1---2name: azure-language-service3description: Expert knowledge for Azure AI Language development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building CLU intents, custom NER, text classification, CQA, sentiment/summarization, or health text solutions, and other Azure AI Language related development tasks. Not for Azure AI Search (use azure-cognitive-search), Azure AI Document Intelligence (use azure-document-intelligence), Azure AI Speech (use azure-speech), Azure Translator (use azure-translator).4---5# Azure AI Language Skill67This skill provides expert guidance for Azure AI Language. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.89## How to Use This Skill1011> **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file1213> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)1415This skill requires **network access** to fetch documentation content:16- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.17- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.1819## Category Index2021| Category | Lines | Description |22|----------|-------|-------------|23| Troubleshooting | L37-L42 | Diagnosing and fixing common errors, low-accuracy results, and configuration issues in custom text classification and custom question answering projects in Azure AI Language. |24| Best Practices | L43-L60 | Best practices for designing, labeling, and evaluating CLU, custom NER, text classification, and CQA projects, including multilingual handling, emojis, schemas, and autolabeling. |25| Decision Making | L61-L70 | Guidance on choosing regions and resources, lifecycle policies, and migration paths from LUIS, QnA Maker, Text Analytics, and Language Studio to Azure Language and Microsoft Foundry |26| Architecture & Design Patterns | L71-L77 | Architectural guidance for CLU and custom text classification: choosing CLU vs orchestration workflows, and designing regional backup, redundancy, and failover strategies. |27| Limits & Quotas | L78-L95 | Limits, quotas, and language/region support for Azure AI Language features (CLU, NER, classification, PII, CQA), including data size, rate, throughput, and container request limits. |28| Security | L96-L105 | Security for Azure AI Language: encryption at rest, customer-managed keys, RBAC, managed identities, SAS tokens, and network isolation/Private Link for CQA resources. |29| Configuration | L106-L133 | Configuring Azure AI Language projects and containers: CLU, custom NER, text classification, CQA, sentiment, summarization, health, data formats, resources, and runtime settings. |30| Integrations & Coding Patterns | L134-L165 | How to call Azure Language/CLU/Health/Summarization/CQA APIs and SDKs, wire them into bots, Power Automate, and Foundry, and correctly handle async, parameters, and outputs |31| Deployment | L166-L175 | How to deploy and run Azure AI Language models (custom classification, NER, QnA, key phrases, language detection) across regions, containers, AKS, and migrate projects/resources. |3233### Troubleshooting34| Topic | URL |35|-------|-----|36| Resolve common issues in custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/faq |37| Troubleshoot common issues in custom question answering | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |3839### Best Practices40| Topic | URL |41|-------|-----|42| Handle multilingual and emoji offsets in Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/multilingual-emoji-support |43| Apply CLU conversational design best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices |44| Implement multilingual CLU projects effectively | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/multiple-languages |45| Design effective CLU project schemas | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/build-schema |46| Tag and label utterances for CLU training | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/tag-utterances |47| Interpret and stabilize CLU model evaluations | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/view-model-evaluation |48| Prepare data and design schemas for custom NER | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/design-schema |49| Label data effectively for custom NER training | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/tag-data |50| Use autolabeling to accelerate custom NER annotation | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/use-autolabeling |51| Prepare data and design schemas for text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/design-schema |52| Label data effectively for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/tag-data |53| Implement best practices for CQA project quality | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices |54| Apply project authoring best practices in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/best-practices |55| Apply document format guidelines for CQA imports | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/reference/document-format-guidelines |5657### Decision Making58| Topic | URL |59|-------|-----|60| Understand Azure Language model lifecycle policies | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/model-lifecycle |61| Choose Azure regions for Language service features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support |62| Migrate Azure Language Studio projects to Microsoft Foundry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/migration-studio-to-foundry |63| Choose and manage Azure resources for CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/azure-resources |64| Decide migration from LUIS and QnA Maker to Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate |65| Migrate Text Analytics apps to Azure Language API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate-language-service-latest |6667### Architecture & Design Patterns68| Topic | URL |69|-------|-----|70| Choose CLU vs orchestration workflow architecture | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/app-architecture |71| Design CLU regional backup and failover | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/fail-over |72| Design regional fail-over for custom text classification solutions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/fail-over |7374### Limits & Quotas75| Topic | URL |76|-------|-----|77| Data size and rate limits for Azure Language features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/data-limits |78| Train and manage CLU model jobs and limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/train-model |79| Apply CLU Docker container request limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/use-containers |80| Apply CLU data, region, and throughput limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/service-limits |81| Check language and region support for custom NER | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/language-support |82| Language support matrix for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/language-support |83| Review custom text classification data and rate limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/service-limits |84| Check language support for entity linking API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/language-support |85| Check language support for key phrase extraction | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support |86| Review language detection supported languages and codes | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/language-support |87| Review language support for Named Entity Recognition | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/language-support |88| Review orchestration workflow data and throughput limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/service-limits |89| Apply PII container per-call character and document limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/use-containers |90| Service limits and boundaries for CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/limits |9192### Security93| Topic | URL |94|-------|-----|95| Understand Language service data-at-rest encryption | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/encryption-data-at-rest |96| Apply Azure RBAC to Azure Language resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/role-based-access-control |97| Use managed identities for Language Blob access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/managed-identities |98| Create SAS tokens for Language Blob access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/shared-access-signatures |99| Configure data-at-rest encryption and CMK for CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/encrypt-data-at-rest |100| Configure network isolation and Private Link for CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/network-isolation |101102### Configuration103| Topic | URL |104|-------|-----|105| Configure Azure resources for CLU fine-tuning | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-azure-resources |106| Configure Azure Language service containers | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-containers |107| Format data correctly for CLU projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/data-formats |108| Configure and use CLU None intent | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/none-intent |109| Use CLU prebuilt entity components | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/prebuilt-component-reference |110| Create custom NER projects and configure Azure resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/create-project |111| Configure and run Custom NER Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/use-containers |112| Use required data formats for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/concepts/data-formats |113| Set up resources and create custom text classification projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/create-project |114| Configure and run training jobs for text classification models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/train-model |115| View and interpret evaluation metrics for text classification models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/view-model-evaluation |116| Map NER entity types and tags across API versions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/ga-preview-mapping |117| Configure NER skill parameters and inference options | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to/skill-parameters |118| Understand and configure confidence scores in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/confidence-score |119| Enable diagnostics and run analytics for CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/analytics |120| Customize default answer behavior in CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/change-default-answer |121| Add and configure chitchat personas in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/chit-chat |122| Configure Azure resources and permissions for CQA fine-tuning | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/configure-azure-resources |123| Configure smart URL refresh for CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/smart-url-refresh |124| Use supported markdown formats in CQA answers | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/reference/markdown-format |125| Run Sentiment Analysis Docker containers | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers |126| Run Summarization Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/summarization/how-to/use-containers |127| Configure Text Analytics for health containers | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/how-to/configure-containers |128| Run Text Analytics for health containers | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/how-to/use-containers |129130### Integrations & Coding Patterns131| Topic | URL |132|-------|-----|133| Integrate Azure Language SDK and REST APIs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/developer-guide |134| Use Azure Language features asynchronously | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/use-asynchronously |135| Call CLU prediction APIs and SDKs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/call-api |136| Integrate CLU with Bot Framework SDK | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/tutorials/bot-framework |137| Start building custom NER models via Foundry or REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/quickstart |138| Send prediction requests to custom text classification deployments | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/call-api |139| Call the entity linking API with correct parameters | https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/how-to/call-api |140| Call entity linking via SDKs and REST API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/quickstart |141| Call the key phrase extraction API correctly | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/call-api |142| Use key phrase extraction via .NET client library | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/quickstart |143| Call language detection API and interpret results | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/how-to/call-api |144| Implement language detection using SDKs and REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/quickstart |145| Call the NER API to extract named entities | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to-call |146| Use the NER client library to extract entities | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/quickstart |147| Use native document support with Language APIs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/overview |148| Use the CQA Authoring API for automated management | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/authoring |149| Call the prebuilt CQA API for ad-hoc answering | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/prebuilt |150| Call Sentiment and Opinion Mining APIs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/call-api |151| Call Sentiment Analysis via SDK and REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/quickstart |152| Call conversation summarization API for chats | https://learn.microsoft.com/en-us/azure/ai-services/language-service/summarization/how-to/conversation-summarization |153| Summarize native documents via API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/summarization/how-to/document-summarization |154| Use extractive text summarization API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/summarization/how-to/text-summarization |155| Use Azure Summarization via SDK and REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/summarization/quickstart |156| Enable FHIR structuring in health API output | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/fhir |157| Interpret relation extraction JSON output | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/relation-extraction |158| Call Text Analytics for health API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/how-to/call-api |159| Quickstart Text Analytics for health via SDK/REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/quickstart |160| Use Azure Language in Power Automate flows | https://learn.microsoft.com/en-us/azure/ai-services/language-service/tutorials/power-automate |161162### Deployment163| Topic | URL |164|-------|-----|165| Deploy custom language projects to multiple regions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/custom-features/multi-region-deployment |166| Deploy custom text classification models for prediction | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/how-to/deploy-model |167| Run key phrase extraction in Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/use-containers |168| Deploy language detection with Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/how-to/use-containers |169| Deploy NER with Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to/use-containers |170| Move custom question answering projects between resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/migrate-knowledge-base |171| Deploy Language containers to Azure Kubernetes Service | https://learn.microsoft.com/en-us/azure/ai-services/language-service/tutorials/use-kubernetes-service |
luokai0