Generic Code Generator

Overview

PyCode generates code and test cases for a task in the programming language you choose. It uses the langchain library to call OpenAI’s language models.

Getting Started

1. Clone the Repository: Clone the PyCode repository to your local machine.
2. Install Dependencies: Run pip install -r requirements.txt to install the dependencies.
3. Environment Setup: Create a .env file and populate it with required environment variables.
4. Execution: Run the main.py script with appropriate command-line arguments to start generating code.

Usage

• Command-Line Arguments:
  • --task: Define the specific task for code and test generation (e.g., “return a list of numbers”).
  • --language: Choose the programming language for the output (e.g., “python”).
• Example: python main.py --task "calculate the factorial of a number" --language "java".

Code Generation Process

1. Load environment variables from the .env file.
2. Create an instance of the OpenAI class from the langchain.llms module.
3. Use the PromptTemplate class from langchain.prompts for defining code and test generation templates.
4. Generate code and tests using instances of the LLMChain class from langchain.chains.
5. Combine the code and test steps with a SequentialChain instance.
6. Execute the chain with specified task and language parameters.
7. Output the generated code and tests to the console.

Contributing

Contributions are welcome. Open an issue, suggest an improvement, or submit a pull request.

Additional Information

• GitHub Repository: PyCode on GitHub
• License: MIT License.