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, 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).4---5# Azure AI Language Skill
6
7This 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.
8
9## How to Use This Skill
10
11> **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
12
13> **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)
14
15This 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.
18
19## Category Index
20
21| Category | Lines | Description |
22|----------|-------|-------------|
23| 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. |
24| 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. |
25| 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. |
26| 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. |
27| 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. |
28| 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. |
29| 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. |
30| 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. |
31| 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. |
32
33### Troubleshooting
34| Topic | URL |
35|-------|-----|
36| 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 |
37| Troubleshoot common CQA issues and errors | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |
38
39### Best Practices
40| Topic | URL |
41|-------|-----|
42| Apply CLU project authoring best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices |
43| 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 |
44| Implement CQA project best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices |
45| Follow CQA project development lifecycle | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/project-development-lifecycle |
46| Apply authoring best practices to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/best-practices |
47| Add chitchat personas to CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/chit-chat |
48| 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 |
49
50### Decision Making
51| Topic | URL |
52|-------|-----|
53| Choose Azure regions for Language service features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support |
54| Choose CLU app vs orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/app-architecture |
55| Migrate Azure Language Studio projects to Microsoft Foundry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/migration-studio-to-foundry |
56| Plan a CQA app and select Azure resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/plan |
57| Decide migration from LUIS and QnA Maker to Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate |
58| Migrate Text Analytics apps to Azure Language API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/reference/migrate-language-service-latest |
59
60### Architecture & Design Patterns
61| Topic | URL |
62|-------|-----|
63| Design regional failover for CLU models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/fail-over |
64| Design regional failover for custom NER models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/fail-over |
65| Design regional failover for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/fail-over |
66| Implement regional failover for orchestration workflow models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/concepts/fail-over |
67
68### Limits & Quotas
69| Topic | URL |
70|-------|-----|
71| Data size and rate limits for Azure Language features | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/data-limits |
72| Understand lifecycle timelines for Azure Language models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/model-lifecycle |
73| 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 |
74| Check CLU supported languages and locales | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/language-support |
75| Reference CLU prebuilt entity components | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/prebuilt-component-reference |
76| Review CLU data and throughput limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/service-limits |
77| 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 |
78| Check language support matrix for custom text classification | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/language-support |
79| 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 |
80| Check language support for entity linking | https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/language-support |
81| Review language support for Key Phrase Extraction | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support |
82| 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 |
83| Check language support for Azure NER feature | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/language-support |
84| Check language support for orchestration workflow projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/language-support |
85| Review data and throughput limits for orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/service-limits |
86| Understand PII detection container data limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/use-containers |
87| Understand CQA project and service limits | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/limits |
88| Review language support for CQA projects | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/language-support |
89| 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 |
90| 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 |
91
92### Security
93| Topic | URL |
94|-------|-----|
95| Understand data-at-rest encryption in Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/encryption-data-at-rest |
96| Configure RBAC for Azure Language resources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/role-based-access-control |
97| Use managed identities to secure storage blob access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/managed-identities |
98| Configure SAS tokens for Azure storage blobs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/native-document-support/shared-access-signatures |
99| 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 |
100| 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 |
101| 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 |
102| Secure Azure Language deployments and data access | https://learn.microsoft.com/en-us/azure/ai-services/language-service/secure-deployment |
103
104### Configuration
105| Topic | URL |
106|-------|-----|
107| Configure Azure resources for CLU fine-tune models | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-azure-resources |
108| Configure Azure Language service containers settings | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/configure-containers |
109| 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 |
110| Use NER entity metadata and resolutions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/entity-metadata |
111| 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 |
112| 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 |
113| Configure the None intent behavior in orchestration workflow | https://learn.microsoft.com/en-us/azure/ai-services/language-service/orchestration-workflow/concepts/none-intent |
114| Interpret and configure CQA confidence scores | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/confidence-score |
115| Enable and query CQA analytics telemetry | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/analytics |
116| Configure default answer behavior in CQA | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/change-default-answer |
117| Manage CQA project settings and sources | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/manage-knowledge-base |
118| 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 |
119| Configure FHIR structuring in health analytics output | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/concepts/fhir |
120| 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 |
121
122### Integrations & Coding Patterns
123| Topic | URL |
124|-------|-----|
125| Integrate Azure Language via SDK and REST APIs | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/developer-guide |
126| 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 |
127| 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 |
128| 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 |
129| 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 |
130| Implement language detection using SDKs and REST | https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/quickstart |
131| Perform NER calls with Azure Language service | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to-call |
132| Build a .NET app using NER client library | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/quickstart |
133| 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 |
134| 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 |
135| Automate CQA authoring with REST API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/authoring |
136| Use the CQA prebuilt answering API | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/prebuilt |
137| 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 |
138| 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 |
139| 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 |
140| Quickstart integrating Text Analytics for health | https://learn.microsoft.com/en-us/azure/ai-services/language-service/text-analytics-for-health/quickstart |
141
142### Deployment
143| Topic | URL |
144|-------|-----|
145| Deploy custom language projects to multiple regions | https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/custom-features/multi-region-deployment |
146| 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 |
147| 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 |
148| Run NER Docker containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/how-to/use-containers |
149| 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 |
150| Move CQA projects between environments | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/migrate-knowledge-base |
151| Deploy Sentiment Analysis containers on-premises | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers |
152| 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