1---
2name: azure-language-service
3description: 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, CQA, health text, sentiment/PII, or orchestration workflows, and other Azure AI Language related development tasks. Not for Azure AI Search (use azure-cognitive-search), Azure Speech in Foundry Tools (use azure-speech), Azure Translator (use azure-translator), Azure AI Document Intelligence (use azure-document-intelligence).
4compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
5metadata:
6 generated_at: "2026-08-31"
7 generator: "docs2skills/1.0.0"
8---
9
10# Azure AI Language Skill
11
12This 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.
13
14## How to Use This Skill
15
16> **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
17
18> **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)
19
20This skill requires **network access** to fetch documentation content:
21- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
22- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.
23
24## Category Index
25
26| Category | Lines | Description |
27|----------|-------|-------------|
28| 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. |
29| 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. |
30| 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. |
31| 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. |
32| 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. |
33| 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. |
34| Configuration | L108-L125 | Configuring Azure AI Language features and runtime: CLU fine-tuning, NER formats/metadata, CQA behavior/telemetry, health/FHIR output, and container settings. |
35| Integrations & Coding Patterns | L126-L145 | 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. |
36| Deployment | L146-L156 | Guides for deploying and running custom language/NER/CQA/sentiment/health models across regions, on-prem via Docker containers, and moving projects between environments. |
37
38### Troubleshooting
39| Topic | URL |
40|-------|-----|
41| 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 |
42| Troubleshoot common CQA issues and errors | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |
43
44### Best Practices
45| Topic | URL |
46|-------|-----|
47| Apply CLU project authoring best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices |
48| 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 |
49| Implement CQA project best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices |
50| Follow CQA project development lifecycle | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/project-development-lifecycle |
51| Apply authoring best practices to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/best-practices |
52| Add chitchat personas to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/chit-chat |
53| 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 |
54
55### Decision Making
56| Topic | URL |
57|-------|-----|
58| Choose Azure regions for Language service features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support |
59| Choose CLU app vs orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/app-architecture |
60| Migrate Azure Language Studio projects to Microsoft Foundry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/migration-studio-to-foundry |
61| Plan a CQA app and select Azure resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/plan |
62| Decide migration from LUIS and QnA Maker to Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate |
63| Migrate Text Analytics apps to Azure Language API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate-language-service-latest |
64
65### Architecture & Design Patterns
66| Topic | URL |
67|-------|-----|
68| Design regional failover for CLU models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/fail-over |
69| Design regional failover for custom NER models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/fail-over |
70| Design regional failover for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/fail-over |
71| Implement regional failover for orchestration workflow models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/concepts/fail-over |
72
73### Limits & Quotas
74| Topic | URL |
75|-------|-----|
76| Data size and rate limits for Azure Language features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/data-limits |
77| Understand lifecycle timelines for Azure Language models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/model-lifecycle |
78| Use CLU containers with on-premises limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/use-containers |
79| Check CLU supported languages and locales | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/language-support |
80| Reference CLU prebuilt entity components | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/prebuilt-component-reference |
81| Review CLU data and throughput limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/service-limits |
82| Manage custom NER training jobs and expiration | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/train-model |
83| Check language support matrix for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/language-support |
84| Review data and rate limits for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/service-limits |
85| Check language support for entity linking | https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/language-support |
86| Review language support for Key Phrase Extraction | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support |
87| Understand entity categories and types in NER | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/named-entity-categories |
88| Check language support for Azure NER feature | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/language-support |
89| Check language support for orchestration workflow projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/language-support |
90| Review data and throughput limits for orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/service-limits |
91| Understand PII detection container data limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/use-containers |
92| Understand CQA project and service limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/limits |
93| Review language support for CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/language-support |
94| Explore medical entity categories in health analytics | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/health-entity-categories |
95| Review language support for Text Analytics for health | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/language-support |
96
97### Security
98| Topic | URL |
99|-------|-----|
100| Understand data-at-rest encryption in Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/encryption-data-at-rest |
101| Configure RBAC for Azure Language resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/role-based-access-control |
102| Use managed identities to secure storage blob access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/managed-identities |
103| Configure SAS tokens for Azure storage blobs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/shared-access-signatures |
104| Configure Azure resources for CQA fine-tuning | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/configure-azure-resources |
105| Configure CMK encryption for CQA data at rest | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/encrypt-data-at-rest |
106| Enable network isolation and Private Link for CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/network-isolation |
107| Secure Azure Language deployments and data access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/secure-deployment |
108
109### Configuration
110| Topic | URL |
111|-------|-----|
112| Configure Azure resources for CLU fine-tune models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-azure-resources |
113| Configure Azure Language service containers settings | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-containers |
114| Use supported data formats for custom NER | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/concepts/data-formats |
115| Use NER entity metadata and resolutions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/entity-metadata |
116| Map NER API versions and entity tags/types | 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| Configure the None intent behavior in orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/concepts/none-intent |
119| Interpret and configure CQA confidence scores | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/confidence-score |
120| Enable and query CQA analytics telemetry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/analytics |
121| Configure default answer behavior in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/change-default-answer |
122| Manage CQA project settings and sources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/manage-knowledge-base |
123| Use assertion detection in Text Analytics for health | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/assertion-detection |
124| Configure FHIR structuring in health analytics output | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/fhir |
125| Configure Text Analytics for health container settings | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/how-to/configure-containers |
126
127### Integrations & Coding Patterns
128| Topic | URL |
129|-------|-----|
130| Integrate Azure Language via SDK and REST APIs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/developer-guide |
131| Call custom NER prediction API and SDK | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/call-api |
132| 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 |
133| 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 |
134| Invoke the Key Phrase Extraction API correctly | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/call-api |
135| Implement language detection using SDKs and REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/quickstart |
136| Perform NER calls with Azure Language service | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to-call |
137| Build a .NET app using NER client library | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/quickstart |
138| Integrate CLU and custom Q&A via orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/tutorials/connect-services |
139| Redact PII from native documents with Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/redact-document-pii |
140| Automate CQA authoring with REST API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/authoring |
141| Use the CQA prebuilt answering API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/prebuilt |
142| Call sentiment analysis and opinion mining APIs correctly | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/call-api |
143| Use relation extraction in Text Analytics for health | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/relation-extraction |
144| 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 |
145| Quickstart integrating Text Analytics for health | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/quickstart |
146
147### Deployment
148| Topic | URL |
149|-------|-----|
150| Deploy custom language projects to multiple regions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/custom-features/multi-region-deployment |
151| Deploy custom NER with Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/how-to/use-containers |
152| Deploy Key Phrase Extraction containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/use-containers |
153| Run NER Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to/use-containers |
154| Create and deploy a CQA agent in Foundry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/deploy-agent |
155| Move CQA projects between environments | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/migrate-knowledge-base |
156| Deploy Sentiment Analysis containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers |
157| Deploy Text Analytics for health containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/how-to/use-containers |
microsoftdocs