Skip to main content

Ollama

note

If your tasking AI server is locally deployed with Docker, and the target model is also running in your local environment, OLLAMA_HOST should start with http://host.docker.internal:port instead of http://localhost:port. Replace port with your actual port number.

Ollama is a powerful framework designed for deploying LLM in Docker containers. We support version 0.1.24 or later.

Requisites​

To integrate a model running on Ollama to TaskingAI, you need to have a valid Ollama service first. To get started, please visit Ollama's website, or follow the simple instructions in the Quick Start.

Required credentials:

  • OLLAMA_HOST: Your Ollama host URL.

Supported Models:​

Wildcard​

  • Model schema id: ollama/wildcard

Quick Start​

Deploy Ollama service to your local environment​

  1. Download Ollama client from Ollama's website.
  2. Start your desired model with Ollama: 
    ollama run <model_name>
    By default, the model is running on your localhost at 11434 port. You can access the model by sending a POST request to http://localhost:11434. For a detailed model list, please check Ollama Models.

Integrate Ollama to TaskingAI​

Now that you have a running Ollama service with your desired model, you can integrate it to TaskingAI by creating a new model with the following steps:

  1. Visit your local TaskingAI service page. By default, it is running at http://localhost:8080.
  2. Login and navigate to Model management page.
  3. Start creating a new model by clicking the Create Model button.
  4. Select Ollama as the provider, and wildcard as model.
  5. Use Ollama service's address http://localhost:11434 as OLLAMA_HOST

Integrate Ollama Models