{"id":30236896,"url":"https://github.com/aidalinfo/extract-kit","last_synced_at":"2025-08-15T01:10:07.584Z","repository":{"id":309230893,"uuid":"1035560914","full_name":"aidalinfo/extract-kit","owner":"aidalinfo","description":"Powerful PDF data extraction library powered by AI vision models. Transform PDFs into structured, validated data using TypeScript, Zod, and AI providers like Scaleway and Ollama.","archived":false,"fork":false,"pushed_at":"2025-08-10T17:22:09.000Z","size":309,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-10T18:29:43.745Z","etag":null,"topics":["ai-sdk","document-processing","pdf","pdf-extraction","vision-llm"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aidalinfo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-08-10T16:54:11.000Z","updated_at":"2025-08-10T17:22:12.000Z","dependencies_parsed_at":"2025-08-10T18:39:56.681Z","dependency_job_id":null,"html_url":"https://github.com/aidalinfo/extract-kit","commit_stats":null,"previous_names":["aidalinfo/extract-kit"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/aidalinfo/extract-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidalinfo%2Fextract-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidalinfo%2Fextract-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidalinfo%2Fextract-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidalinfo%2Fextract-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aidalinfo","download_url":"https://codeload.github.com/aidalinfo/extract-kit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aidalinfo%2Fextract-kit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270506992,"owners_count":24596887,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-14T02:00:10.309Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-sdk","document-processing","pdf","pdf-extraction","vision-llm"],"created_at":"2025-08-15T01:09:36.667Z","updated_at":"2025-08-15T01:10:07.567Z","avatar_url":"https://github.com/aidalinfo.png","language":"TypeScript","readme":"# Extract Kit 🚀\n\nWelcome to **Extract Kit** - a powerful, modern solution for document data extraction and conversion, powered by AI vision models! Transform your PDFs and Office documents into structured, validated data with ease.\n\n\u003e 🌟 **Inspired by [Sparrow](https://github.com/katanaml/sparrow)** - This project builds upon the innovative concepts from Katana ML's Sparrow framework, reimagined with modern TypeScript, Bun runtime, and enhanced AI vision capabilities.\n\n## 🎯 What is Extract Kit?\n\nExtract Kit is a monorepo containing a suite of production-ready TypeScript/Bun-based tools that leverage cutting-edge AI vision models and advanced parsing techniques to intelligently extract and convert data from various document formats.\n\n## 🛠️ Available Packages\n\nThis repository contains the following open-source packages:\n\n### 1. PDF Processor\n\n[![npm version](https://badge.fury.io/js/%40aidalinfo%2Fpdf-processor.svg)](https://www.npmjs.com/package/@aidalinfo/pdf-processor)\n[![npm downloads](https://img.shields.io/npm/dm/@aidalinfo/pdf-processor.svg?style=flat-square)](https://www.npmjs.com/package/@aidalinfo/pdf-processor)\n\nA service that leverages cutting-edge AI vision models (Scaleway, Mistral, Ollama) to intelligently extract structured data from PDF documents. It's perfect for processing invoices, receipts, tables, or any custom document type.\n\n- **NPM Package**: [`@aidalinfo/pdf-processor`](https://www.npmjs.com/package/@aidalinfo/pdf-processor)\n- **Documentation**: [Read the PDF Processor README](./packages/pdf-processor/README.md)\n\n### 2. Office to Markdown\n\n[![npm version](https://badge.fury.io/js/%40aidalinfo%2Foffice-to-markdown.svg)](https://www.npmjs.com/package/@aidalinfo/office-to-markdown)\n[![npm downloads](https://img.shields.io/npm/dm/@aidalinfo/office-to-markdown.svg?style=flat-square)](https://www.npmjs.com/package/@aidalinfo/office-to-markdown)\n\nA modern TypeScript library for converting Office documents (DOCX) to Markdown format. It's optimized for the Bun ecosystem and includes advanced support for mathematical equations (OMML) and tables.\n\n- **NPM Package**: [`@aidalinfo/office-to-markdown`](https://www.npmjs.com/package/@aidalinfo/office-to-markdown)\n- **Documentation**: [Read the Office to Markdown README](./packages/office-to-markdown/README.md)\n\n## ✨ Key Features\n\n- **🤖 AI-Powered Extraction**: Harness the power of Scaleway Pixtral, Mistral AI, Ollama LLaVA, and custom AI providers for PDF processing.\n- **🔄 Advanced DOCX Conversion**: Convert `.docx` files to clean Markdown, preserving structure, styles, and even complex mathematical equations.\n- **📄 Smart PDF Processing**: Automatic PDF to optimized image conversion using Sharp for better AI recognition.\n- **⚡ Lightning Fast**: Built on Bun runtime with parallel worker processing for maximum performance.\n- **🔒 Type-Safe**: Full TypeScript implementation with Zod schema validation for reliable data extraction.\n- **📦 Dual Mode**: Use as a standalone REST API microservice or as a library in your existing Node.js/Bun projects.\n\n## 🚀 Quick Start\n\nFor detailed instructions, please refer to the README file of the specific package you want to use:\n\n- **For PDF Extraction**: [`packages/pdf-processor/README.md`](./packages/pdf-processor/README.md)\n- **For DOCX Conversion**: [`packages/office-to-markdown/README.md`](https://github.com/aidalinfo/extract-kit/blob/main/packages/office-to-markdown/README.md)\n\n## 🤝 Contributing\n\nWe welcome contributions! Please read our contribution guidelines (coming soon). For now, you can:\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## 🙏 Acknowledgments\n\n- Built with [Bun](https://bun.sh/) - The fast JavaScript runtime.\n- PDF Processor is powered by [Scaleway AI](https://www.scaleway.com/en/ai/), [Mistral AI](https://mistral.ai/), and [Ollama](https://ollama.ai/).\n- Office to Markdown is inspired by Microsoft's [MarkItDown](https://github.com/microsoft/markitdown).\n\n---\n\n**Happy Extracting!** 🎉","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faidalinfo%2Fextract-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faidalinfo%2Fextract-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faidalinfo%2Fextract-kit/lists"}