"ThunderAI" Setup Guide - Ollama (Local AI)

The Ollama integration lets you run AI models locally on your own machine.
Your emails never leave your computer: there are no API keys, no cloud services, no costs beyond your hardware.

Prerequisites

• Ollama installed and running on your machine (or accessible on your local network)
• At least one model downloaded in Ollama
• Thunderbird with ThunderAI installed

Installing Ollama and downloading a model

If you haven't installed Ollama yet:

1. Download it from ollama.com and follow the installation instructions for your OS
2. Open a terminal and pull a model, for example:
   

   ollama pull llama3

   Other good options for email tasks: mistral, phi3, gemma2
3. Verify Ollama is running:
   

   ollama list

Configuring CORS

Thunderbird extensions run in a sandboxed environment, so Ollama needs to be configured to accept requests from browser extensions.
You need to set the OLLAMA_ORIGINS environment variable to moz-extension://*.

For more detailed CORS configurations, see the Ollama CORS Information page.

Setup

1. Open ThunderAI Options

In Thunderbird, click the ThunderAI menu and select Options, or go to
Tools → Add-ons and Themes → ThunderAI → Preferences.

2. Select the Ollama integration

In the Connection section, choose Ollama from the integration dropdown.

3. Set the server URL

Enter the URL of your Ollama server. The default is:

http://localhost:11434

If Ollama is running on another machine on your network, replace localhost with that machine's IP address.

4. Choose a model

Select a model from the Model dropdown. Click the button to refresh the list.

5. Save and test

Click Save. Open any email, use the ThunderAI menu, and run a prompt to verify the connection.

Tips

• Performance depends on your hardware. A modern machine with at least 16 GB of RAM will handle models like llama3 or mistral comfortably. A GPU significantly speeds things up.
• Smaller models (7B parameters) are faster but less capable; larger models (13B, 70B) produce better results but require more resources.
• For email tasks, mistral and llama3 are popular choices offering a good balance of quality and speed.

Troubleshooting

"Failed to connect" or no response

Check that Ollama is actually running (ollama list in a terminal). Verify the server URL in ThunderAI options matches your Ollama setup.

CORS error

The OLLAMA_ORIGINS variable is either not set or Ollama was not restarted after setting it. Follow the steps above again, or use the "All URLs" permission as a workaround.

Empty model list

Make sure you have pulled at least one model with ollama pull <modelname> and that Ollama is running.