Overview
This node integrates with Ittes AI models to generate completions using various language models provided by the Ittes AI service. It is designed for scenarios where users want to leverage AI-driven text generation, such as content creation, chatbots, summarization, or any task requiring natural language understanding and generation.
Practical examples include:
- Generating creative writing or marketing copy.
- Building conversational agents that respond dynamically.
- Summarizing large texts or extracting key information.
- Experimenting with different AI models to find the best fit for a specific use case.
Properties
| Name | Meaning |
|---|---|
| Each model has different capabilities and costs. Learn more about available models | Informational notice explaining that different models have varying features and pricing. |
| Model | The specific AI model to use for generating completions. Options are dynamically loaded from the Ittes AI API. |
| Options | Additional configuration options for the AI completion: |
| - Maximum Number of Tokens | Limits the maximum number of tokens in the generated output (default 2048). |
| - Temperature | Controls randomness in output; higher values produce more diverse results (default 0.7). |
| - Top P | Controls nucleus sampling; limits token selection to a subset with cumulative probability topP (default 1). |
| - Frequency Penalty | Penalizes new tokens based on their existing frequency in the text to reduce repetition (default 0). |
| - Presence Penalty | Penalizes new tokens based on whether they appear in the text at all to encourage topic diversity (default 0). |
Output
The node outputs data under the json field containing the AI-generated completion response. This includes the textual result produced by the selected Ittes AI model based on the input parameters.
No binary data output is indicated by the source code.
Dependencies
- Requires an API key credential for authenticating with the Ittes AI service.
- The node dynamically fetches available models from the Ittes AI API endpoint
/api/n8n/models. - Network access to the Ittes AI API URL configured in the credentials is necessary.
Troubleshooting
Common issues:
- Failure to fetch models: Could be due to invalid API credentials, network issues, or API endpoint changes.
- Empty or invalid model selection: Ensure a valid model is selected from the dynamically loaded list.
- API request errors: Check that the API key is correct and has sufficient permissions.
Error messages:
- "No models found" — Indicates the API did not return any models; verify API availability and credentials.
- "Error fetching models" — Includes error details; check logs and ensure proper API key and URL configuration.