AI Processor
The AI Processor sends data through an Analytics flow to an AI model and returns the model's response. Use it to generate natural language output, summarize or classify incoming data, or extract structured JSON from raw data, without writing custom code.
Why use the AI Processor
Use the AI Processor when a flow needs to interpret or transform data using natural language rather than fixed logic, for example, summarizing sensor readings, classifying an event from its description, or pulling structured fields out of unstructured text.
The processor's parameters let you tune the model's behavior for your use case:
- Set a System Prompt to enforce a consistent tone, persona, or domain expertise across every response.
- Adjust Temperature to trade consistency for creativity, or the reverse.
- Enable Force Response Format to JSON? when the result needs to feed directly into downstream processing.
Parameters
Parameter | Details |
|---|---|
Name | The unique identifier for this instance of the AI Processor. |
AI Model | The AI model used to generate responses. |
HTTP Timeout | The maximum time (in seconds) to wait for a response from the model before the request times out and is ignored. |
System Prompt | A predefined instruction that shapes the model's tone, persona, or domain expertise for every response. |
Temperature | Controls the randomness of responses. Lower values (for example, 0.2) produce more focused, deterministic output. Higher values (for example, 1.8) produce more varied, creative output. Default: 1.0. |
Max Completion Tokens | Limits the number of tokens the model can generate in a single response. If not set, the model's default applies. |
Time Interval | Duration or frequency at which certain operations or requests should occur. |
Force Response Format to JSON? | When enabled, the model returns only valid JSON. When disabled, the model follows its default output style. See the important note below. |
Pass Through Value | Determines whether the processor's output is the model's response or the original unchanged input value. |
Important: If you enable Force Response Format to JSON?, you must also instruct the model to produce JSON yourself, through a system or user message. Enabling the parameter alone doesn't guarantee JSON output.