Overview
The "Understand Tech Chat" node enables sending chat messages to a specified AI model hosted by UnderstandTech. It is designed for scenarios where users want to interact conversationally with an AI model, such as generating responses, getting assistance, or automating chat-based workflows.
Typical use cases include:
- Customer support automation by querying a chat model.
- Generating content or ideas through conversational prompts.
- Integrating AI chat capabilities into business processes.
For example, a user can send a prompt like "Explain the benefits of renewable energy" to a chosen model and receive a detailed response.
Properties
| Name | Meaning |
|---|---|
| Model Name | The identifier of the AI model to chat with. |
| Prompt | The message or question sent to the model to generate a response. |
| Additional Options | A collection of optional settings: |
| - Secret | A secret key for the chat session, required for models that need it (optional). |
| - Acting User Email | Email address representing the user on whose behalf the chat is conducted (optional). |
| - Language Preference | Selects the language for the chat interaction; options are English (US) or French (France). |
| - History Period | Defines the timeframe of chat history to include in the conversation context; options are Today, Yesterday, Last Week, or Last 30 Days. |
Output
The node outputs an array of JSON objects, each containing the full response from the UnderstandTech API under the json field. This response includes the chat model's reply and any additional metadata returned by the service.
No binary data output is produced by this node.
Example output structure snippet:
{
"json": {
"response": "...",
"metadata": { ... }
}
}
Dependencies
- Requires an API key credential for authentication with the UnderstandTech API.
- The node expects a valid base URL configured in the credentials for the UnderstandTech service.
- Network access to the UnderstandTech API endpoint is necessary.
Troubleshooting
- Missing Base URL: If the base URL is not set or invalid, the node will throw an error indicating the base URL is required and must be a valid URL. Ensure the credential configuration includes a correct API endpoint.
- Authentication Failures: Errors related to authentication usually mean the API key or token is missing or incorrect. Verify the credential details.
- Invalid Model Name or Prompt: Providing empty or incorrect values for the model name or prompt will cause the request to fail. Both fields are mandatory.
- API Response Errors: If the API returns an error, the node captures and outputs the error message and details unless "Continue On Fail" is enabled, in which case it proceeds with the next item.
- Language or History Period Options: Using unsupported values for language preference or history period may lead to unexpected behavior. Use only the provided options.