dendi-wang/thingsboard
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

AI rule node: correct markdown prompt settings example

Browse Source
This commit is contained in:
Dmytro Skarzhynets 2025-07-14 16:34:34 +03:00
parent 46bdbbdb05
commit c48ce6fd12
No known key found for this signature in database
GPG Key ID: 2B51652F224037DF
1 changed files with 15 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
ui-ngx/src/assets/help/en_US/rulenode/ai_node_prompt_settings.md
View File

@ -1,19 +1,15 @@
#### Example Usage: AI-Powered Alarm Analysis
This example demonstrates how to use the AI node to automatically analyze a new device alarm, generate a human-readable summary, and suggest troubleshooting steps.
This example demonstrates how to use the AI node to automatically analyze a new device alarm, generate a human-readable summary, and suggest troubleshooting steps.
This is useful for creating enriched notifications or populating a dashboard widget.
#### Scenario
##### Scenario
An IoT freezer unit generates a "High Temperature" alarm. We want the AI to process this alarm data to create a clear summary and a recommended action plan for an operator.
1. Incoming Message Structure
1. **Incoming message structure**
When the alarm is created, the message sent through the rule chain has the following structure:
Message body (represent an alarm, usual alarm fields omitted for brevity)
Message body (represents an alarm, some alarm fields omitted for brevity):
```json
{
"type": "High Temperature",
"details": {
"currentTemp_C": -5,
"threshold_C": -18
@ -21,7 +17,7 @@ Message body (represent an alarm, usual alarm fields omitted for brevity)
}
```
Message metadata
Message metadata:
```json
{
"deviceName": "Freezer-B7",
@ -29,12 +25,11 @@ Message metadata
}
```
2. To achieve our goal, we configure the two prompt fields as follows:
2. **Prompt configuration**
**System prompt**
Here, we set the AI's role and enforce a strict JSON output format. This ensures the output is always machine-parsable.
```
You are an expert AI assistant for IoT operations.
Your task is to analyze device data and respond with a single, valid JSON object.
@ -44,7 +39,6 @@ Do not include any text, explanations, or markdown formatting before or after th
**User prompt**
This prompt defines the specific task, using templates to dynamically insert data from the incoming alarm message.
```
Analyze the following alarm from a "${deviceType}" unit named "${deviceName}".
@ -56,18 +50,19 @@ Based on the alarm data, generate a JSON object with two keys:
2. "action": A concrete, recommended next step for an operator.
```
3. How It Works
3. **How it works**
When the alarm message from "Freezer-B7" is processed by the AI node, the templates are substituted with the actual data:
- `${deviceName}` becomes "Freezer-B7"
- `${deviceType}` becomes "CommercialFreezer"
- `$[*]` is replaced by the entire message body JSON: `{"alarmType": "High Temperature", "severity": "CRITICAL", "currentTemp_C": -5, "threshold_C": -18}`
- `$[*]` is replaced by the entire message body JSON: `{"type":"High Temperature","details":{"currentTemp_C":-5,"threshold_C":-18}}`
> **Note:** You can also use `$[*]`. In this case, it will be replaced with the entire message metadata JSON.
The final instruction sent to the AI is a combination of the system and the substituted user prompt.
4. Expected AI Output
4. **Expected AI output**
Given the combined instructions, the AI would generate the following structured JSON output, which can then be used in subsequent rule nodes (e.g., to send an enriched email or create a trouble ticket).
Given the combined instructions, the AI would generate the following structured JSON output, which can then be used in subsequent rule nodes (e.g., to send an enriched email).
```json
{
@ -75,3 +70,6 @@ Given the combined instructions, the AI would generate the following structured
"action": "Dispatch technician immediately to inspect the unit's cooling system and ensure the door is properly sealed. Investigate for potential power issues."
}
```
> **Note:** The scenario above is a hypothetical example designed to illustrate the functionality of the node and its templating capabilities.
> The specific details, such as freezer alarms, are used for demonstration purposes and are not intended to suggest or limit the potential use cases.