Overview
This node integrates with Straico's chat-completion AI models, enabling users to generate text completions based on conversational input. It is designed for scenarios where AI-driven language generation is needed, such as building chatbots, generating content, or automating responses in workflows.
Practical examples include:
- Creating an AI assistant that responds to user queries.
- Generating creative writing or marketing copy.
- Automating customer support replies using AI-generated text.
Properties
| Name | Meaning |
|---|---|
| Model | Choose the Straico model to generate the completion. Options are dynamically loaded from Straico's available models. More info: Straico Models |
| Options | Collection of optional parameters to customize the AI output: |
| - Frequency Penalty: Penalizes tokens based on their frequency in the text (range: -2 to 2). | |
| - Max Retries: Maximum number of retry attempts for the request. | |
| - Max Tokens: Maximum number of tokens to generate in the response. | |
| - Presence Penalty: Penalizes tokens based on their presence in the text (range: -2 to 2). | |
| - Temperature: Controls randomness of the model output (range: 0 to 2). | |
| - Timeout (Ms): Maximum allowed time for the request in milliseconds. | |
| - Top P: Controls diversity via nucleus sampling (range: 0 to 1). |
Output
The node outputs data through the json field containing the AI-generated completion result from the Straico model. The exact structure depends on the Straico API response but generally includes the generated text and related metadata.
If binary data were supported, it would represent any non-textual output from the model, but this node focuses on textual completions only.
Dependencies
- Requires an API key credential for Straico's API service.
- The node makes HTTP requests to Straico's API endpoint, defaulting to
https://api.straico.com/v0unless overridden by credentials. - Network connectivity to Straico's API is necessary.
- No additional external dependencies beyond the Straico API and its authentication.
Troubleshooting
- Common Issues:
- Invalid or missing API key will cause authentication failures.
- Network timeouts if the API does not respond within the specified timeout.
- Selecting a model that is deprecated or unavailable may cause errors.
- Error Messages:
- Authentication errors typically indicate invalid credentials; verify the API key.
- Timeout errors suggest increasing the "Timeout (Ms)" option or checking network stability.
- API errors related to parameters may require adjusting options like max tokens or penalties.