The Ollama Provider supports querying local Ollama models for prompt-based interactions. Make sure you have Ollama installed and running locally with your desired models.

​
Cloud Limitation

This provider is disabled for cloud environments and can only be used in local or self-hosted environments.

​
Inputs

The Ollama Provider supports the following inputs:

  • prompt: Interact with Ollama models by sending prompts and receiving responses
  • model: The model to be used, defaults to llama2 (must be pulled in Ollama first)
  • max_tokens: Limit amount of tokens returned by the model, default 1024.
  • structured_output_format: Optional JSON format for the structured output (check examples at the GitHub).

​
Outputs

Currently, the Ollama Provider outputs the response from the model based on the prompt provided.

​
Authentication Parameters

The Ollama Provider requires the following configuration parameter:

​
Connecting with the Provider

To use the Ollama Provider:

  1. Install Ollama on your system from Ollama’s website.
  2. Start the Ollama service.
  3. Pull your desired model(s) using ollama pull model-name.
  4. Configure the host URL in your Keep configuration.

​
Prerequisites

  • Ollama must be installed and running on your system.
  • The desired models must be pulled and available in your Ollama installation.
  • The Ollama API must be accessible from the host where Keep is running.
Ntfy.sh ProviderOpenAI Provider