GPT-4 Sentiment and Risk Analysis API

Description

This project is a Node.js application that interacts with the OpenAI GPT-4 API to perform sentiment and self-harm risk analysis on user messages. It stores analysis results in MongoDB, manages user authentication, and sends email alerts when potential self-harm content is detected. The application provides a chat interface for users and can be deployed locally or to a cloud environment.

Features

• Self-Harm Risk Detection: Utilizes OpenAI's Moderation API to detect self-harm content in user messages.
• Email Notifications: Sends email alerts to designated recipients when potential self-harm risk is detected.
• MongoDB Integration: Stores risk analysis results and user data in a MongoDB database using Mongoose.
• Secure User Authentication: Implements JWT for session management and bcrypt for password hashing.
• Real-time Chat Interface: Users can communicate with the AI in real-time through a web-based chat interface.
• User Registration and Login: Allows users to create accounts and securely log in before accessing the chat.

Table of Contents

• Installation
• Configuration
• Running the Application
• API Endpoints
• Email Notifications
• Deployment
• Security and Privacy Considerations
• Contributing
• License
• Acknowledgments

Installation

Prerequisites

• Node.js: Ensure you have Node.js installed.
• MongoDB Atlas Account: Sign up for a free MongoDB Atlas account.
• OpenAI API Key: Obtain an API key from OpenAI.
• Email Service Account: Set up an account with an email service provider like SendGrid.
• Git: For cloning the repository.

Steps

1. Clone the Repository:

   git clone https://github.com/carson-evans/GPT-API.git

2. Navigate to the Project Directory:

   cd path/to/project-directory

3. Install Dependencies:

   npm install

4. Set Up Environment Variables:

   • Rename sample_env.js to env.js and update it with your actual keys and configurations.

     // env.js
     export const process = {
       env: {
         OPENAI_API_KEY: "your-openai-api-key",
         MONGODB_URI: "your-mongodb-connection-uri",
         EMAIL_SERVICE_API_KEY: "your-email-service-api-key",
         ALERT_EMAIL_RECIPIENT: "alerts@example.com",
         JWT_SECRET: "your-jwt-secret-key",
       },
     };

   • Note: Ensure env.js is included in your .gitignore file to prevent sensitive information from being committed to version control.

Configuration

OpenAI API Key

• Obtain your API key from the OpenAI dashboard.
• Update the OPENAI_API_KEY in your env.js.

MongoDB Setup

• Create a MongoDB Atlas cluster.
• Set up a database user and whitelist your IP address.
• Obtain your connection URI and update the MONGODB_URI in your env.js.

Email Service Setup

• Create an account with SendGrid or another email service provider.
• Generate an API key and update the EMAIL_SERVICE_API_KEY in your env.js.
• Verify your sender identity as per your email service's instructions.
• Set the ALERT_EMAIL_RECIPIENT in your env.js to the email address where alerts should be sent.
• Set the from: 'no-reply@yourdomain.com' in index.js to the verified sender email.

JWT Secret

• Generate a secure secret key for signing JWT tokens.
• Update the JWT_SECRET in your env.js.

Running the Application

Start the Server

npm start

• The server will run at http://localhost:3000.

Access the Application

• Open your browser and navigate to http://localhost:3000.
• Register a new account and log in to access the chat interface.

API Endpoints

POST /register

• Registers a new user.

Request Body

{
  "username": "your-username",
  "password": "your-password"
}

Response

{
  "message": "Registration successful"
}

POST /login

• Authenticates a user and returns a JWT token.

Request Body

{
  "username": "your-username",
  "password": "your-password"
}

Response

{
  "message": "Login successful",
  "token": "your-jwt-token"
}

POST ``

• Handles chat messages and performs risk analysis.

Headers

• Authorization: Bearer your-jwt-token

Request Body

{
  "messages": [
    {
      "role": "user",
      "content": "Your message here"
    }
  ]
}

Response

{
  "response": "Assistant's response"
}

Email Notifications

• When potential self-harm content is detected in a user's message, the application sends an email alert to the address specified in ALERT_EMAIL_RECIPIENT.
• Email Content:
  • Subject: Urgent: Self-Harm Risk Detected for User ID [userId]
  • Body: Includes the user's message and the self-harm score.

Deployment

Deploying to a Cloud Platform

• Ensure all environment variables are set securely in your hosting environment.
• Common platforms include Heroku, AWS Elastic Beanstalk, and Azure App Service.

SSL and Security

• Use HTTPS to secure data in transit.
• Obtain SSL certificates through services like Let's Encrypt.

Security and Privacy Considerations

• User Consent: Inform users that their messages are analyzed for safety purposes.
• Data Protection: Implement measures to protect user data, including encryption and secure storage practices.
• Access Control: Limit access to sensitive data and ensure only authorized personnel can view alerts.
• Compliance: Adhere to relevant laws and regulations, such as GDPR or HIPAA.

Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository.
2. Create a new branch:

 git checkout -b feature/your-feature-name

3. Commit your changes:

   git commit -m "Add your descriptive commit message"

4. Push to the branch:

   git push origin feature/your-feature-name

5. Open a pull request.

License

This project is licensed under the MIT License.

Acknowledgments

• OpenAI for providing the GPT-4 and Moderation APIs.
• MongoDB for database solutions.
• SendGrid for email services.