{"id":24770882,"url":"https://github.com/amir-mohseni/shelfie","last_synced_at":"2026-02-27T10:06:54.906Z","repository":{"id":258018404,"uuid":"855189820","full_name":"Amir-Mohseni/Shelfie","owner":"Amir-Mohseni","description":"An intelligent grocery list application with AI-powered item categorization. Built with React and Flask, this app simplifies shopping by predicting categories, adapting to user preferences, and providing flexible, user-friendly features. Perfect for managing shopping lists efficiently!","archived":false,"fork":false,"pushed_at":"2025-12-10T11:57:28.000Z","size":7984,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-12-10T16:32:59.498Z","etag":null,"topics":["ai","categorization","flask-application","machine-learning","ui"],"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/Amir-Mohseni.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":"2024-09-10T13:18:18.000Z","updated_at":"2025-12-10T11:56:18.000Z","dependencies_parsed_at":"2025-01-15T11:25:05.106Z","dependency_job_id":"e719c393-0ee8-4889-9f97-cc9bb40acc60","html_url":"https://github.com/Amir-Mohseni/Shelfie","commit_stats":null,"previous_names":["amir-mohseni/grocery-list-app","amir-mohseni/shelfie"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Amir-Mohseni/Shelfie","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Amir-Mohseni%2FShelfie","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Amir-Mohseni%2FShelfie/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Amir-Mohseni%2FShelfie/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Amir-Mohseni%2FShelfie/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Amir-Mohseni","download_url":"https://codeload.github.com/Amir-Mohseni/Shelfie/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Amir-Mohseni%2FShelfie/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29890683,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T09:48:51.284Z","status":"ssl_error","status_checked_at":"2026-02-27T09:48:43.992Z","response_time":57,"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":["ai","categorization","flask-application","machine-learning","ui"],"created_at":"2025-01-29T03:57:02.079Z","updated_at":"2026-02-27T10:06:53.262Z","avatar_url":"https://github.com/Amir-Mohseni.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Shelfie: The AI-powered Grocery List App\n\nShelfie is a full-stack Grocery List app with an intelligent interface designed to enhance the grocery shopping experience. It features a React frontend and a Flask backend. The app not only allows users to create and manage grocery lists but also leverages AI to predict item categories, making the process efficient and personalized.\n\n## Features\n\n- **User Authentication**: Provides secure login and signup functionality.\n- **AI-Driven Categorization**: Automatically predicts the category for each grocery item as you type, helping users organize items faster.\n- **Flexible Categorization Options**: Users can override AI predictions and manually assign items to categories, providing control over the categorization process.\n- **Real-Time Predictions**: The app responds in real-time, offering immediate categorization suggestions without delays.\n- **Personalized Learning**: The AI model adapts over time, learning from user overrides to improve future predictions.\n\n\u003cimg src=\"./report/AI.png\" alt=\"AI-Integrated Version Screenshot\" width=\"400\"\u003e\n\n## Project Methodology\n\nThis project was developed in phases to ensure a user-centered design:\n\n1. **Requirement Extraction**: Based on a survey of 16 participants, mostly university students and postgraduates, essential features were identified, such as quick item entry, effective categorization, and AI-driven suggestions. \n   \n2. **Low-Fidelity Prototype**: A low-fidelity prototype was created to visualize the main interactions and functionalities, providing a foundation for design decisions.\n\n3. **Hard-Coded Baseline Version**: A non-AI version was first developed, allowing users to manually assign categories. This version established a baseline for comparison with the AI-enhanced version.\n\n4. **AI Integration**: A logistic regression model, enhanced with Word2Vec embeddings, was integrated to predict item categories. The model is retrained based on user behavior, allowing it to adapt to individual preferences.\n\n5. **User Testing**: A user study with 12 participants tested both versions of the app. The AI-enabled version significantly reduced task completion time and improved user satisfaction.\n\n## Key Results from User Testing\n\n- **Task Completion Time**: The AI-enabled version reduced task completion time by 40-50% compared to the manual version.\n- **User Emotions**: Positive emotions like satisfaction, confidence, and interest increased significantly, while negative emotions like frustration and boredom decreased.\n- **Flexibility**: The AI-enabled app effectively supported flexibility, allowing users to override predictions, control categorization, and personalize the experience.\n\n\u003cimg src=\"./report/ekman_model.png\" alt=\"Comparison of User Emotions\" width=\"400\"\u003e\n\n## Installation Guide\n\nTo streamline the setup process, you can use the provided `setup.sh` script to install dependencies and start the project.\n\n### Using the Setup Script\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/Amir-Mohseni/Shelfie.git\n   cd Shelfie\n   ```\n\n2. Run the setup script:\n\n   ```bash\n   bash setup.sh\n   ```\n\n   This script will:\n   - Install Node.js dependencies\n   - Set up the Python virtual environment and install Python dependencies\n   - Start both the frontend and backend servers concurrently\n\n### Manual Setup\n\nIf you prefer to install dependencies manually, follow these steps.\n\n#### 1. Install Node.js Dependencies\n\nIn the project root, run:\n\n```bash\nnpm install\n```\n\n#### 2. Install Python Dependencies\n\n1. Navigate to the backend directory:\n\n   ```bash\n   cd src/backend\n   ```\n\n2. Create and activate a virtual environment:\n\n   ```bash\n   python3 -m venv venv\n   source venv/bin/activate  # On Windows, use venv\\Scripts\\activate\n   ```\n\n3. Install Python packages:\n\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n#### 3. Run the Project\n\nTo start both the frontend and backend servers, run:\n\n```bash\nnpm run dev\n```\n\n- The React frontend will be available at [http://localhost:3000](http://localhost:3000).\n- The Flask backend will be available at [http://localhost:5000](http://localhost:5000).\n\n## Available Scripts\n\nIn the project directory, you can run:\n\n### `npm run dev`\n\nRuns both the React frontend and Flask backend concurrently in development mode.\n\n### `npm run start`\n\nRuns only the React frontend in development mode. Open [http://localhost:3000](http://localhost:3000) to view it in the browser.\n\n### `npm run backend`\n\nRuns only the Flask backend on [http://localhost:5000](http://localhost:5000).\n\n## Directory Structure\n\n- **src**: Contains all source code.\n  - **src/backend**: Flask backend.\n- **public**: Static assets for the frontend.\n- **requirements.txt**: Python dependencies for the backend.\n- **setup.sh**: Shell script to set up and start the project.\n\n## Future Improvements\n\n1. **Immersive Communication Technologies**: Augmented Reality (AR) could guide users to specific aisles in a grocery store, enhancing in-store navigation.\n2. **Explainability Features**: A history section that displays the model's predictions and category probabilities can improve transparency and build user trust.\n3. **Enhanced AI Capabilities**: Further training with diverse datasets and improved embeddings can boost the AI's prediction accuracy and adaptability.\n\n## Learn More\n\nTo learn more about the tools used in this project:\n\n- [React Documentation](https://reactjs.org/)\n- [Flask Documentation](https://flask.palletsprojects.com/)\n- [Tailwind CSS Documentation](https://tailwindcss.com/)\n\n## License\n\nThis project is licensed under the MIT License. See the LICENSE file for details.\n\n---\n\n## `setup.sh` (Installation Script)\n\nThis script simplifies the setup process by installing all necessary dependencies and starting both the frontend and backend servers.\n\n```bash\n#!/bin/bash\n\necho \"Setting up Shelfie...\"\n\n# Install Node.js dependencies\necho \"Installing Node.js dependencies...\"\nnpm install\n\n# Set up Python virtual environment and install dependencies\necho \"Setting up Python environment and installing dependencies...\"\ncd src/backend\npython3 -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\ncd ../../\n\n# Start both frontend and backend servers\necho \"Starting both frontend and backend servers...\"\nnpm run dev\n```\n\n### Instructions for Using `setup.sh`\n\n1. Make the script executable:\n\n   ```bash\n   chmod +x setup.sh\n   ```\n\n2. Run the script:\n\n   ```bash\n   ./setup.sh\n   ```\n\nThis will install dependencies and start both servers.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famir-mohseni%2Fshelfie","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famir-mohseni%2Fshelfie","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famir-mohseni%2Fshelfie/lists"}