With the Ollama provider

This page outlines the steps involved in using the Ollama provider.

To use this feature, you must first install Ollama 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.

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:

ollama list

1. (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 for more information.

2. Click Test request to validate the provider settings.

3. Set your scan prompt in the AI scanner tab, then either send requests for individual scans or enable processing for all active scans.