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

# Ollama

> Use local models via Ollama.

Run models locally with [Ollama](https://ollama.ai). No API key required.

## Setup

```bash theme={null}
# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh

# Pull a model
ollama pull llama3
```

## Basic Usage

```python theme={null}
from definable.model.ollama import Ollama
from definable.model.message import Message

model = Ollama(id="llama3")
response = model.invoke(
    messages=[Message(role="user", content="Hello!")],
    assistant_message=Message(role="assistant", content=""),
)
print(response.content)
```

## String Shorthand

```python theme={null}
agent = Agent(model="ollama/llama3")
```

## Parameters

<ParamField path="id" type="str" required>
  Model name (must be pulled first with `ollama pull`).
</ParamField>

<ParamField path="host" type="str" default="http://localhost:11434">
  Ollama server URL.
</ParamField>

<ParamField path="temperature" type="float">
  Sampling temperature.
</ParamField>

<ParamField path="max_tokens" type="int">
  Maximum output tokens.
</ParamField>

## Imports

```python theme={null}
from definable.model.ollama import Ollama
```