Overview
This node integrates with MakeHub AI's language models to perform chat-based interactions. It allows users to send prompts and receive generated text completions from a selected MakeHub AI model. This is useful for automating conversational tasks, generating content, or building AI-driven assistants within n8n workflows.
Common scenarios include:
- Creating chatbots that respond to user queries.
- Generating text based on prompts for content creation.
- Enhancing automation workflows with AI-generated insights or replies.
For example, you could use this node to generate customer support responses dynamically or to brainstorm ideas by feeding prompts into the AI model.
Properties
Name | Meaning |
---|---|
Ce nœud peut être connecté à: Nœuds de chaîne AI, Agents AI | Notice indicating this node can connect to AI Chain nodes or AI Agent nodes. |
Model | Choose the MakeHub AI language model to use. The list is dynamically loaded from the MakeHub API. |
Options | Additional options to customize the request: - Max Retries: Maximum retry attempts (default 2) - Maximum Number of Tokens: Max tokens to generate (default 1024) - Sampling Temperature: Controls randomness (0 to 2, default 0.7) - Stream: Whether to stream partial results (boolean) - System Prompt: System message to set assistant behavior - Timeout: Max request time in milliseconds (default 360000) |
Min Throughput Settings | Configure minimum throughput: - Mode: Best Price, Custom Value, or Best Performance - Min Throughput: Custom tokens/sec value (shown if Custom selected) |
Max Latency Settings | Configure maximum latency: - Mode: Best Price, Custom Value, or Best Performance - Max Latency: Custom max latency in ms (shown if Custom selected) |
Output
The node outputs data under the json
field containing the AI model's response. The output structure includes the generated text completion from the MakeHub AI chat model.
If streaming is enabled, partial progress updates may be streamed back during execution.
No binary data output is indicated.
Dependencies
- Requires an API key credential for authenticating with the MakeHub AI service.
- Connects to the MakeHub AI API at
https://api.makehub.ai/v1
. - Uses the
@langchain/openai
package internally to interface with the MakeHub API.
Troubleshooting
- Missing API Key: If no valid API key is provided, the node throws an error indicating the missing credential. Ensure the API key is configured correctly in n8n credentials.
- Timeouts: Requests may fail if the timeout is too low. Adjust the "Timeout" property to allow sufficient time for responses.
- Invalid Model Selection: Selecting a model not available or supported by MakeHub will cause errors. Use the dropdown to select from the dynamically loaded list.
- Retries Exhausted: If the node fails repeatedly, check network connectivity and API limits; increase "Max Retries" if needed.
- Streaming Issues: Enabling streaming requires compatible downstream nodes; otherwise, partial data may not be handled properly.
Links and References
- MakeHub AI Documentation
- MakeHub AI API base URL:
https://api.makehub.ai/v1