| Troubleshooting | L37-L48 | Diagnosing and fixing Azure AI Search indexer and skillset issues, including debug sessions, OData filter errors, private link problems, and storage/metrics discrepancies. |
| Best Practices | L49-L69 | Design, scaling, and performance tuning of Azure AI Search indexing/querying, including enrichment pipelines, chunking/vectorization, data modeling, concurrency-safe updates, and vector optimization. |
| Decision Making | L70-L82 | Planning Azure AI Search capacity, SKUs, and costs, and upgrading/migrating REST APIs, skills, SDKs, and service tiers for agentic retrieval and .NET apps |
| Architecture & Design Patterns | L83-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 behaviors for Azure AI Search: service and index caps by tier, vector/index size limits, indexer scheduling windows, enrichment quotas, and related FAQs. |
| Security | L100-L138 | Securing Azure AI Search: RBAC/keyless auth, keys, CMK encryption, private endpoints, firewalls, indexer identity/network access, ACL/Purview-based document security, and Azure Policy compliance. |
| Configuration | L139-L230 | Configuring Azure AI Search: data sources, indexes, analyzers, skillsets, enrichment, vector/semantic settings, knowledge bases, monitoring, and relevance/answer tuning. |
| Integrations & Coding Patterns | L231-L289 | Integrating Azure AI Search with data sources, SDKs, vectorizers, and custom skills; building knowledge stores; and crafting queries/filters (OData, Lucene, semantic, vector, agentic). |
| Deployment | L290-L297 | Deploying and moving Azure AI Search services with ARM/Bicep/Terraform, plus guidance on cross-region moves and checking regional feature and SKU availability. |