Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Use this article to find information on integrating Azure Language SDK and REST API into your applications.
Development options
Language service supports development through Microsoft Foundry, REST APIs, and client libraries in several languages.
Microsoft Foundry
Microsoft Foundry provides a guided development experience for building, testing, and deploying Language solutions without writing initial integration code. You can use Foundry to configure resources, create and manage projects, and validate model behavior before integrating with SDK or REST-based production workflows.
To get started with feature-specific Foundry workflows, see:
Client libraries (Azure SDK)
The Language provides three namespaces for using the available features. Depending on which features and programming language you're using, you need to download one or more of the following packages, and have the following framework/language version support:
| Framework/Language | Minimum supported version |
|---|---|
| .NET | .NET Framework 4.6.1 or newer, or .NET (formerly .NET Core) 2.0 or newer. |
| Java | v8 or later |
| JavaScript | v14 LTS or later |
| Python | v3.7 or later |
Azure.AI.TextAnalytics
Note
If you're using custom named entity recognition or custom text classification, you need to create a project and train a model before using the SDK. The SDK only allows for you to analyze text using models you create. See the following quickstarts for information on creating a model.
The Azure.AI.TextAnalytics namespace enables you to use the following Language features. Use the following links for articles to help you send API requests using the SDK.
- Custom named entity recognition
- Custom text classification
- Document summarization
- Entity linking
- Key phrase extraction
- Named entity recognition (NER)
- Personally Identifying Information (PII) detection
- Sentiment analysis and opinion mining
- Text analytics for health
As you use these features in your application, use the following documentation and code samples for additional information.
| Language → Latest GA version | Reference documentation | Samples |
|---|---|---|
| C#/.NET → v5.2.0 | C# documentation | C# samples |
| Java → v5.2.0 | Java documentation | Java Samples |
| JavaScript → v1.0.0 | JavaScript documentation | JavaScript samples |
| Python → v5.2.0 | Python documentation | Python samples |
Azure.AI.Language.Conversations
Note
If you're using conversational language understanding or orchestration workflow, you need to create a project and train a model before using the SDK. The SDK only allows you to analyze text using models you create. For more information, see:
The Azure.AI.Language.Conversations namespace enables you to use the following Language features. Use the following links for articles to help you send API requests using the SDK.
- Conversational language understanding
- Orchestration workflow
- Conversation summarization (Python only)
- Personally Identifying Information (PII) detection for conversations
As you use these features in your application, use the following documentation and code samples for additional information.
| Language → Latest GA version | Reference documentation | Samples |
|---|---|---|
| C#/.NET → v1.0.0 | C# documentation | C# samples |
| Python → v1.0.0 | Python documentation | Python samples |
Azure.AI.Language.QuestionAnswering
The Azure.AI.Language.QuestionAnswering namespace enables you to use the following Language features:
- Question answering
- Authoring - Automate common tasks like adding new question answer pairs and working with projects/knowledge bases.
- Prediction - Answer questions based on passages of text.
As you use these features in your application, use the following documentation and code samples for additional information.
| Language → Latest GA version | Reference documentation | Samples |
|---|---|---|
| C#/.NET → v1.0.0 | C# documentation | C# samples |
| Python → v1.0.0 | Python documentation | Python samples |
REST API
The Language provides multiple API endpoints depending on which feature you wish to use.
Conversation analysis authoring API
The conversation analysis authoring API enables you to author custom models and create/manage projects for the following features.
For more information, see the reference documentation.
Conversation analysis runtime API
The conversation analysis runtime API enables you to send requests to custom models you create for the following features:
It additionally enables you to use the following features, without creating any models:
For more information, see the reference documentation.
Text analysis authoring API
The text analysis authoring API enables you to author custom models and create/manage projects for:
For more information, see the reference documentation.
Text analysis runtime API
The text analysis runtime API enables you to send requests to custom models you create for the following features:
It additionally enables you to use the following features, without creating any models:
- Document summarization
- Entity linking
- Key phrase extraction
- Named entity recognition (NER)
- Personally Identifying Information (PII) detection
- Sentiment analysis and opinion mining
- Text analytics for health
For more information, see the reference documentation.
Question answering APIs
The question answering APIs enables you to use the question answering feature.
Reference documentation
For more information, see the following reference documentation:
- Prebuilt API - Use the prebuilt runtime API to answer specified question using text provided by users.
- Custom authoring API - Create a knowledge base to answer questions.