> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Set Ollama Client

## Code

```python cookbook/models/ollama/set_client.py theme={null}
from agno.agent import Agent, RunResponse  # noqa
from agno.models.ollama import Ollama
from agno.tools.duckduckgo import DuckDuckGoTools
from ollama import Client as OllamaClient

agent = Agent(
    model=Ollama(id="llama3.2", client=OllamaClient()),
    tools=[DuckDuckGoTools(search=True)],
    markdown=True,
)

# Print the response in the terminal
agent.print_response("What are the latest news about AI developments?")
```

## Usage

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install Ollama">
    Follow the [installation guide](https://github.com/ollama/ollama?tab=readme-ov-file#macos) and run:

    ```bash theme={null}
    ollama pull llama3.2
    ```
  </Step>

  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U ollama ddgs agno
    ```
  </Step>

  <Step title="Run Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/models/ollama/set_client.py
      ```

      ```bash Windows theme={null}
      python cookbook/models/ollama/set_client.py
      ```
    </CodeGroup>
  </Step>
</Steps>