azure-language-service

What this skill does

# Azure AI Language Skill

This 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.

## How to Use This Skill

> **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 file

> **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)

This skill requires **network access** to fetch documentation content:
- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.

## Category Index

| Category | Lines | Description |
|----------|-------|-------------|
| Troubleshooting | L37-L42 | Diagnosing and fixing common issues in custom text classification and custom question answering, including model performance, configuration, and runtime/response problems. |
| Best Practices | L43-L59 | Best practices for designing, labeling, and evaluating CLU, custom NER, text classification, and CQA projects, including multilingual handling, emojis, schemas, and autolabeling. |
| Decision Making | L60-L69 | 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 |
| Architecture & Design Patterns | L70-L76 | Architectural guidance for CLU and custom text classification: choosing CLU vs orchestration workflows, and designing regional backup, redundancy, and failover strategies. |
| Limits & Quotas | L77-L95 | Limits, quotas, and language/region support for Azure AI Language features (CLU, NER, PII, key phrases, QnA), including data sizes, throughput, containers, and training job constraints. |
| Security | L96-L106 | Security, encryption, and access control for Azure AI Language: RBAC, managed identities, SAS, CMK/data-at-rest, network isolation, Private Link, and CQA-specific security setup. |
| Configuration | L107-L131 | Configuring Azure AI Language/CLU/NER/CQA projects and containers, including data formats, resources, Docker/on-prem setups, metrics, confidence scores, PII redaction, and sentiment/summarization. |
| Integrations & Coding Patterns | L132-L163 | Implementing Azure AI Language features via REST/SDKs: CLU, custom NER/classification, CQA, sentiment, summarization, health, entity linking, and integrating with bots/Power Automate. |
| Deployment | L164-L173 | 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. |

### Troubleshooting
| Topic | URL |
|-------|-----|
| Resolve common issues in custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/faq |
| Diagnose and resolve custom question answering issues | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |

### Best Practices
| Topic | URL |
|-------|-----|
| Handle multilingual and emoji offsets in Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/multilingual-emoji-support |
| Apply CLU conversational design best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices |
| Implement multilingual CLU projects effectively | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/multiple-languages |
| Design effective CLU project schemas | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/build-schema |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| Implement best practices for CQA project quality | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices |
| Apply project authoring best practices in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/best-practices |

### Decision Making
| Topic | URL |
|-------|-----|
| Understand Azure Language model lifecycle policies | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/model-lifecycle |
| Choose Azure regions for Language service features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support |
| Migrate Azure Language Studio projects to Microsoft Foundry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/migration-studio-to-foundry |
| Choose and manage Azure resources for CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/azure-resources |
| Decide migration from LUIS and QnA Maker to Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate |
| Migrate Text Analytics apps to Azure Language API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate-language-service-latest |

### Architecture & Design Patterns
| Topic | URL |
|-------|-----|
| Choose CLU vs orchestration workflow architecture | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/app-architecture |
| Design CLU regional backup and failover | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/fail-over |
| 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 |

### Limits & Quotas
| Topic | URL |
|-------|-----|
| Data size and rate limits for Azure Language features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/data-limits |
| Train and manage CLU model jobs and limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/h