Skip to main content

Generate Code

Generates code using Google Vertex AI's code generation models.

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​

  • Connection Id - The unique identifier of the connection to Vertex AI, typically obtained from the Connect node.
  • Prompt - The prompt describing the code to be generated.

Options​

  • Temperature - Controls randomness in the response (optional).
  • Max Output Tokens - Maximum number of tokens in the response. Default is 256. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.
  • Candidate Count - Number of response candidates to generate. Default is 1.
  • Model - The code model to use. Options include:
    • Custom Model
    • Code Bison
    • Default is Code Bison.
  • Custom Model - Custom model name if "Custom Model" is selected.
  • Locations - Google Cloud region for the service. Default is "us-central1".
  • Publishers - Publisher of the model. Default is "google".

Output​

  • Response - The generated code from the Vertex AI model as an object.

How It Works​

The Generate Code node sends a prompt to a Vertex AI code generation model and returns the model's code response. When executed, the node:

  1. Validates the connection ID and retrieves the authentication token
  2. Validates the required prompt input
  3. Collects all optional parameters and configurations
  4. Constructs a request with the prompt and parameters
  5. Sends the request to the Vertex AI code model endpoint
  6. Processes the response and returns it

Requirements​

  • A valid connection to Vertex AI established with the Connect node
  • Valid Google Cloud credentials with appropriate permissions
  • A properly configured Vertex AI code generation model
  • A clear prompt describing the desired code

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection ID
  • Empty prompt
  • Invalid parameter values
  • Missing required parameters
  • Invalid model selection
  • Network connectivity issues
  • Vertex AI service errors
  • Authentication failures

Usage Notes​

  • The Connection ID must be obtained from a successful Connect node execution
  • The Prompt should clearly describe what code you want to generate
  • Temperature controls creativity: lower values for more deterministic code, higher values for more creative solutions
  • Max Output Tokens limits the length of generated code
  • Multiple candidates can be generated by increasing Candidate Count
  • The Code Bison model is optimized for code generation tasks
  • The Locations parameter should match where your Vertex AI resources are deployed
  • Generated code should be reviewed and tested before use in production environments