Features

• GPT-powered chatbot that can handle general chat, code generation, and mathematical queries.
• Firebase Firestore integration to store and retrieve chat history.
• Streamlit web interface for a user-friendly interaction with the chatbot.
• Displays responses with typing effects, including Python code snippets.

Prerequisites

Before running this project, make sure you have the following:

• Python 3.8 or higher installed.
• A Google Firebase account with Firestore enabled.
• A Google API key from ai.google.dev.

Setup

1. Clone the repository:

git clone https://github.com/yourusername/your-repo.git
cd your-repo

2. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # For Linux/macOS
venv\Scripts\activate     # For Windows

3. Install dependencies:

pip install -r requirements.txt

4. Set up Firebase and Google API Key:

Firebase Setup

1. Create a Firebase project in the Firebase Console.
2. Enable Firestore as your database.
3. Create a Firebase service account key by navigating to Project Settings > Service Accounts. Download the JSON file and place it in the root directory of your project as firebase_key.json.

Google API Key

1. Go to Google's AI Model API and create a new API key.
2. Copy the API key and add it to the .env file.

5. Set up environment variables:

• Create a .env file in the root directory with the following variables:

  API_KEY=your_gpt_api_key
  FIREBASE_KEY=path_to_firebase_key.json

6. Running the App

1. Start the Streamlit app:

   streamlit run main.py

2. This will open a web interface where you can start chatting with the AI bot.

Project Structure

• main.py: Handles Streamlit's front-end interface and chatbot functionality.
• backend.py: Manages GPT API communication, Firebase interactions, and message processing.
• firebase_key.json: Firebase service account configuration for Firestore access.
• .env: Stores environment variables, including API and Firebase keys.

Usage

Start Chatting

• Click the "Start Chatting" button to load previous chat history from Firestore.
• Enter your prompt in the chat input field, and the bot will generate a response.

Chatbot Interaction

• The chatbot supports regular chat, math expressions, and code generation (Python).
• The chat history will be stored in Firebase, and previous interactions will be loaded when you reopen the app.

Key Components

Backend (backend.py)

• Firebase Integration: Uses Firestore to store user prompts and bot responses.
• GPT Interaction: Sends user input to the Gemini AI model, processes the response, and handles different types of outputs (text, code, etc.).

Frontend (main.py)

• Streamlit Interface: Displays a user-friendly chat interface where you can input messages and view responses.
• Message Handling: Processes user inputs and responses, including displaying Python code if generated by the AI.

Example Chatbot Interaction

Once the chatbot is running, it can handle interactions like:

User: "Can you write a Python program to add two numbers?"

Bot:

def add_two_numbers(num1, num2):
    return num1 + num2

number1 = float(input("Enter the first number: "))
number2 = float(input("Enter the second number: "))

result = add_two_numbers(number1, number2)
print("The sum of", number1, "and", number2, "is", result)