Document processing & OCR
1,074 agents · most starred first
Document processing & OCR, page 4 of 11
微软markitdown免安装一键启动整合包,PDF/WORD/PPT/HTML转Markdown
Hierarchical document chunking for RAG. Structure in, structure out.
Cutting-edge tool designed to intelligently segment text documents into optimally-sized chunks
Demo of a Fiber Cut Response Agent using Azure Content Understanding to process multi-modal field documents (PDFs, photos, diagrams, audio) and reason with Foundry models for incident triage. From Microsoft Build 2026.
LLM document ingestion pipeline with AI readiness scoring and structured Markdown/JSON output.
Book to Skill Github: Turn Any PDF Into Local AI Skill (No Token Limits!) - Turn any PDF or book into structured local AI Agent Skills using Hermes AIAgent and Ollama.
Portable Agent Skill for converting PDF to editable Word/DOCX while preserving layout. Works with Codex, Claude Code, other AI agents, and local CLI.
Split PDF textbooks into organized chapter files using AI-powered bookmark and TOC analysis. Supports OpenAI-compatible APIs.
Self-contained demos for the Nutrient Data Extraction API — grounded extraction with per-field citations, bounding boxes, and confidence scores.
Recover broken Arabic from native PDFs with evidence-based diagnosis, conservative repair, BiDi/order recovery, artifact cleanup, and multi-column RTL layout. Zero-dependency core. OCR not claimed.
Batch-convert Word/Excel/PowerPoint/PDF/EPUB/RTF/CSV to clean Markdown before the agent reads them. Wrapper over firecrawl/anydoc. | Пакетная конвертация Word, Excel, PowerPoint, PDF, EPUB, RTF и CSV в чистый Markdown до того, как документ прочитает ИИ-агент.
Simple Streamlit application that parses the data from Invoice images and returns it in JSON format
An AI-powered tool by DeepSeek API for summarizing documents, supporting PDFs, DOCX, images, etc. Features OCR for scanned files, bilingual (Chinese/English) output, multiple summary types, smart caching, and real-time progress tracking, with easy setup via Python.
This project is a user-friendly web application that allows you to upload PDFs, DOCX files, or images, automatically extracts text using advanced OCR techniques, and generates concise summaries using Google Gemini 2.5 Flash via LangChain. Built with Streamlit, it provides a seamless experience for document understanding and quick insight extraction
“Change formats. Extract insights. All with AI.”
Universal documentation extraction tool
Reference implementation of a Databricks-native document intelligence agent with cited answers.
Arabic Chat with PDF is a user-friendly application that lets you interact with Arabic PDF documents. Powered by advanced language models, OCR, and vector search, it allows you to upload PDFs, ask questions, and receive accurate Arabic responses 🚀
CLI that helps with docs splitting, embedding and exposing them in a seamless manner
Intelligent document OCR and structured extraction. Turn PDFs and images into typed JSON with zero vendor lock-in.
Pure-Rust document parsing for RAG/agents: PDF · DOCX · HTML · more → byte-deterministic, page+bbox-citable chunks. One binary, zero deps.
Deterministic PDF/DOCX parser for RAG/LLMs — Rust core with byte-identical Python/Node/WASM bindings
gradio region:us
Convert .eml and .mbox email, including Gmail Takeout, to Markdown with YAML front matter
PDF Parser (EXE available) is a fast desktop application for extracting text, images, drawings, and metadata from PDF documents. It supports batch processing, table extractions, hyphenation repair, and exports visual content for external AI-based description, with results reintegrated into the extracted text.
Multimodal OCR table grid & merged-cell reconstruction into Markdown (MinerU / Marker)
Accio Work-inspired GenPark Skill
A Streamlit document Q&A assistant for PDF, DOCX and TXT files, with OCR for scanned pages and TF-IDF retrieval over a FAISS index.
This repository contains the code for the information extraction app that uses langchain to extract a structured output from unstructured data for a particular schema.
How to process semi-structured data using Large Language Models (LLMs) on Amazon Bedrock.
Typescript client for the markdown2pdf.ai service. ⚡ Markdown to PDF conversion, for agents. ⚡ Agents speak Markdown. Humans prefer PDF. Bridge the gap for the final stage of your agentic workflow. No sign-ups, no credit cards, just sats for bytes.
HanNLP Client for Node.js
A collection of NLP Applications built using FastAPI, HTML, CSS, and Streamlit.
Transform your Dialogflow NLP model to a NLP.js model
Glaucias is an open source platform focused on RAG. The purpose of the platform is to extract the structure of documents and make it as feasible as possible for RAG by identifying the references in the text(implicit and explicit)
A plugin dveloped for ChesireCat AI to detect complex math formulas from any image and reproduce them in Latex syntax
A service for automating document ingestion for Semantic Kernel's KernelMemory service
extractor is an HTTP service used to convert PDF, Markdown, HTML, Docx, Xlsx, CSV and other files into plain text output. It is used in RAG implementation to read external documents for vectorization.
Python client for the markdown2pdf.ai service. ⚡ Markdown to PDF conversion, for agents. ⚡ Agents speak Markdown. Humans prefer PDF. Bridge the gap for the final stage of your agentic workflow. No sign-ups, no credit cards, just sats for bytes.
RAG workflow-friendly enhancement of Marker that converts PDFs into a single-file markdown equivalents. It handles GPU and PyTorch configuration, document splitting and chunking, image BASE64 embedding, LLM post-processing and cleanup, and consolidation of output.
SmartDocQ is an AI-powered assistant designed to help users intelligently search, analyze, and extract insights from documents. Powered by Google Gemini, it uses natural language to automate document processing for learning, research, and professional document management.
Parse any file to Markdown and JSON, anyparse, document-parsing, document-understanding, ocr, vlm, multimodal, image, pdf, markdown, docx, pptx, xlsx, tsv, csv, txt, md, rst, htm, html, xhtml, shtml, png, jpeg, jpg, webp, epub, ipynb, eml, etc.
Organize Simple API — turns a receipt, invoice or card statement PDF into structured JSON. NestJS, Prisma, LangChain, Poppler.
Open-source API to convert URLs and documents into PDFs, screenshots, Markdown, and structured data.
An integration package connecting pdf-inspector to LangChain
Convert documents once. Give agents only what they need — PDFs and Office files to clean Markdown, chunks and local search.
Channel layer that turns any content needing IDP — scans, photos, image PDFs, Office files — into trustworthy structured data (OCR + Markdown + metadata + optional field extraction), exposed via REST / EventBus / MCP. Built on ABP.
Open, independent benchmark on document parsing APIs and frontier VLMs for AI agents and RAG: does a struck-out clause in a redlined contract PDF survive the parse? Open source code + open data. LlamaParse, Reducto, Datalab, Extend, Pulse, Mistral OCR, GPT-6 Astra, Claude Fable 5.1.
Intelligent PDF Summarizer and Inquiry Companion
Turn PDF into Notes in seconds📝
PDF reader for LLM agents
AI pretends to be paper/textbook author, you can ask it questions about the paper as a whole, specific parts of it right in the PDF viewing app (e.g. Apple Preview) using annotations and see the replies there.
Universal document-to-markdown and section splitter for HTML, URLs, and PDFs.
AutoML/Unstructured Data Processing for RAG and LLM Dataset Creation. Current Database Options are: Qdrant or Marqo DB.
📄 Extract BibTeX entries from PDFs automatically, generating a complete bibliography without manual input or reliance on external APIs.
DoubleXTouch is a lightweight AI-powered desktop PDF assistant for students and small offices. It focuses on fast PDF organization, smart summaries, and essential editing—without the bloat of traditional PDF editors.
AI-powered Mongoose plugin for intelligent document processing
High-fidelity PDF/DOCX/PPTX to Markdown conversion with multi-stage QC, image extraction, and Claude Code integration.
Go rewrite of PageIndex for generating a hierarchical, reasoning-friendly tree index from PDF documents
Provider-neutral multimodal OCR CLI and MCP server(+ web app) for images, PDFs, URLs, structured extraction, and agentic workflows—Gemini, Kimi, Muse, OpenRouter, and Cloudflare AI Gateway.
Chunking that understands who is speaking. Parse any transcript, chunk it without ever splitting a speaker turn. Zero dependencies.
Agent-first OCR CLI and MCP server for images, PDFs, URLs, structured data, and resumable extraction with Gemini, Kimi, Muse, OpenRouter, and compatible APIs.
Qwen3-VL-30B → 2B distillation for document parsing; the production parser in RCPS (EMNLP 2026).
Professional Windows desktop app that converts JSON/Text to TOON format, optimizing LLM token usage by 15-30% while maintaining 100% data fidelity.
A TypeScript library for DOM to Snapshot conversion - compress HTML documents for efficient processing by LLMs.
A python package for extracting composition-property data from scientific articles for building databases
Intelligent Document Understanding Machine as an API Service
A Python script that generates a descriptive name for a file based on its content using AI.
The PDF Chatbot project uses advanced NLP models and Unstructured.io for parsing complex PDFs, enabling streamlined extraction and querying of information, including tables, graphs, and images, through a user-friendly interface.
Convert, extract, and process documents from the command line
Watcharapon Weeraborirak Computer Engineering AI Developer (Machine Learning)
Solving PDF accessibility with OpenAI
annotate by GAI, use Semantic Kernel, a blazor site.
An Open-Source Persian Language Techs Toolkit with Python
"Docs in a Row" is an automated script designed to handle image data extraction, correction, categorization, and storage. It utilizes a variety of technologies including OpenAI, Google Cloud Vision, pytesseract, and PIL to extract and correct text from images, categorize the content, and store useful metadata.
Extract structured data from residential lease PDFs using OCR and AI. Outputs tenant info, rent, dates, and terms as clean CSV/Excel.
Exchange collections of files with Large Language Models.
SumMedia is a powerful Python tool used for extracting and parsing newspaper articles
Documentation Build Tool - Generate YAML documentation for dbt models with optional AI assistance. Built with Streamlit for an intuitive and familiar web interface.
file2md is a versatile tool for converting multiple file formats to Markdown.
A fully offline NLP pipeline for extracting, chunking, embedding, querying, summarizing, and translating research documents using local LLMs. Inspired by the fictional mystery of Dr. X, the system supports multi-format files, local RAG-based Q&A, Arabic translation, and ROUGE-based summarization — all without cloud dependencies.
Extract DOCX template styles into JSON. Regenerate pixel-perfect branded documents from Markdown. CLI + AI agent ready.
Digital document management with AI 🤖🧠 on Synology NAS 🧾
Turn your PDF collection into clean text your AI can actually read. Mac app.
A self-hosted, privacy-first document ingestion service that captures, processes, extracts metadata, and archives documents to Paperless-ngx.
The industry's first "Open Source OCR Arena," a free, no-login utility for one-click benchmarking of 7 top-tier models (Marker, MinerU, MonkeyOCR, Docling, Dolphin, OCRFlux, PP-StructureV3) on your PDF/image files, specializing in PDF-to-Markdown conversion.
Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.
给历史研究者的中文文献 OCR 校对与阅读 pipeline · Agent-native OCR, collation & reading workflow for historical Chinese scholarship — works with Claude Code, Codex, Gemini CLI, Cursor & Hermes agents
Rust-native, local-first, auditable structured extraction with schemas, benchmarks, persistence, and operational reliability
.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.
File/Folder Organizer Skill. Easily Sort and Rename based on Entire Contents!
Extract and distill knowledge from a folder of PDF books into AI-optimized markdown (Docling + a pluggable LLM CLI; single-pass, map-reduce, and outline-driven per-chapter modes).
a powerful Markdown chunking tool that understands document structure. Unlike naive token splitters, it protects atomic elements (code, math, tables), merges by semantic affinity, and scores chunk quality — ready for RAG and fine-tuning workflows.
High-fidelity Word (.docx) to Markdown converter. Preserves tables (vMerge), footnotes, field codes, bibliography, lists, and images where Pandoc and others fall short.
AI-powered mobile app for converting handwritten notes and documents into editable digital text - built to boost productivity for students and educators.
A React Native app that allows users to extract text from images, PDFs, and audio using AI-powered OCR and transcription technology. The app features a queue-based job processing system with automatic polling, markdown rendering for rich text display, user authentication, camera functionality, PDF document Q&A with multiple AI model
Self-hosted document intelligence for RAG — parse, classify, split, and extract from PDF/DOCX/PPTX and images: searchable, cited, retrieval-ready chunks and schema-driven extraction
Docling RAG ingestion pipeline on Backblaze B2 — parse PDFs, DOCX, PPTX and HTML into clean Markdown and token-aware chunks written back to B2 over the S3-compatible API. Next.js + FastAPI, on-device models, no second API key.