Cognitive Services Models
Overview
This page describes object types returned by Azure AI Foundry workflow activities.
Use these models when binding activity outputs in the Process Data drawer or when mapping results in downstream activities.
AnalyzeSentimentResult
Returned by Analyze Sentiment as Analyze Sentiment Result.
Properties
| Property | Type | Description |
|---|---|---|
| Sentiment | String | Overall sentiment: Positive, Negative, Neutral, or Mixed. |
| PositiveScore | Double | Confidence that the sentiment is positive (0 to 1). |
| NegativeScore | Double | Confidence that the sentiment is negative (0 to 1). |
| NeutralScore | Double | Confidence that the sentiment is neutral (0 to 1). |
| MixedScore | Double | Confidence that the sentiment is mixed (0 to 1). |
| Sentences | List<SentimentSentence> | Sentence-level sentiment details. |
SentimentSentence
Represents sentiment information for a single sentence within AnalyzeSentimentResult.Sentences.
Properties
| Property | Type | Description |
|---|---|---|
| Sentence | String | Text of the sentence. |
| Sentiment | String | Sentiment detected for the sentence. |
| PositiveScore | Double | Confidence that the sentiment is positive (0 to 1). |
| NegativeScore | Double | Confidence that the sentiment is negative (0 to 1). |
| NeutralScore | Double | Confidence that the sentiment is neutral (0 to 1). |
| MixedScore | Double | Confidence that the sentiment is mixed (0 to 1). |
| Length | Int32 | Length of the sentence text. |
| Offset | Int32 | Starting position of the sentence within the input text. |
DetectLanguageResult
Returned by Detect Language as Detect Language Result.
Properties
| Property | Type | Description |
|---|---|---|
| Language | String | Detected language name (for example, English). |
| LanguageCode | String | ISO 639-1 language code (for example, en). |
| ConfidenceScore | Double | Confidence of the language detection (0 to 1). |
Entity
Base type for extracted entities.
Used by:
- Recognize Entities
- Recognize PII Entities
Properties
| Property | Type | Description |
|---|---|---|
| Text | String | Detected entity text. |
| ConfidenceScore | Double | Confidence of the detection (0 to 1). |
| Length | Int32 | Length of the entity text. |
| Offset | Int32 | Starting position of the entity within the input text. |
CategorizedEntity
Returned in Categorized Entities and PII Entities collections.
Extends Entity with category information.
Properties
| Property | Type | Description |
|---|---|---|
| Text | String | Detected entity text. |
| ConfidenceScore | Double | Confidence of the detection (0 to 1). |
| Length | Int32 | Length of the entity text. |
| Offset | Int32 | Starting position of the entity within the input text. |
| Category | String | Entity category. |
| SubCategory | String | Entity subcategory, when available. |
AnalyzeResult
Returned by Analyze Document as Analyze Result.
Represents the top-level output of document analysis.
Properties
| Property | Type | Description |
|---|---|---|
| ApiVersion | String | API version used for the analysis. |
| ModelId | String | Model identifier used for the analysis. |
| Content | String | Extracted text content from the document. |
| ContentFormat | String | Format of the extracted content. |
| Pages | List | Document pages with layout and text details. |
| Paragraphs | List | Paragraphs detected in the document. |
| Tables | List | Tables detected in the document. |
| Figures | List | Figures detected in the document, when available. |
| Sections | List | Document sections, when available. |
| KeyValuePairs | List | Key-value pairs detected when the feature is enabled. |
| Styles | List | Style information detected when the feature is enabled. |
| Languages | List | Languages detected when the feature is enabled. |
| Documents | List | Structured fields extracted for the selected document type. |
Usage Notes
The structure of nested page, table, paragraph, figure, and document field objects is defined by Azure AI Foundry Document Intelligence.
Refer to the Azure AI Foundry documentation for detailed schema information.