Azure AI Search Skill
This skill provides expert guidance for Azure AI Search. 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), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetchwith query stringfrom=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpagewith query stringfrom=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L37-L48 | Diagnosing and fixing Azure AI Search indexer/skillset errors, filter and metric issues, permission-filtered results, and private link or storage discrepancies. |
| Best Practices | L49-L66 | Best practices for designing, scaling, and troubleshooting enrichment/indexing pipelines, optimizing vector search, performance, and costs, and safely updating Azure AI Search resources. |
| Decision Making | L67-L82 | Guidance on choosing regions, tiers, pricing, capacity, connectors, and SDK/API versions, plus how to plan costs and migrate Azure AI Search services and apps to newer APIs. |
| Architecture & Design Patterns | L83-L88 | Architectural patterns for Azure AI Search: combining vector and keyword search, designing multitenant or isolated indexes, and building resilient multi-region search deployments. |
| Limits & Quotas | L89-L98 | Limits, quotas, and capacity planning for Azure AI Search: billing/free enrichment, indexer schedules/concurrency/runtime, service capacity limits, and vector index size/throughput constraints. |
| Security | L99-L141 | Securing Azure AI Search: RBAC/Entra ID, keys, encryption, network isolation, indexer auth to data sources (SQL, Storage, SharePoint, Cosmos, Functions), and document-level/label-based access control. |
| Configuration | L142-L234 | Configuring Azure AI Search: data sources, index schemas, analyzers, skillsets, enrichment, vectorization, semantic ranker, monitoring, and agentic retrieval/knowledge base setup. |
| Integrations & Coding Patterns | L235-L310 | Patterns and code for integrating Azure AI Search: indexers, skills, vectorization, query syntax (Lucene/OData), semantic ranking, filters, pagination, and app/Power BI integrations. |
| Deployment | L311-L318 | Deploying and moving Azure AI Search: ARM/Bicep/Terraform provisioning, cross-region migration, and deploying C# search apps to Azure Container Apps. |
Troubleshooting
Best Practices
Decision Making
Architecture & Design Patterns
| Topic | URL |
|---|---|
| Design multitenant and isolated content in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/search-modeling-multitenant-saas-applications |
| Design multi-region architectures for Azure AI Search | https://learn.microsoft.com/en-us/azure/search/search-multi-region |
Limits & Quotas
| Topic | URL |
|---|---|
| Billing limits and free quotas for Azure AI Search enrichment | https://learn.microsoft.com/en-us/azure/search/cognitive-search-attach-cognitive-services |
| Manage indexer execution, duration, and concurrency | https://learn.microsoft.com/en-us/azure/search/search-howto-run-reset-indexers |
| Configure Azure AI Search indexer schedules and limits | https://learn.microsoft.com/en-us/azure/search/search-howto-schedule-indexers |
| Understand indexer runtime quotas on Serverless and S3 HD | https://learn.microsoft.com/en-us/azure/search/search-indexer-high-density-serverless-overview |
| Plan Azure AI Search capacity using service limits | https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity |
| Understand Azure AI Search vector index limits | https://learn.microsoft.com/en-us/azure/search/vector-search-index-size |
Security
Configuration
Integrations & Coding Patterns
Deployment
| Topic | URL |
|---|---|
| Deploy Azure AI Search via ARM templates | https://learn.microsoft.com/en-us/azure/search/search-get-started-arm |
| Deploy Azure AI Search using Bicep files | https://learn.microsoft.com/en-us/azure/search/search-get-started-bicep |
| Provision Azure AI Search services with Terraform | https://learn.microsoft.com/en-us/azure/search/search-get-started-terraform |
| Move Azure AI Search services across regions | https://learn.microsoft.com/en-us/azure/search/search-howto-move-across-regions |
| Deploy C# Azure AI Search apps to Container Apps | https://learn.microsoft.com/en-us/azure/search/tutorial-csharp-deploy-web-search |