Code Assistant powered by Deepseek

🚀 Why fear when AI and Arman are here?

🧠 Introduction

Code Assistant is an AI-powered coding assistant built using Streamlit and Deepseek, running locally with Ollama. This tool provides assistance with debugging, code documentation, and solution design using Deepseek-r1:1.5b and Deepseek-r1:3b models.

📌 Features

• 🐍 Python Expert – Get help with Python programming.
• 🐞 Debugging Assistant – Identify and fix errors quickly.
• 📝 Code Documentation – Generate documentation for your code.
• 💡 Solution Design – Get structured solutions for coding problems.

---

🔧 Prerequisites

Before running the project, make sure you have:

1. Ollama installed (to run LLM models locally)
2. Deepseek model downloaded: deepseek-r1:1.5b
3. Python and Conda installed (recommended for virtual environment setup)

🔽 Install Deepseek Model

Run the following command in the terminal:

ollama run deepseek-r1:1.5b

---

🏗️ Installation & Setup

Step 1: Clone the Repository

git clone https://github.com/your-username/code-assistant.git
cd code-assistant

Step 2: Create a Virtual Environment (Optional but Recommended)

conda create --name code-assistant python=3.9 -y
conda activate code-assistant

Step 3: Install Dependencies

pip install -r requirements.txt

Step 4: Run the Application

streamlit run app.py

---

📸 Screenshots

---

🛠️ Built With

• Streamlit – UI Framework
• LangChain – LLM Orchestration
• Ollama – LLM Runtime

---

📜 Requirements

Ensure you have the following dependencies installed:

streamlit
langchain_core
langchain_community
langchain_ollama

---

📌 Contributing

Feel free to fork this repository and submit pull requests. If you find any issues, open an issue on GitHub.

---

📞 Contact

For any inquiries, reach out via GitHub Issues or email at armanshikalgar01@gmail.com.