Actions21
Overview
The node provides integration with the RetellAI API, allowing users to manage various resources such as calls, agents, concurrency, knowledge bases, phone numbers, voices, and large language models (LLMs). Specifically, for the LLM Update operation, it enables updating properties of an existing LLM instance within RetellAI.
This is useful in scenarios where you want to programmatically modify the configuration of an LLM, such as changing its model type, adjusting temperature settings for response variability, or updating the general prompt that guides the LLM's behavior. For example, you might update an LLM to switch from a GPT-4 model to a Claude 3.5 Sonnet model or tweak the temperature to make responses more creative or deterministic.
Properties
| Name | Meaning |
|---|---|
| LLM ID | The unique identifier of the Retell LLM to update. |
| Update Fields | A collection of fields to update on the LLM: |
| - Model | The LLM model to use. Options: GPT-4, GPT-4 Mini, Claude 3.5 Sonnet, Claude 3 Haiku. |
| - Model Temperature | A number between 0 and 1 controlling the randomness/creativity of the model's output. |
| - General Prompt | A string prompt that sets the general context or instructions for the LLM's responses. |
Output
The node outputs JSON data representing the updated LLM object returned by the RetellAI API after the update operation. This typically includes the LLM's current configuration and metadata reflecting the changes made.
If the node supports binary data output (not indicated here), it would represent any associated files or media related to the LLM, but this is not applicable based on the provided code and properties.
Dependencies
- Requires an active connection to the RetellAI API.
- Needs an API authentication token configured in n8n credentials (referred generically as "an API key credential").
- The base URL for API requests is
https://api.retellai.com. - The node depends on internal helper functions to handle the LLM operations and validate credentials.
Troubleshooting
Common Issues:
- Invalid or missing LLM ID: Ensure the LLM ID provided exists and is correct.
- Authentication errors: Verify that the API key credential is correctly set up and has necessary permissions.
- Invalid field values: For example, setting a model temperature outside the 0-1 range will likely cause errors.
- Network issues: Connectivity problems with the RetellAI API endpoint can cause failures.
Error Messages:
- Errors returned from the API will be surfaced in the node output if "Continue On Fail" is enabled.
- Typical error messages may include "Unauthorized" (check API key), "Not Found" (invalid LLM ID), or validation errors for input fields.
To resolve these, double-check input parameters, ensure valid credentials, and confirm network connectivity.
Links and References
- RetellAI API Documentation (hypothetical link, replace with actual if available)
- n8n documentation on Creating Custom Nodes
- General info on LLM models and temperature settings:
Note: The summary is based solely on static analysis of the provided source code and property definitions without runtime execution or external API inspection.