azure-cognitive-search

# 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`), 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-L48 | Diagnosing and fixing Azure AI Search issues: indexer errors/warnings, skillset debugging, OData filters, private link and SharePoint permission problems, and storage/metrics discrepancies. |
| Best Practices | L49-L67 | Best practices for designing, scaling, and troubleshooting Azure AI Search indexing and enrichment (incl. vectors, blobs, concurrency, performance, costs, and responsible GenAI Prompt skill use). |
| Decision Making | L68-L82 | Planning capacity, regions, tiers, pricing, and SDK/REST upgrades for Azure AI Search, including migrations, scaling, and handling regional capacity or cost constraints. |
| Architecture & Design Patterns | L83-L89 | 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 | L90-L99 | Limits, quotas, and scheduling for indexers and enrichment, including billing/free tiers, runtime and concurrency caps, vector index size limits, and capacity planning. |
| Security | L100-L140 | Securing Azure AI Search: RBAC, ACLs, keys, encryption, network isolation (VNet, private endpoints, firewalls), and indexer access to data sources with managed identities and policies. |
| Configuration | L141-L225 | Configuring Azure AI Search: data sources, index schemas, analyzers, skillsets/enrichment, vectorization, semantic ranker, query options, logging, and billing for agentic retrieval. |
| Integrations & Coding Patterns | L226-L309 | Patterns and code for integrating Azure AI Search with data sources, skills, vectorization, semantic ranking, and query syntaxes, plus building agentic retrieval and knowledge bases. |
| Deployment | L310-L317 | Deploying and moving Azure AI Search: ARM/Bicep/Terraform provisioning, cross-region migration, and deploying C# search apps to Azure Container Apps. |

### Troubleshooting
| Topic | URL |
|-------|-----|
| Troubleshoot Azure AI Search indexer errors and warnings | https://learn.microsoft.com/en-us/azure/search/cognitive-search-common-errors-warnings |
| Debug and troubleshoot Azure AI Search skillsets | https://learn.microsoft.com/en-us/azure/search/cognitive-search-how-to-debug-skillset |
| Debug Azure AI Search skillsets using portal sessions | https://learn.microsoft.com/en-us/azure/search/cognitive-search-tutorial-debug-sessions |
| Diagnose and fix Azure AI Search indexer issues | https://learn.microsoft.com/en-us/azure/search/search-indexer-troubleshooting |
| Troubleshoot OData collection filters in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/search-query-troubleshoot-collection-filters |
| Troubleshoot shared private link resource issues in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/troubleshoot-shared-private-link-resources |
| Troubleshoot SharePoint permission-filtered queries in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/troubleshoot-sharepoint-query-permission-filtering |
| Diagnose Azure AI Search storage and metric discrepancies | https://learn.microsoft.com/en-us/azure/search/troubleshoot-storage-metrics |

### Best Practices
| Topic | URL |
|-------|-----|
| Design and troubleshoot AI enrichment pipelines in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-troubleshooting |
| Scale and manage custom skills in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/cognitive-search-custom-skill-scale |
| Apply responsible AI best practices for GenAI Prompt skill | https://learn.microsoft.com/en-us/azure/search/responsible-ai-best-practices-genai-prompt-skill |
| Handle changed and deleted blobs in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/search-how-to-index-azure-blob-changed-deleted |
| Optimize large-scale indexing in Azure AI Search | https://learn.microsoft.com/en-us/azure/search/search-how-to-large-index |
| Apply optimistic concurrency for Azure AI Search resources | https://learn.microsoft.com/en-us/azure/search/search-howto-concurrency |
| Update or rebuild Azure AI Search indexes safely | https://learn.microsoft.com/en-us/azure/search/search-howto-reindex |
| Analyze Azure AI Search query and indexing performance | https://learn.microsoft.com/en-us/azure/search/search-performance-analysis |
| Optimize Azure AI Search query and indexing performance | https://learn.microsoft.com/en-us/azure/search/search-performance-tips |
| Optimize Azure AI Search Serverless costs | https://learn.microsoft.com/en-us/azure/search/serverless-cost-optimization |