# With the Ollama provider

{% hint style="warning" %}
To use this feature, you must first [install Ollama](https://ollama.com/download) on your machine and ensure that the models you want to query are already downloaded and available locally. For detailed information on installing Ollama and managing models, please refer to the [official Ollama documentation](https://github.com/ollama/ollama/tree/main/docs).
{% endhint %}

To configure and use the Ollama model provider, follow these steps:

1. Go to the `Provider settings` tab.
2. Select `Ollama` from the `Model provider` dropdown.
3. (Optional) The `Base URL` field defaults to Ollama's address: `http://localhost:11434`. If your Ollama instance runs on a different host or port, update this field accordingly.
4. Leave the `API key` field blank unless your deployment requires one.
5. In the `Model` field, enter the name of a model already installed in your Ollama environment. To list available models, run:

{% code fullWidth="false" %}

```powershell
ollama list
```

{% endcode %}

6. (Optional) Adjust the JSON-formatted settings in the `Request parameters` field to fine-tune the model’s completion behaviour. Refer to the [detailed list of valid parameters and their accepted values](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values) for more information.
7. Click `Test request` to validate the provider settings.
8. Set your scan prompt in the `AI scanner` tab, then either send requests for individual scans or enable processing for all active scans.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.burpgpt.app/how-to/use-supported-local-model-providers/with-the-ollama-provider.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.