A Streamlit-based application that leverages AI to assist with software development tasks. The application uses LangChain, OpenAI, and LangGraph to create an intelligent coding assistant that can help with code generation, testing, and debugging.
See Blog post / tutorial here: https://www.ernovuori.com/ai-development-assistant/
- Interactive web interface built with Streamlit
- AI-powered code generation and refinement
- Automated test case generation
- Code execution and error handling
- Multi-agent workflow for comprehensive code development
- Environment setup and configuration management
- Python 3.8 or higher
- OpenAI API key
- Azure OpenAI API credentials (if using Azure)
- Clone the repository:
git clone <repository-url>
cd software-development-assistant- Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows, use `.venv\Scripts\activate`- Install dependencies:
pip install -r requirements.txt- Set up environment variables:
- Copy
.env-exampleto.env - Fill in your API keys and configuration settings
- Copy
app.py: Main application file with Streamlit interfaceagents.py: Agent definitions and setupmodels.py: Data models and schemasworkflow.py: LangGraph workflow implementation.streamlit/: Streamlit configuration directory.env: Environment variables and API keysrequirements.txt: Project dependencies
- Start the application:
streamlit run app.py-
Open your web browser and navigate to the provided local URL (typically http://localhost:8501)
-
Use the interface to:
- Input your coding requirements
- Generate and refine code
- Run tests
- Debug and fix issues
- streamlit >= 1.32.0
- langchain >= 0.1.0
- langchain-openai >= 0.0.5
- langgraph >= 0.0.15
- langchain-core >= 0.1.0
- pydantic >= 2.0.0
- duckduckgo-search >= 4.1.1
- python-dotenv >= 1.0.0
Erno Vuori (erno.vuori@gmail.com)
[Add your license information here]