Overview
This node integrates with the Ittes AI API to generate AI-powered chat completions based on user prompts. It is designed to send a prompt along with various parameters to an AI model hosted by Ittes AI and receive generated text responses.
Common scenarios where this node is beneficial include:
- Automating content creation such as drafting emails, articles, or social media posts.
- Building conversational agents or chatbots that require dynamic AI-generated replies.
- Enhancing workflows with natural language understanding or generation capabilities.
- Experimenting with different AI models and tuning generation parameters for creative or analytical tasks.
For example, a user can input a prompt like "Explain the benefits of renewable energy" and receive a detailed AI-generated explanation. By adjusting parameters like temperature or max tokens, users can control the creativity and length of the output.
Properties
| Name | Meaning |
|---|---|
| Prompt | The text prompt to send to the AI model for generating a response. |
| AI Model | Select which AI model to use for generating the response. Models are dynamically loaded from the API. |
| System Context | Instructions or context provided to the AI model to guide its behavior (default: "You are a helpful AI assistant."). |
| Temperature | Controls randomness in the output; higher values (up to 2) produce more random and creative results. |
| Max Tokens | Maximum number of tokens (words/pieces) the AI should generate in the response (1 to 8192). |
| Additional Fields | Optional advanced parameters including: |
| - Top P | Controls diversity via nucleus sampling (0 to 1). |
| - Frequency Penalty | Penalizes repeated tokens to reduce repetition (-2 to 2). |
| - Presence Penalty | Encourages introduction of new topics (-2 to 2). |
Output
The node outputs JSON data containing the AI-generated response from the Ittes AI API. The exact structure depends on the API's response but typically includes the generated text and possibly metadata about the generation.
If multiple input items are processed, the output is an array where each element corresponds to the respective input item, preserving pairing.
No binary data output is produced by this node.
Dependencies
- Requires an active connection to the Ittes AI API endpoint.
- Needs an API key credential for authentication, passed as a Bearer token in the Authorization header.
- The node dynamically fetches available AI models from the API to populate the model selection dropdown.
- Network access to the configured API URL must be available from the n8n environment.
Troubleshooting
Common Issues:
- Invalid or missing API credentials will cause authentication failures.
- Incorrect API URL configuration may lead to network errors or inability to fetch models.
- Providing unsupported or empty model names can result in API errors.
- Exceeding max tokens limits or invalid parameter ranges may cause request rejections.
Error Messages:
- Errors returned from the API are surfaced as node execution errors with details.
- If
continueOnFailis enabled, errors per item are returned in the output JSON under anerrorfield. - Network or HTTP errors during model fetching or request sending are logged and may appear as "Error fetching models" or similar messages.
Resolutions:
- Verify API key validity and permissions.
- Confirm the API base URL is correct and reachable.
- Use the model dropdown to select valid models rather than typing manually.
- Adjust parameters within allowed ranges as documented.
Links and References
- Ittes AI API Documentation (Assumed placeholder, replace with actual if available)
- OpenAI GPT-like Model Parameters Explanation
- n8n HTTP Request Node Documentation
Note: This summary is based solely on static analysis of the provided source code and property definitions.