Study guide
5.1 Azure AI Search — Fundamentals and Architecture
Azure AI Engineer Associate AI-102
Track your progress as you read
Finished sections get a check mark.
1 Introduction
About the Azure AI Engineer Associate (AI-102) Exam Study Strategies and Exam Tips for the AI-102
2 Domain 1: Plan and Manage an Azure AI Solution (20-25%)
1.1 Azure AI Services Overview and Selection 1.2 Resource Provisioning and Configuration 1.3 Security and Access Management 1.4 Responsible AI Principles and Implementation 1.5 Azure AI Solution Architecture Patterns
3 Content Safety and Moderation (within Plan and Manage, Domain 1)
2.1 Azure AI Content Safety Overview 2.2 Prompt Shields and Adversarial Attack Detection 2.3 Text and Image Moderation Implementation 2.4 Content Filtering in Azure OpenAI Service
4 Domain 4: Implement Computer Vision Solutions (10-15%)
3.1 Azure AI Vision — Image Analysis 4.0 3.2 Azure AI Face Service 3.3 Azure AI Custom Vision 3.4 Optical Character Recognition (OCR) 3.5 Video Analysis and the Retired Spatial Analysis
5 Domain 5: Implement Natural Language Processing Solutions (15-20%)
4.1 Azure AI Language — Text Analytics Features 4.2 Conversational Language Understanding (CLU) 4.3 Custom Text Classification and Custom NER 4.4 Azure AI Speech Services 4.5 Azure AI Translator Service 4.6 Question Answering and Conversational AI
6 Domain 6: Implement Knowledge Mining and Information Extraction Solutions (15-20%)
5.1 Azure AI Search — Fundamentals and Architecture 5.2 AI Enrichment with Skillsets 5.3 Azure AI Document Intelligence
7 Domain 2: Implement Generative AI Solutions (15-20%)
6.1 Azure OpenAI Service — Models and Deployment 6.2 Chat Completions API and Prompt Engineering 6.3 Embeddings and Vector Search for RAG 6.4 Fine-Tuning and Model Customization 6.5 Image Generation (gpt-image; DALL-E 3 Retired) 6.6 RAG After On Your Data, and AI Agents
8 Domain 3: Implement an Agentic Solution (5-10%)
3.1 Agentic Solutions: Foundry Agent Service and the Microsoft Agent Framework
9 Exam Review: Cross-Domain Topics and Advanced Practice
7.1 Service Comparison and Selection Guide 7.2 SDK and REST API Patterns 7.3 Responsible AI Across All Domains 7.4 End-to-End Solution Architectures 7.5 Exam Day Quick Reference
5.1 Azure AI Search — Fundamentals and Architecture
Key Takeaways Explain This Topic AI
Azure AI Search (formerly Cognitive Search) provides full-text search, AI enrichment, vector search, and semantic ranking; the indexing pipeline runs Data Source → Indexer → Skillset → Index.
fieldMappings map source fields BEFORE enrichment; outputFieldMappings map skill outputs AFTER enrichment — confusing the two is a top exam trap.
Each field has independent attributes (searchable, filterable, sortable, facetable, retrievable, key); only Edm.String / Collection(Edm.String) are searchable for keyword search.
Vector search stores embeddings in a Collection(Edm.Single) field and retrieves the k nearest neighbors via an HNSW or exhaustiveKnn algorithm using a cosine, dotProduct, or euclidean metric.
Semantic ranker (an L2 re-ranker) requires a semantic configuration and a paid tier; hybrid search (BM25 + vector) plus semantic ranking is the recommended Retrieval-Augmented Generation pattern.
Last updated: October 2026
Quick Answer: Azure AI Search runs an indexing pipeline: Data Source -> Indexer -> Skillset -> Index -> Query. Indexers pull from Blob Storage, Azure SQL, Cosmos DB, ADLS Gen2, and SharePoint. Skillsets enrich data with Optical Character Recognition (OCR), Named Entity Recognition (NER), and key phrases. Vector search stores embeddings; semantic ranking re-ranks results. For RAG, use hybrid search (keyword + vector) with semantic ranking.
Where This Sits on AI-102
Knowledge mining and information extraction (Domain 6) is worth 15-20% of the AI-102 exam, which has a 100-minute time limit, a passing score of 700/1000 , and a $165 USD registration fee. Microsoft retired the AI-102 exam on June 30, 2026; AI-103 replaced it. Azure AI Search questions are heavy on case-study drag-and-drop : you order pipeline components, fix a broken field mapping, or choose the right search mode for a RAG scenario.
- Indexing Pipeline Order [Data Sources] [AI Enrichment] [Search]
- Blob / SQL / Cosmos --> Skillset (OCR, NER, --> Index (full-text +
- DB / ADLS Gen2 / key phrases, custom) vector + semantic)
- SharePoint
- ^ |
- Indexer ----------------- coordinates ------------------+
The indexer is the orchestrator: it connects to one data source, optionally invokes one skillset, and writes documents to exactly one index. A common trap presents the components scrambled (Index first, or Skillset before Indexer) — the correct sequence is always Data Source -> Indexer -> Skillset -> Index .
Field Mappings vs Output Field Mappings
This is the single most-tested logistics detail in 5.1:
Mapping type Runs Maps from Typical use
fieldMappings BEFORE enrichment Raw source field Rename metadata_storage_name -> documentName ; base64-encode a key
outputFieldMappings AFTER enrichment Enrichment-tree node ( /document/... ) Write skill output /document/organizations -> index field organizations
If a skill output never appears in the index, the missing piece is almost always an absent outputFieldMapping — not a skillset error.
- Index Field Attributes {"name": "id", "type": "Edm.String", "key": true, "filterable": true},
- {"name": "content", "type": "Edm.String", "searchable": true, "analyzer": "en.microsoft"},
- {"name": "category", "type": "Edm.String", "filterable": true, "facetable": true},
{"name": "contentVector", "type": "Collection(Edm.Single)", "searchable": true, "dimensions": 1536, "vectorSearchProfile": "vp"}
- Attribute Meaning Worked example
- searchable Full-text indexed via an analyzer content for keyword queries
- filterable Usable in $filter (OData) category eq 'Legal'
- sortable Usable in $orderby Sort by lastModified desc
- facetable Drives faceted navigation counts Sidebar of categories
- retrievable Returned in results Turn off for embeddings you do not display
- key Unique document identifier Exactly one per index, Edm.String
Trap: attributes are immutable once the index is created. Adding filterable to an existing field requires rebuilding the index — you cannot patch it in place. Only one field can be key , and it must be Edm.String .
Vector Search
Vector search retrieves by semantic similarity instead of exact tokens. You store an embedding (e.g., 1536 floats from Azure OpenAI text-embedding-ada-002 , or 3072 from text-embedding-3-large ) in a Collection(Edm.Single) field, then query for the k nearest neighbors . "vectorSearch": {
- "algorithms": [{
- "name": "hnsw-1", "kind": "hnsw",
- "hnswParameters": {"metric": "cosine", "m": 4, "efConstruction": 400, "efSearch": 500}
- }],
- "profiles": [{"name": "vp", "algorithm": "hnsw-1"}]
- }
- Algorithm Behavior When
- hnsw Approximate nearest neighbor, fast, graph-based Large indexes, low latency
- exhaustiveKnn Exact, scans every vector Small sets or 100% recall needed
- Metric Notes
- cosine Default; matches OpenAI embeddings (angle, ignores magnitude)
- dotProduct Use only with pre-normalized vectors
- euclidean Straight-line distance
The dimensions value must match the embedding model exactly — mismatching 1536 against a 3072-dim model throws an indexing error. from azure.search.documents.models import VectorizedQuery
- results = search_client.search(
- search_text=None,
- vector_queries=[VectorizedQuery(
- vector=query_embedding, k_nearest_neighbors=5, fields="contentVector")])
- Hybrid Search and Semantic Ranking
Hybrid search runs BM25 keyword scoring and vector search in parallel, then fuses ranks with Reciprocal Rank Fusion (RRF) . Layering the semantic ranker on top adds an L2 deep-learning re-rank of the top 50 candidates, plus semantic captions (the best passage per hit) and semantic answers (a verbatim extracted answer).
- Mode How it scores Best for
- Keyword (BM25) Term frequency / document frequency Exact terms, codes, SKUs
- Vector Embedding similarity (k-NN) Synonyms, paraphrase, intent
- Hybrid RRF fusion of both General RAG recall
- Hybrid + semantic RRF then L2 re-rank Best RAG precision
Semantic ranking requires a semantic configuration in the index and a Basic tier or higher (not free). For a RAG chatbot scenario, the exam-correct answer is almost always hybrid search with semantic ranking — it maximizes both recall and the relevance of the few chunks you feed the language model.
On the Exam: Distinguish BM25 (keyword), vector (embeddings, k-NN), and semantic ranking (re-rank). When a question says "customers misspell or paraphrase queries," the fix is vector or hybrid search; when it says "surface a direct answer snippet," enable semantic answers.