...

README.md

@@ -0,0 +1,124 @@
+---
+title: MediBot
+emoji: 🏥
+colorFrom: blue
+colorTo: green
+sdk: streamlit
+sdk_version: "1.38.0"
+app_file: app.py
+pinned: false
+---
+
+# MediBot - Health Assistant
+
+MediBot is a Streamlit-based web application designed to assist users in identifying possible health conditions based on symptoms and answering health-related questions using AI. It leverages a Neon PostgreSQL database for storing user data and symptom-disease mappings, and integrates with the Groq API for natural language responses.
+
+**Disclaimer**: This app provides preliminary health information based on symptoms and AI analysis. It is not a substitute for professional medical advice, diagnosis, or treatment. Always consult a qualified healthcare provider for any health concerns.
+
+## Features
+- **Symptom-Based Diagnosis**: Users can select symptoms to receive potential disease matches, descriptions, and precautions based on provided datasets.
+- **Health Question Answering**: Users can ask free-text health questions, answered via the Groq API.
+- **User Management**: Optional registration and login to save symptom history, with a unique user ID.
+- **History Tracking**: Registered users can view their past symptom searches and AI responses.
+- **Database Integration**: Uses Neon PostgreSQL to store user data, symptoms, diseases, and history.
+- **Responsive Design**: Built with Streamlit for a user-friendly interface.
+
+## Setup Instructions
+
+### Prerequisites
+- A Hugging Face account to deploy the Space.
+- A Neon PostgreSQL database with the schema set up (see `create_tables.sql`).
+- A Groq API key for answering health questions.
+
+### Deployment on Hugging Face
+1. **Create a New Space**:
+   - Go to [Hugging Face Spaces](https://huggingface.co/spaces) and create a new Space.
+   - Choose the Streamlit SDK and name your Space (e.g., `MediBot`).
+
+2. **Upload Files**:
+   - Upload the following files to the Space repository:
+     - `app.py`
+     - `database.py`
+     - `user_management.py`
+     - `requirements.txt`
+     - `create_tables.sql` (for reference)
+     - `README.md` (this file)
+
+3. **Configure Secrets**:
+   - In the Space settings, add the following secrets:
+     - `DB_CONNECT`: Your Neon PostgreSQL connection string (e.g., `postgresql://neondb_owner:mypassword@ep-shiny-band-a2wzybro-pooler.eu-central-1.aws.neon.tech/medibot?sslmode=require&channel_binding=require`).
+     - `GROQ_API_KEY`: Your Groq API key.
+
+4. **Set Up Database**:
+   - Connect to your Neon PostgreSQL database using a tool like `psql` or Neon's SQL editor.
+   - Run the SQL script in `create_tables.sql` to create and populate the tables (`mb_users`, `mb_history`, `mb_symptoms`, `mb_diseases`, `mb_disease_symptoms`).
+
+5. **Deploy**:
+   - Commit the files and wait for Hugging Face to build and deploy the Space.
+   - Once deployed, access the app via the provided Space URL.
+
+### Local Development
+1. **Clone the Repository**:
+   ```bash
+   git clone https://huggingface.co/spaces/<your-username>/MediBot
+   cd MediBot
+   ```
+
+2. **Install Dependencies**:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **Set Environment Variables**:
+   ```bash
+   export DB_CONNECT="postgresql://neondb_owner:mypassword@ep-shiny-band-a2wzybro-pooler.eu-central-1.aws.neon.tech/medibot?sslmode=require&channel_binding=require"
+   export GROQ_API_KEY="your-groq-api-key"
+   ```
+
+4. **Run the App**:
+   ```bash
+   streamlit run app.py
+   ```
+
+5. **Access the App**:
+   - Open your browser and navigate to `http://localhost:8501`.
+
+## Project Structure
+- `app.py`: Main Streamlit app handling symptom input, diagnosis, and health question queries.
+- `database.py`: Manages database connections and queries for symptoms, diseases, and user history.
+- `user_management.py`: Handles user registration, login, and history display.
+- `create_tables.sql`: SQL script to set up the Neon PostgreSQL database.
+- `requirements.txt`: Python dependencies for the app.
+
+## Database Schema
+- **mb_users**: Stores user information (user_id, date_of_birth, email, registration_date).
+- **mb_history**: Stores user symptom history and predicted diseases.
+- **mb_symptoms**: Stores symptom names and severity weights.
+- **mb_diseases**: Stores disease names, descriptions, and precautions.
+- **mb_disease_symptoms**: Maps diseases to symptoms for diagnosis.
+
+## Datasets
+The app uses the following datasets (populated in the database via `create_tables.sql`):
+- `dataset.csv`: Maps symptoms to diseases.
+- `Symptom-severity.csv`: Provides symptom weights.
+- `symptom_Description.csv`: Disease descriptions.
+- `symptom_precaution.csv`: Disease precautions.
+
+## Technologies Used
+- **Streamlit**: For the web interface.
+- **Neon PostgreSQL**: For data storage.
+- **Groq API**: For answering health questions.
+- **psycopg2**: For PostgreSQL database connectivity.
+- **Python**: Core programming language.
+
+## Contributing
+Contributions are welcome! Please fork the repository and submit a pull request with your changes.
+
+## License
+This project is licensed under the MIT License.
+
+## Contact
+For support or inquiries, contact the xAI team or open an issue in the repository.
+
+---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference