{"id":25201532,"url":"https://github.com/tnahom/image-search-engine","last_synced_at":"2026-04-14T10:32:18.769Z","repository":{"id":257420221,"uuid":"858210348","full_name":"TNAHOM/Image-Search-Engine","owner":"TNAHOM","description":"The Image Search Engine is a modern AI-powered web application leveraging Retrieval-Augmented Generation (RAG) to combine large language models (LLMs) with advanced image retrieval techniques.","archived":false,"fork":false,"pushed_at":"2024-11-09T17:04:18.000Z","size":518,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-04T20:41:17.003Z","etag":null,"topics":["fastapi","openai","pgvector","postgresql","python","rag","react","tailwindcss"],"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/TNAHOM.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}},"created_at":"2024-09-16T13:59:15.000Z","updated_at":"2024-12-08T13:28:39.000Z","dependencies_parsed_at":"2024-09-16T16:52:33.647Z","dependency_job_id":"d867ef9e-935a-43e3-82d9-d42475650d32","html_url":"https://github.com/TNAHOM/Image-Search-Engine","commit_stats":null,"previous_names":["tnahom/image-search-engine"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TNAHOM/Image-Search-Engine","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNAHOM%2FImage-Search-Engine","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNAHOM%2FImage-Search-Engine/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNAHOM%2FImage-Search-Engine/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNAHOM%2FImage-Search-Engine/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TNAHOM","download_url":"https://codeload.github.com/TNAHOM/Image-Search-Engine/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNAHOM%2FImage-Search-Engine/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31793212,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T02:24:21.117Z","status":"ssl_error","status_checked_at":"2026-04-14T02:24:20.627Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["fastapi","openai","pgvector","postgresql","python","rag","react","tailwindcss"],"created_at":"2025-02-10T05:16:47.445Z","updated_at":"2026-04-14T10:32:18.755Z","avatar_url":"https://github.com/TNAHOM.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image Search Engine (RAG-Retrieval-Augmented Generation)\n\n## Description\n\nThe Image Search Engine is a modern AI-powered web application leveraging Retrieval-Augmented Generation (RAG) to combine large language models (LLMs) with advanced image retrieval techniques. Designed for seamless user experience, this tool allows users to upload and search through images in a highly accurate, visually engaging way. Utilizing vector embeddings through OpenAI's models, the engine achieves context-aware search results that surpass traditional keyword-based searches—ideal for image-heavy applications like e-commerce.\n\n## Features\n\n- Image upload with drag-and-drop support\n- Image search functionality using vector embeddings\n- Responsive grid layout for displaying search results\n- Modern UI with smooth animations and transitions\n- Integration with Google Drive for image storage\n- Utilization of OpenAI's embeddings models for advanced search capabilities\n\n## Technology Stack\n\n- Frontend: React.js with Tailwind CSS for styling\n- Backend: FastAPI with PostgreSQL and pgvector\n- Image Storage: Google Drive\n- Vector Embeddings: OpenAI embeddings models\n- API: RESTful API for image upload and search\n\n## Installation\n\n### Prerequisites\n\n- Node.js and npm\n- Python 3.7+\n- PostgreSQL with pgvector extension\n- Google Drive API credentials\n\n### Frontend Setup\n\n1. Clone the repository:\n\n   ```\n   git clone https://github.com/TNAHOM/Image-Search-Engine.git\n   cd Image-Search-Engine/frontend\n   ```\n\n2. Install dependencies:\n\n   ```\n   npm install\n   ```\n\n3. Create a `.env` file in the frontend directory and add necessary environment variables:\n\n   ```\n   REACT_APP_API_URL=http://localhost:8000\n   ```\n\n4. Start the development server:\n   ```\n   npm start\n   ```\n\n### Backend Setup\n\n1. Navigate to the backend directory:\n\n   ```\n   cd ../backend\n   ```\n\n2. Create a virtual environment and activate it:\n\n   ```\n   python -m venv venv\n   source venv/bin/activate  # On Windows, use `venv\\Scripts\\activate`\n   ```\n\n3. Install required packages:\n\n   ```\n   pip install -r requirements.txt\n   ```\n\n4. Create a `.env` file in the backend directory and add necessary environment variables:\n\n   ```\n   DATABASE_URL=postgresql://username:password@localhost/dbname\n   OPENAI_API_KEY=your_openai_api_key\n   GOOGLE_DRIVE_CREDENTIALS_FILE=path/to/your/credentials.json\n   ```\n\n5. Set up the database:\n\n   ```\n   alembic upgrade head\n   ```\n\n6. Start the FastAPI server:\n   ```\n   uvicorn main:app --reload\n   ```\n\n## Usage\n\n1. **Uploading Images:**\n\n   - Drag and drop an image into the upload area, or click to select a file.\n   - Click the \"Upload Image\" button to submit the image.\n\n2. **Searching Images:**\n\n   - Use the search bar at the top of the page to enter your search query.\n   - Press Enter or click the search button to view results.\n\n3. **Viewing Results:**\n   - Scroll through the responsive grid of image results.\n   - Click on an image to view it in full size (if implemented).\n\n## API Endpoints\n\n- `/upload/`: POST request to upload an image\n- `/search/`: GET request to search for images using vector embeddings\n\nFor detailed API documentation, run the backend server and visit `http://localhost:8000/docs`.\n\n## Contributing\n\nContributions to the Image Search Engine project are welcome! Please follow these steps:\n\n1. Fork the repository\n2. Create a new branch: `git checkout -b feature-branch-name`\n3. Make your changes and commit them: `git commit -m 'Add some feature'`\n4. Push to the branch: `git push origin feature-branch-name`\n5. Submit a pull request\n\n## Contact\n\nFor any inquiries or issues, please open an issue on the [GitHub repository](https://github.com/TNAHOM/Image-Search-Engine/issues).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftnahom%2Fimage-search-engine","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftnahom%2Fimage-search-engine","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftnahom%2Fimage-search-engine/lists"}