AI Chat Application

Overview

This repository contains a full-stack AI-powered chat application built with the following components:

• Backend: Python FastAPI server that handles API requests and integrates with OpenAI's GPT-3.5 Turbo model.
• Frontend: A simple HTML and JavaScript-based user interface for interacting with the chat application.
• Utilities: Shell scripts and Python scripts for managing server processes and combining text data.

The project demonstrates seamless integration of AI capabilities into a modern web application.

Project Structure

File Descriptions

• server.py: The FastAPI server implementation, providing a /chat/ endpoint to process user input and return AI responses.
• index.html: The main frontend file providing a user interface for the chat application.
• script.js: Handles user interactions on the frontend and communicates with the backend API.
• start_server.sh: A shell script to kill any process running on port 8000 and restart the FastAPI server.
• combiner.py: Utility script to combine content from all files in the current directory into a single text file.
• test_transformers.py: A standalone script showcasing text generation using the Hugging Face GPT-2 model.
• .DS_Store: Automatically generated system file (ignored in most cases).
• README.md: This documentation file.
• combined_output.txt: Output file generated by combiner.py containing combined content from all files.

Prerequisites

Backend Requirements

• Python 3.8+

Required Python packages:

• fastapi
• uvicorn
• pydantic
• openai
• transformers

Install dependencies using:

pip install -r requirements.txt

Frontend Requirements

• A modern web browser.

Running the Application

Backend Setup

1. Set OpenAI API Key: Ensure the OPENAI_API_KEY environment variable is set in your shell. Example:

   export OPENAI_API_KEY="your_openai_api_key"

2. Start the Server: Use the provided shell script to start the FastAPI server:

   ./start_server.sh

   The server will be accessible at http://127.0.0.1:8000.

Frontend Setup

• Open index.html in your browser.
• Interact with the application by typing messages and viewing AI responses.

Additional Utilities

Combine Files Script

The combiner.py script reads all files in the current directory, extracts their content, and saves it in combined_output.txt. Run it using:

python combiner.py

Test Transformers Script

The test_transformers.py script demonstrates text generation using Hugging Face GPT-2. Execute it as:

python test_transformers.py

Deployment Notes

Ensure the server is running on http://127.0.0.1:8000 for the frontend to function.

For production, consider deploying using services like AWS, GCP, or Azure and securing API keys and endpoints.