windows, macOS & Linux powered by MarkItDown, Docling, GLM-OCR and Markit.
A tool to OCR PDFs using gen-AI models
gradio region:us
Extract structured data from local or remote LLM models
The easiest way to get structured data from unstructured text or images using LLMs. No prompt engineering, no chat history, just a simple API to extract structured JSON from text or images.
Podlite markup language: parser, CLI (convert, lint, query, test), and MCP server for AI agents
3DCF / doc2dataset: token-efficient document layer with NumGuard numeric integrity and multi-framework exports for RAG & fine-tuning.
Convert your PDFs to custom JSON data using AI.
A data discovery and manipulation toolset for unstructured data
This is a documents loader. (文档解析加载器,rag文档解析,rag知识库构建)
Part of the KDAN ecosystem, DocSlight offers document parsing, OCR, and data extraction that turn PDFs, scans, images, and Office files into structured outputs for RAG pipelines, AI agents, and enterprise document automation.
AI-powered Python library that converts any document (PDF, Word, Excel, PowerPoint, HTML) to clean Markdown while preserving complex tables and layouts using AI-Powered OCR technology.
Part of the KDAN ecosystem, DocSlight offers document parsing, OCR, and data extraction that turn PDFs, scans, images, and Office files into structured outputs for RAG pipelines, AI agents, and enterprise document automation.
Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON
PDF, Parsing, Agent, IDP, Document, OCR, Python, Layout
Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.
This tool has been deprecated. Use Agentic Document Extraction instead.
Sharepoint to text: A python-libraries which extracts the plain text from legacy and modern office documents and PDF. An enabling library for the agentic age which is driven more by Sharepoint content that you would think ...
Convert Confluence MIME exports (.doc) to clean Markdown
Sync reMarkable to PDF and MarkDown via either USB or Wifi. Backup your device and let your AI agents reason over the content.
Sample scripts to use with Agentic Document Extraction (ADE).
Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.
📝 An AI-powered document analysis app that turns long, complex documents into summaries, key insights, analytics, and contextual conversations, helping people understand and work with information in seconds instead of hours.
AI-powered post-consume script for Paperless NGX that generates high-quality, language-aware document titles using OpenAI, Claude or local Ollama models.
gradio region:us
The developper starter pack for document processing
Fullbleed PDF Engine - deterministic Python/Rust document generation for reports, invoices, accessible/print-ready PDF, and compiled VDP.
Workspace for documents with AI
Connect Claude to your Zotero library — Zotero plugin that mirrors collections as agent-readable folders with Markdown, BibTeX, and AI reviews.
Chew is a Go library for processing various content types into markdown/plaintext.
🧠✂️ SemanticSlicer — A smart text chunker for LLM-ready documents.
Local-first OCR-VLM multimodal document retrieval and independent evaluation prototype.
Privacy-conscious Python CLI and library for analyzing TXT, Markdown, and PDF documents with OpenAI's Responses API.
A very fast, feature-packed, AI-first Markdown (CommonMark/GFM) gem for Ruby, based on pulldown-cmark (Rust).
Make your .docx self-describing for AI agents. One prompt bootstraps the document — the agent maps it, contracts it, navigates it.
Convert HTML to Markdown with Elixir
语雀文档批量导出到本地。所见即可下载。支持收藏文件导出。幕布文档批量导出到本地。支持Markdown格式,方便迁移AI笔记、obsidian等。
Enterprise-ready Document Analysis with Large Language Models
Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files
Using LangExtract and Gemma 3 for structured information extraction from unstructured text in insurance polices
Open-source PDF-to-Markdown post-processor with footnotes, LaTeX normalization, figure links, and YAML metadata. Supports Marker, MinerU, PyMuPDF, and Docling. Includes a self-hosted web UI.
A high-accuracy, multilingual rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate sentence segmentation.
Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with precision.
MinerU Training Camp course materials and tutorials
AI-powered chatbot with GPT-3.5 Turbo model for document analysis, modification, and image insertion. Backend uses Django REST API with MySQL and Firestore, and TensorFlow for unsupervised learning. Frontend is built with React, Vite, and JavaScript, featuring responsive design and two color modes.
Convert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.
Framework-neutral DOCX engine with React/Vue editors, Nuxt integration, and agent tooling
Document extraction and validation for logistics companies.
Structurizer is a web application that helps you extract structured data from PDF files with Large Language Models!
This is a complete website in which you can chat with pdf, extract meta data, text, links, image, and lot more . Check my blog for more details: https://medium.com/@amit.2503719/allaboutpdf-tool-for-data-extraction-and-talking-to-pdf-using-chatpdf-feature-f2daea15a59c
실제 한국어 문서 데이터셋을 기반으로 만든 3가지 VLM 벤치마크 데이터셋
Pure Go text extraction library with fluent API, layout analysis, and RAG-ready chunking with support for pdf, html, odt, epub, and MS Office documents
Search electronic parts, download datasheets, and extract structured data for LLM agents — Mouser & DigiKey CLI in Rust
This sample demonstrates how to use Document Intelligence's Layout model to convert a PDF document, such as invoices, into Markdown, then use GPT-3.5 Turbo to extract structured JSON data using the Azure OpenAI Service.
Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.
An intelligent document processing solution using Azure Content Understanding and OpenAI to extract data from documents and enable natural language querying with citations.
Apple-native iOS/macOS app for document intelligence, OCR, cited answers, and source-backed retrieval over PDFs, scans, and user-controlled files.
A Python tool for splitting large Markdown files into smaller sections based on a specified token limit. This is particularly useful for processing large Markdown files with GPT models, as it allows the models to handle the data in manageable chunks.
Code for the OpenCV demo of a recipe transcription OCR agent.
Ein Python-Script zum automatischen Organisieren von PDF-Dateien. Das Tool nutzt KI (OpenAI, Anthropic oder Ollama lokal) zum Umbenennen, Sortieren und Aufsplitten von PDF-Stapeln in Einzeldokumente. Zusätzlich findet es Duplikate, validiert Dateien und konvertiert Bilder bzw. gescannte PDFs per OCR in durchsuchbare PDFs.
Advanced receipt OCR and analysis using PaddleOCR, GPT-3.5-turbo, Plotly, and Gradio for interactive visualizations.
A Node.js CLI and library that uses OpenAI, Ollama, ZhipuAI, Google Gemini or Coze to write AI-generated image descriptions and/or tags to EXIF metadata by its content.
Find and remove duplicate documents in paperless-ngx. MinHash/LSH fuzzy matching catches near-duplicates that exact hashing misses, with optional AI metadata suggestions.
A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.
CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.
A tool that converts scientific PDFs into plain text for your LLM-related needs, such as building RAGs or agents for academic knowledge. It was developed in collaboration with the LlamaIndex team.
Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, source maps, and automatic document splitting.
A browser extension to automatically extract and batch-copy transcripts from Udemy videos. Perfect for students and learners who use note-taking apps like NotebookLM.
Ironclad-OCR is an asynchronous invoice ingestion and extraction service built for vendor PDFs that do not share a single stable layout.
Interactive demo of a SOTA agentic OCR document approval flow
Convert your ChatGPT export into readable, searchable files. Built for everyone who deserved better.
Async Docling sidecar that turns PDFs and office documents into Markdown, text, structured blocks, chunks, and extracted images for RAG. Python · FastAPI.
Repair invalid JSON documents in C#
A PMC ID in. Clean, loss-aware article JSON out. Parse PubMed Central and JATS XML for biomedical AI, RAG, search, and literature pipelines.
An integration package connecting PyMuPDF4LLM to LangChain
LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.
Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results fall short
Datasets, case studies and benchmarks for extracting structured information from PDFs, HTML files or images, created by the Parsee.ai team. Datasets also on Hugging Face: https://huggingface.co/parsee-ai
Cutting-edge tool that unlocks the full potential of semantic chunking