This project provides a locally-run, privacy-focused AI coding assistant powered by the DeepSeek-r1 model via Ollama and built with Gradio. It targets developers seeking on-device assistance for Python coding, debugging, documentation, and solution design without relying on external cloud services.

How It Works

The assistant leverages LangChain to orchestrate interactions with the DeepSeek-r1 language model, served locally by Ollama. This architecture allows for 100% local execution, ensuring data privacy and offline usability. The Gradio interface provides a user-friendly chat experience for querying the model.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Download model: ollama pull deepseek-r1:1.5b
• Run Ollama: ollama serve
• Launch app: python app.py
• Prerequisites: Python 3.8+, Ollama, DeepSeek model.
• Access: http://127.0.0.1:7860

Highlighted Details

• Fine-tuned for Python: offers code completion, bug fixing, best practices, and performance tips.
• Debugging assistance: provides strategic print suggestions, error analysis, and step-by-step problem solving.
• Code documentation: generates docstrings, explains code, and suggests comment best practices.
• Solution design: offers architecture recommendations, design patterns, and scalability considerations.

Maintenance & Community

Contributions, issues, and feature requests are welcome via the issues page.

Licensing & Compatibility

MIT License. Permissive for commercial use and closed-source linking.

Limitations & Caveats

The project relies on the availability and performance of the DeepSeek-r1 model and Ollama. Specific model versions (1.5b vs. 3b) offer trade-offs between response speed and complexity handling.