Analyze Sentiment
azure_language.analyze_sentiment
ActionMicrosoft Azureconnection required
Calls the Azure AI Language :analyze-text endpoint (api-key auth).
Classify the sentiment of text with Azure AI Language.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Azure AI Language
- Secret shape
- the Azure AI Language API key
- Config it needs
- azure_endpoint
- Resolved by
- config.connection_id, else node.connection_id
Configuration
2 fields, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
text Text to analyse. Supports {{ }}. | string | Yes | — | — | — |
language Language code (default en). | string | No | en | — | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"language": "en"
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
sentiment | string | — |
scores | object | — |
{
"scores": {},
"sentiment": ""
}See Analyze Sentiment run in a workflow.
In a technical demo we add the Azure AI Language connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.