{"id":26737265,"url":"https://github.com/msparihar/forofuse","last_synced_at":"2025-03-28T02:39:11.476Z","repository":{"id":282949687,"uuid":"947233127","full_name":"Msparihar/forofuse","owner":"Msparihar","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-17T19:36:43.000Z","size":109,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-17T20:36:04.249Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Msparihar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-12T11:11:43.000Z","updated_at":"2025-03-17T19:36:46.000Z","dependencies_parsed_at":"2025-03-17T20:49:10.748Z","dependency_job_id":null,"html_url":"https://github.com/Msparihar/forofuse","commit_stats":null,"previous_names":["msparihar/forofuse"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Msparihar%2Fforofuse","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Msparihar%2Fforofuse/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Msparihar%2Fforofuse/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Msparihar%2Fforofuse/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Msparihar","download_url":"https://codeload.github.com/Msparihar/forofuse/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245959270,"owners_count":20700590,"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","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":[],"created_at":"2025-03-28T02:39:10.927Z","updated_at":"2025-03-28T02:39:11.458Z","avatar_url":"https://github.com/Msparihar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Forofuse\n\n![Python Version](https://img.shields.io/badge/python-3.9%2B-blue)\n![License](https://img.shields.io/badge/license-MIT-green)\n\nAn innovative AI platform that combines a natural language user matching engine with a CLIP-based image recommendation system. Forofuse leverages modern AI techniques to enable discovery of like-minded individuals and to deliver image recommendations based on visual and contextual similarities.\n\n## Features\n\n### User Matching System\n\n- Natural language queries to find like-minded people\n- Vector-based similarity search using Qdrant\n- Compatibility scoring and match explanations\n- User profiles with interests, values, and expertise\n\n### Image Recommendation System\n\n- Content-based image similarity using CLIP model\n- Multi-aspect similarity scoring\n- Support for sequential recommendations\n- Detailed similarity explanations\n\n## Technical Stack\n\n- **Backend**: FastAPI\n- **Frontend**: Streamlit\n- **Vector Database**: Qdrant\n- **ML Models**: CLIP for embeddings\n- **Image Processing**: Pillow\n- **Data Storage**: Local file system\n\n## Prerequisites\n\n- Python 3.9+\n- Docker (for Qdrant)\n- CUDA-compatible GPU (optional, for faster inference)\n\n## Installation\n\n1. Clone the repository:\n\n```bash\ngit clone \u003crepository-url\u003e\ncd ai-matching-system\n```\n\n2. Install dependencies:\n\n```bash\nuv pip install -r requirements.txt\n```\n\n3. Start Qdrant using Docker:\n\n```bash\ndocker run -d --name qdrant -p 6333:6333 -p 6334:6334 qdrant/qdrant\n```\n\n## Running the Application\n\n1. Start the application using the provided script:\n\n```bash\npython run_app.py\n```\n\nThis will:\n\n- Start Qdrant if not running\n- Launch the FastAPI backend\n- Start the Streamlit frontend\n- Open the application in your default browser\n\nThe application will be available at:\n\n- Frontend: \u003chttp://localhost:8501\u003e\n- Backend API: \u003chttp://localhost:8000\u003e\n- API Documentation: \u003chttp://localhost:8000/docs\u003e\n\n## Usage\n\n### User Matching\n\n1. Navigate to the User Matching page\n2. Enter a natural language query describing the kind of people you're looking for\n3. Adjust the number of matches you want to see\n4. View detailed profiles with compatibility scores and match reasons\n\nExample query:\n\n```\nI'm looking for AI researchers in NYC who are passionate about environmental conservation and hiking\n```\n\n### Image Recommendations\n\n1. Navigate to the Image Recommendation page\n2. Upload images with descriptive labels\n3. Select a reference image\n4. View similar images with similarity scores and explanations\n5. Use the \"Next\" feature to explore more recommendations\n\n## Project Structure\n\n```\n.\n├── backend/\n│   ├── api/\n│   │   ├── main.py\n│   │   ├── user_routes.py\n│   │   └── image_routes.py\n│   ├── models/\n│   │   ├── user.py\n│   │   └── image.py\n│   └── services/\n│       ├── user_matching.py\n│       └── image_recommendation.py\n├── frontend/\n│   └── pages/\n│       ├── user_matching.py\n│       └── image_recommendation.py\n├── data/\n│   ├── users.json\n│   └── images/\n├── requirements.txt\n└── run_app.py\n```\n\n## API Documentation\n\n### User Matching Endpoints\n\n- `POST /api/users/match`: Find matching users\n  - Parameters: query text, limit\n  - Returns: Ranked list of matches with compatibility scores\n\n### Image Recommendation Endpoints\n\n- `POST /api/images/upload`: Upload and index a new image\n  - Parameters: image file, labels\n  - Returns: Image ID and confirmation\n\n- `POST /api/images/recommend`: Get similar images\n  - Parameters: reference image ID, limit\n  - Returns: Ranked list of similar images with scores\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch\n3. Commit your changes\n4. Push to the branch\n5. Create a Pull Request\n\n## License\n\nMIT License - feel free to use this project for any purpose.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsparihar%2Fforofuse","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmsparihar%2Fforofuse","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsparihar%2Fforofuse/lists"}