/azure-language-service

name: azure-language-service
description: 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 using CLU, custom/health NER, CQA, sentiment/PII APIs, or Language/TA/health containers, 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 Speech in Foundry Tools (use azure-speech), Azure Translator (use azure-translator).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-09-13"
  generator: "docs2skills/1.0.0"

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 Azure Language custom NER and conversational question answering (CQA), including model errors, configuration problems, and troubleshooting workflows. | | Best Practices | L43-L53 | Best practices for designing and authoring CLU, custom NER, PII, and CQA projects, including data prep, schemas, lifecycles, chitchat personas, and document formatting. | | Decision Making | L54-L63 | Guides for choosing regions and app types, planning CQA solutions, and deciding or executing migrations from LUIS, QnA Maker, Text Analytics, and Language Studio to Azure Language/Fountry. | | Architecture & Design Patterns | L64-L71 | Designing and implementing regional failover and high-availability patterns for CLU, custom NER, custom text classification, and orchestration workflow models in Azure AI Language. | | Limits & Quotas | L72-L95 | Limits, quotas, languages, and model lifecycles for Azure Language features (CLU, NER, text classification, CQA, health), including data size, rate, throughput, and container constraints. | | Security | L96-L107 | Securing Azure Language and CQA: encryption at rest (including CMK), RBAC, managed identities, SAS tokens, network isolation/Private Link, and secure deployment/data access configuration. | | Configuration | L108-L124 | Configuring Azure AI Language features: CLU fine-tuning, containers, custom/health NER, orchestration None intent, CQA scoring/telemetry, FHIR output, and related project/skill settings. | | Integrations & Coding Patterns | L125-L144 | How to call Azure Language/TA/health/CLU/CQA APIs and SDKs for NER, entity linking, key phrases, language detection, sentiment, PII redaction, relations, and orchestration workflows. | | Deployment | L145-L155 | Guides for deploying and running custom language/NER/CQA/sentiment/health models across regions, on-prem via Docker containers, and moving projects between environments. |

Troubleshooting

| Topic | URL | |-------|-----| | Resolve common issues with custom NER in Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/faq | | Troubleshoot common CQA issues and errors | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |

Best Practices

| Topic | URL | |-------|-----| | Apply CLU project authoring best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices | | Adapt PII detection to custom domain terminology | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/adapt-to-domain-pii | | Implement CQA project best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices | | Follow CQA project development lifecycle | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/project-development-lifecycle | | Apply authoring best practices to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/best-practices | | Add chitchat personas to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/chit-chat | | Apply document formatting best practices for custom Q&A | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/reference/document-format-guidelines |

Decision Making

| Topic | URL | |-------|-----| | Choose Azure regions for Language service features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/re