This project is a simple chatbot server built with Python FastAPI.
As it is a local model, we have to download Ollama and Qwen2.5 model locally before running this API.
- Chatbot server implementation
- Easy to run and extend
-
Create a virtual environment (optional but recommended):
python -m venv venv .\venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Run the server:
uvicorn server:app --reload --host 0.0.0.0 --port 8000
See requirements.txt for dependencies.
MIT License