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 indexer and skillset issues, including debug sessions, OData filter errors, private link problems, and storage metric discrepancies. |
| Best Practices | L49-L68 | Guidance on designing, scaling, and troubleshooting indexing/enrichment pipelines, modeling data, optimizing performance/costs, and tuning vector/GenAI behavior in Azure AI Search. |
| Decision Making | L69-L83 | Guidance on planning and migrating Azure AI Search: API/SDK upgrades, capacity and region choices, data connectors, pricing models, and cost management. |
| Architecture & Design Patterns | L84-L89 | Architectural guidance for Azure AI Search: RAG patterns, knowledge store design, multitenancy and tenant isolation, and multi-region/high-availability deployment designs. |
| Limits & Quotas | L90-L99 | Limits, quotas, and scheduling for Azure AI Search: billing/free enrichment, indexer run windows and runtime caps, service/index/vector size limits by tier and platform. |
| Security | L100-L137 | Securing Azure AI Search: RBAC/keyless auth, API keys, encryption/CMK, network isolation (private endpoints, firewalls), indexer access to data sources, and query-time ACL/labels. |
| Configuration | L138-L237 | Configuring Azure AI Search: data sources, indexers, skillsets, analyzers, vectors, semantic ranker, logging/monitoring, and agentic retrieval/answer synthesis settings. |
| Integrations & Coding Patterns | L238-L304 | Patterns and code for integrating Azure AI Search with data sources, vectorization, query syntaxes (OData/Lucene), custom skills/vectorizers, knowledge stores, and app/agent retrieval flows |
| Deployment | L305-L311 | Deploying and moving Azure AI Search services with ARM/Bicep/Terraform, plus guidance on cross-region moves and checking regional feature and SKU availability. |

### Troubleshooting
| Topic | URL |
|-------|-----|
| Troubleshoot Azure AI Search indexer errors and warnings | https://learn.microsoft.com/en-us/azure/search/cognitive-search-common-errors-warnings |
| Understand Debug Sessions for skillset troubleshooting | https://learn.microsoft.com/en-us/azure/search/cognitive-search-debug-session |
| 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 |
| Troubleshoot Azure AI Search indexer issues without errors | https://learn.microsoft.com/en-us/azure/search/search-indexer-troubleshooting |
| Troubleshoot OData collection filter errors 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 |
| Diagnose Azure AI Search storage metric discrepancies | https://learn.microsoft.com/en-us/azure/search/troubleshoot-storage-metrics |

### Best Practices
| Topic | URL |
|-------|-----|
| Design tips and troubleshooting for AI enrichment pipelines | 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 |
| Model SQL relational data for Azure AI Search indexing | https://learn.microsoft.com/en-us/azure/search/index-sql-relational-data |
| 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 Azure Blob plaintext indexing with parsing modes | https://learn.microsoft.com/en-us/azure/search/search-how-to-index-azure-blob-plaintext |
| 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