{"id":28291769,"url":"https://github.com/josiah-mbao/docu-vision","last_synced_at":"2026-05-10T16:38:27.233Z","repository":{"id":292200244,"uuid":"980082215","full_name":"josiah-mbao/Docu-Vision","owner":"josiah-mbao","description":"An AI tool that turns documents into insights using Google Cloud and a FastAPI backend","archived":false,"fork":false,"pushed_at":"2025-05-08T17:49:28.000Z","size":1703,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-22T04:12:06.959Z","etag":null,"topics":["api","fastapi","gcp-storage-bucket"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/josiah-mbao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-05-08T14:32:05.000Z","updated_at":"2025-05-08T17:49:31.000Z","dependencies_parsed_at":"2025-05-08T18:40:41.864Z","dependency_job_id":"a34eac1e-84f1-4956-a5c3-113652899aed","html_url":"https://github.com/josiah-mbao/Docu-Vision","commit_stats":null,"previous_names":["josiah-mbao/document-intelligence-api","josiah-mbao/docu-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/josiah-mbao/Docu-Vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josiah-mbao%2FDocu-Vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josiah-mbao%2FDocu-Vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josiah-mbao%2FDocu-Vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josiah-mbao%2FDocu-Vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/josiah-mbao","download_url":"https://codeload.github.com/josiah-mbao/Docu-Vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josiah-mbao%2FDocu-Vision/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266342809,"owners_count":23914262,"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":"2025-07-21T11:47:31.412Z","response_time":64,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"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":["api","fastapi","gcp-storage-bucket"],"created_at":"2025-05-22T04:12:02.591Z","updated_at":"2026-05-10T16:38:27.209Z","avatar_url":"https://github.com/josiah-mbao.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DocuVision 🧠📄 - AI Document Processing\n\n[![FastAPI](https://img.shields.io/badge/FastAPI-005571?style=for-the-badge\u0026logo=fastapi\u0026logoColor=white)](https://fastapi.tiangolo.com/)\n[![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge\u0026logo=python\u0026logoColor=white)](https://python.org)\n[![OpenRouter](https://img.shields.io/badge/OpenRouter-1E1E2D?style=for-the-badge\u0026logo=openai\u0026logoColor=white)](https://openrouter.ai)\n[![PWA](https://img.shields.io/badge/PWA-5A0FC8?style=for-the-badge\u0026logo=pwa\u0026logoColor=white)](https://web.dev/progressive-web-apps/)\n[![HTML5](https://img.shields.io/badge/HTML5-E34F26?style=for-the-badge\u0026logo=html5\u0026logoColor=white)](https://developer.mozilla.org/en-US/docs/Web/HTML)\n[![CSS3](https://img.shields.io/badge/CSS3-1572B6?style=for-the-badge\u0026logo=css3\u0026logoColor=white)](https://developer.mozilla.org/en-US/docs/Web/CSS)\n[![JavaScript](https://img.shields.io/badge/JavaScript-F7DF1E?style=for-the-badge\u0026logo=javascript\u0026logoColor=black)](https://developer.mozilla.org/en-US/docs/Web/JavaScript)\n\n---\n\n![DocuVision Screenshot](https://github.com/user-attachments/assets/497c3d82-f396-4d54-92c3-5df37fc0e249)\n\n---\n\n## 📄 About\n\n**DocuVision** is an AI-powered document processing system that combines OCR extraction with intelligent document analysis. It uses **OCR.space** for text extraction and **OpenRouter AI** for document understanding, classification, and data structuring. The application is built with production-ready practices including rate limiting, API security, and PWA support.\n\nKey Improvements:\n- 🛡️ Added API security and rate limiting\n- 📱 Enhanced mobile experience with PWA support\n- 🧠 Smarter document analysis with AI classification\n- ⚡ Optimized performance with GZip compression\n- 🎨 Improved UI/UX with better feedback systems\n\n---\n\n## 🧠 Core Features\n\n### Document Processing\n- 📤 **Multi-format Upload**: Supports PDFs, JPEG, PNG (up to 10MB)\n- 🔍 **Advanced OCR**: OCR.space integration with fallback handling\n- 🧠 **AI Analysis**: Document classification and data extraction via OpenRouter\n- 📊 **Structured Output**: Clean JSON responses with typed fields\n\n### Technical Features\n- ⚡ **Production-Ready API**: Rate limiting, error handling, and docs\n- 🔒 **Optional API Key Security**: Protect your endpoints\n- 📱 **PWA Support**: Installable and works offline\n- 📈 **Progress Tracking**: Real-time upload and processing feedback\n- 🖨️ **Print Styles**: Document-friendly print output\n\n### Developer Experience\n- 📝 **Swagger Docs**: Interactive API documentation at `/api/docs`\n- 🔍 **Validation**: Strict file type and size validation\n- 🧩 **Modular Design**: Clean separation of concerns\n- 📊 **Logging**: Comprehensive request and error logging\n\n---\n\n## 🌐 Enhanced Tech Stack\n\n| Component          | Technology                                                                 |\n|--------------------|---------------------------------------------------------------------------|\n| **Frontend**       | HTML5, CSS3, JavaScript (PWA-enabled)                                    |\n| **Backend**        | FastAPI (Python) with Pydantic models                                    |\n| **OCR**           | OCR.space API                                                            |\n| **AI Analysis**    | OpenRouter AI (Mistral 7B)                                               |\n| **Security**       | API Key Auth, Rate Limiting                                              |\n| **Performance**    | GZip Middleware, Async Processing                                       |\n| **DevOps**         | Logging, Error Tracking, Configuration Management                       |\n\n---\n\n## ⚙️ Local Setup\n\n### Prerequisites\n- Python 3.9+\n- Node.js (for optional frontend builds)\n- API keys for:\n  - OCR.space (free tier available)\n  - OpenRouter (optional)\n\n### Installation\n```bash\n# Clone the repository\ngit clone https://github.com/josiah-mbao/docuvision.git\ncd docuvision\n\n# Create and activate virtual environment\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n\n# Install dependencies\npip install -r requirements.txt\n\n# Set up environment variables\ncp .env.example .env\n# Edit .env with your API keys","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosiah-mbao%2Fdocu-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosiah-mbao%2Fdocu-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosiah-mbao%2Fdocu-vision/lists"}