Opera help

Ollama

Ollama is an open source tool that runs large language models (LLMs) locally, on your own machine or server. Connected to Opera, it lets you use the Maestro assistant without relying on the cloud, keeping your conversations and your data entirely private.

How do I connect Ollama to Opera locally?

1 / Install Ollama on your computer or server

Before connecting Ollama to Opera, start by installing it on your machine.

  • Download Ollama: ollama.com
  • Run the installer and follow the instructions.

2 / Download an AI model

Once Ollama is installed, download an AI model.

  • Open the terminal on your machine.
  • Type the following command: ollama run llama3

3 / Share Ollama on your local network

Ollama has to be visible on the network so that it can talk to Opera.

  • In the Ollama app, turn on the « Expose Ollama to the network » option.
  • Note your machine's IP address (ipconfig on Windows, ipconfig getifaddr en0 on Mac, hostname -I on Linux).
  • Note the Ollama port (11434 by default).

4 / Check that everything works

Open the terminal and type the following command: curl http://localhost:11434/api/tags

You should get a JSON response listing the tags of the AI models available.

5 / Connect Opera to Ollama

Now that Ollama is running, connect it to Opera.

  • Open Opera, then go to « Settings » → « Service » → « Ollama » → « Add a server ».
  • Enter your local Ollama address (e.g.: http://[IP_ADDRESS]:11434).