Ollama DeepSeek R1

Pair a local Ollama Llama 3.2 model with DeepSeek R1 as a reasoning model to solve the trolley problem.

Add the following code to your Python file

ollama_reasoning.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", options={"num_predict": 4096}),
)
agent.print_response(
    "Solve the trolley problem. Evaluate multiple ethical frameworks. "
    "Include an ASCII diagram of your solution.",
    stream=True,
)

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U agno ollama

Install Ollama

Follow the installation guide and run:

ollama pull llama3.2:latest
ollama pull deepseek-r1:14b

Run Agent

python ollama_reasoning.py