Skip to main content

Connect

Establishes a connection to your local Ollama server and creates a client session for interacting with AI models.

tip

You can skip using Connect/Disconnect nodes by providing the Host URL directly in other Ollama nodes. This is useful for simple, one-off operations.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.
info

If the ContinueOnError property is true, no error is caught when the project is executed, even if a Catch node is used.

Inputs​

This node does not have any inputs.

Output​

  • Client ID - A unique identifier for this Ollama client session. Use this ID in other Ollama nodes to reuse the same connection.

Options​

This node uses the Ollama Host credential configured in the vault. If not specified in the vault, it defaults to http://localhost:11434.

How It Works​

The Connect node:

  1. Creates a new Ollama client instance
  2. Establishes connection to the Ollama server (local or remote)
  3. Generates a unique client ID
  4. Returns the client ID for use in subsequent Ollama operations

Usage Example​

Basic Connection Flow​

1. Connect
   └─> Client ID: "abc123..."

2. Generate Completion (using Client ID: "abc123...")
   └─> Response: "Your generated text..."

3. Disconnect (using Client ID: "abc123...")

Configuring Ollama Host​

To connect to a custom Ollama server:

  1. Go to Vault > Credentials
  2. Add a new Ollama Host credential
  3. Enter your server URL (e.g., http://192.168.1.100:11434 for a remote server)
  4. Select this credential in your Connect node

Requirements​

  • Ollama must be installed and running on the target machine
  • The Ollama service must be accessible at the specified URL
  • Default port is 11434

Common Use Cases​

  • Establishing a persistent connection for multiple AI operations
  • Connecting to a remote Ollama server on your network
  • Sharing a single connection across multiple nodes in your workflow

Tips​

  • Store the Client ID in a message variable to reuse across multiple nodes
  • If you only need to perform a single operation, consider using the Host URL option directly in the operation node instead of using Connect/Disconnect
  • For local installations, the default settings usually work without configuration
  • Use Disconnect at the end of your workflow to properly clean up resources

Error Handling​

Common errors you might encounter:

  • "Failed to create client" - The Ollama service is not running or not accessible
  • Connection refused - Check that Ollama is running on the specified host and port
  • Invalid URL - Verify the Ollama Host URL format (should start with http:// or https://)