Python Compiler with OpenAI and Streamlit

This project provides a simple interface for simulating a Python compiler using OpenAI's GPT-3.5-Turbo model. Users can input Python code into a Streamlit application, and the app will return the console output as if the code were executed in a Python interpreter.

Features

• Interactive Code Input: Enter Python code in a text area.
• Simulated Execution: View the expected Python console output generated by GPT-3.5-Turbo.
• Streamlit Interface: User-friendly interface for seamless interaction.

Requirements

To run this application, you need the following:

• Python 3.7+
• Required libraries:
  • openai
  • streamlit

Setup

Step 1: Clone the Repository

git clone https://github.com/your-username/python-compiler.git
cd python-compiler

Step 2: Install Dependencies

Install the required Python packages using pip:

pip install openai streamlit

Step 3: Set Up OpenAI API Key

1. Create an OpenAI API key from the OpenAI API Dashboard.
2. Save the API key in a text file named .openai_api_key.txt under the keys directory:

   mkdir keys
   echo "your-openai-api-key" > keys/.openai_api_key.txt

Step 4: Run the Application

Start the Streamlit application:

streamlit run app.py

File Structure

.
├── app.py                # Main Streamlit application script
├── keys/
│   └── .openai_api_key.txt  # Contains the OpenAI API key
├── README.md             # Project documentation
└── requirements.txt      # List of dependencies (optional)

How It Works

1. The application reads the OpenAI API key from the .openai_api_key.txt file.
2. Users enter a Python code snippet into the text area provided by Streamlit.
3. Upon clicking the "Compile" button, the code is sent to OpenAI's GPT-3.5-Turbo model with a system prompt to act as a Python compiler.
4. The model generates the expected terminal output for the code, which is displayed in the Streamlit interface.

Example

Input:

print("Hello, World!")

Output:

Hello, World!

Contributing

Feel free to submit issues or pull requests to improve this project.

License

This project is licensed under the MIT License. See the LICENSE file for more details.