Ollama DeepSeek R1

Code

cookbook/reasoning/models/ollama/reasoning_model_deepseek.py

from agno.agent import Agent
from agno.models.ollama.chat import Ollama

agent = Agent(
    model=Ollama(id="llama3.2:latest"),
    reasoning_model=Ollama(id="deepseek-r1:14b", max_tokens=4096),
)
agent.print_response(
    "Solve the trolley problem. Evaluate multiple ethical frameworks. "
    "Include an ASCII diagram of your solution.",
    stream=True,
)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install Ollama

   Follow the installation guide and run:

   ollama pull llama3.2:latest
   
3. Install libraries

   pip install -U ollama agno
   
4. Run Agent

   Mac

   python cookbook/reasoning/models/ollama/reasoning_model_deepseek.py