AI-200 Data Management Services And Vector Search Practice Test 3 — 15 Questions

Question 1

Which THREE data types or formats are commonly used to represent embeddings when preparing data for storage in a vector-enabled Azure service?

Accepted Answer

JSON arrays.. Options A, B, and C are correct because embeddings are fundamentally numeric vectors, and these three formats all represent that vector data directly: JSON arrays (A) are the standard serialization used when sending embeddings through REST APIs to services like Azure AI Search or Azure Cosmos DB, arrays of floats (B) match the single-precision float32 representation that vector indexes such as Azure AI Search's HNSW/IVF indexes expect, and lists of floating-point numbers (C) are the native in-memory Python/NumPy form used when generating and loading embeddings before storage. Options D and E are not correct: Base64-encoded binary image data (D) is a way to store raw image bytes, not an embedding vector, and vectorized text sequences of token IDs (E) are tokenizer output for model input, not the dense embedding vectors stored in a vector-enabled service.

Answer

Base64 encoded binary image data.

Answer

Vectorized text sequences (token IDs).

Question 2

You are designing an Azure Cosmos DB for NoSQL container to store documents with vector embeddings. You need to perform vector search using the built-in VectorDistance function. The embeddings are 1536-dimensional and you expect millions of documents. You want to minimize latency while maintaining high recall. Which indexing policy should you configure?

Accepted Answer

Create a vector index on the embedding field with the 'quantizedFlat' index type and specify dimensions and similarity metric.. For large-scale vector search in Cosmos DB for NoSQL, the quantizedFlat index type provides a good trade-off between latency and recall by compressing vectors. The flat index is exact but slower, while diskANN and HNSW are not available in Cosmos DB. Therefore, quantizedFlat is the correct choice to minimize latency while maintaining high recall.

Answer

Create a vector index on the embedding field with the 'flat' index type and specify dimensions and similarity metric.

Answer

Create a vector index on the embedding field with the 'HNSW' index type and specify dimensions and similarity metric.

Answer

Create a vector index on the embedding field with the 'diskANN' index type and specify dimensions and similarity metric.

Question 3

You are using Azure AI Search to implement a hybrid search solution that combines keyword search and vector search. You want to ensure that the results are ranked by a combined relevance score. What should you configure?

Accepted Answer

Set the 'searchMode' parameter to 'all' and include both 'searchText' and 'vectorQueries' in the request.. Hybrid search in Azure AI Search is performed by submitting a query that includes both a text search and a vector search. The service automatically combines the scores from both methods using reciprocal rank fusion (RRF) to produce a single ranked result set. No additional configuration is needed beyond including both query components. Thus, the correct approach is to include both searchText and vectorQueries in the request.

Answer

Create a scoring profile that boosts documents based on the vector similarity score.

Answer

Enable semantic ranking and set the query type to 'semantic'.

Answer

Configure a custom analyzer to tokenize the vector field for keyword search.

Question 4

You are managing an Azure Cosmos DB for NoSQL account that stores vector embeddings in a container. You need to reduce the cost of vector queries while maintaining acceptable recall. Which configuration change should you make?

Accepted Answer

Use a lower-dimensional embedding model and adjust the vector index accordingly.. Reducing vector dimensions lowers the computational and storage overhead of vector indexing and querying, which can decrease RU consumption per query. This is a practical way to optimize cost while balancing recall, provided the lower-dimensional model still meets semantic requirements. Other options either do not apply or would harm performance.

Answer

Decrease the value of the 'maxDegree' parameter in the vector index.

Answer

Disable indexing on all scalar properties to free up RUs for vector queries.

Answer

Increase the number of dimensions in the vector index.

Question 5

When configuring an Azure Cosmos DB for NoSQL container to store embeddings, what data type must the vector property be stored as within the JSON document?

Accepted Answer

An array of 32-bit floating-point numbers. Azure Cosmos DB for NoSQL stores vector embeddings as a JSON array of 32-bit floating-point numbers (float32), which is the format its native vector indexing and DiskANN-based similarity search expect. Each element represents one dimension of the embedding, and the container's vector policy declares dimensions and the float32 data type.

Answer

A base64 encoded string

Answer

An array of integers

Answer

A binary blob

Question 6

You are configuring an Azure AI Search index schema via the REST API. You need to define a field that will hold a 1536-dimensional vector. Which field type must you assign to this field?

Accepted Answer

Edm.SingleCollection. In Azure AI Search, vector fields are defined using the Edm.SingleCollection type, which represents a collection of single-precision floating-point values — the standard representation for embeddings. A 1536-dimensional vector (e.g., from text-embedding-ada-002) is declared as Edm.SingleCollection with dimensions set to 1536 and a vectorSearchProfile attached. There is no Edm.Vector type in the Azure AI Search schema.

Answer

Edm.Vector

Answer

Edm.String

Answer

Edm.DoubleCollection

Question 7

You are configuring semantic ranking in Azure AI Search to improve search relevance for your enterprise application. Which tier of Azure AI Search is required to enable semantic ranking?

Accepted Answer

Standard (S1 or higher). Semantic ranking in Azure AI Search requires the Standard tier (S1) or higher — it is not available on Free or Basic tiers. Semantic ranking uses Microsoft's language models to rerank the top results from BM25 or vector search, improving relevance for natural-language queries. Enabling it on a supported tier is done by adding a semantic configuration to the index and setting queryType to 'semantic'.

Answer

Storage Optimized (L1)

Answer

Free

Answer

Basic

Question 8

You are building a hybrid search solution using Azure AI Search that combines BM25 full-text search with vector search. What is the name of the feature that intelligently combines and normalizes scores from different retrieval systems before presenting the final top results?

Accepted Answer

Reciprocal Rank Fusion (RRF). Reciprocal Rank Fusion (RRF) is the algorithm Azure AI Search uses to merge BM25 and vector result sets in hybrid queries. It converts each result's rank into a reciprocal score (1/(k+rank)) and sums them, producing a normalized combined ranking without needing to align raw score scales. This is why hybrid search in Azure AI Search 'just works' without manual score normalization.

Answer

Min-Max Score Scaling

Answer

Cosine Distance Normalization

Answer

Cross-Encoder Re-ranking

Question 9

Your company stores product catalog items in Azure Cosmos DB for NoSQL and needs to implement vector search for recommendation capabilities. Which indexing policy property must you add to enable vector indexing on a container?

Accepted Answer

vectorIndexes. Azure Cosmos DB for NoSQL requires a `vectorIndexes` array in the container's indexing policy to define vector indexing on vector-typed properties. Each entry specifies the vector path and the vector index type (flat, quantizedFlat, or diskANN). Without this property, vector search queries cannot be served efficiently or at all against the container.

Answer

compositeIndexes

Answer

spatialIndexes

Answer

fullTextIndexes

Question 10

You are writing a query in Azure Cosmos DB for NoSQL to retrieve documents based on vector similarity against a target embedding. Which built-in SQL function should you use in the ORDER BY clause?

Accepted Answer

VectorDistance(). Azure Cosmos DB for NoSQL exposes the VectorDistance() built-in function, which computes the similarity/distance between a stored vector property and a query vector, and is used inside ORDER BY to rank results by similarity. It supports cosine, dot product, and Euclidean metrics via an optional third argument. This is the documented function for vector search queries in the NoSQL API.

Answer

CosSimilarity()

Answer

EmbeddingDistance()

Answer

GetVectorDistance()

Question 11

Which similarity metric measures the cosine of the angle between two vectors, focusing on orientation rather than magnitude, and is commonly used in Azure AI Search?

Accepted Answer

cosine. Cosine similarity measures the cosine of the angle between two vectors, which captures their orientation (direction) while ignoring their magnitude. This makes it ideal for comparing text embeddings of different lengths, and it is the default and most commonly used similarity metric in Azure AI Search vector profiles. The option 'cosine' directly names this metric.

Answer

manhattan

Answer

euclidean

Answer

dotProduct

Question 12

You are using Azure OpenAI Service to generate embeddings for your documents before storing them in Azure Cosmos DB for NoSQL. The embedding model outputs vectors with a length of 1536. When defining the vector embedding policy in Cosmos DB, what value should you specify for the dimensions property?

Accepted Answer

1536. The dimensions property in Cosmos DB's vector embedding policy must match the exact length of the vectors produced by the embedding model. Since the Azure OpenAI embedding model outputs 1536-dimensional vectors, you must specify 1536. Mismatched dimensions cause indexing failures or query errors.

Answer

3072

Answer

512

Answer

768

Question 13

You are designing an enterprise search architecture on Azure that requires hybrid search capabilities. Which THREE components or features must be configured to successfully execute a hybrid query with semantic ranking in Azure AI Search? (Choose three)

Accepted Answer

A searchable Edm.String text field for keyword matching. Option B is correct because hybrid search always includes a keyword (full-text) component, which requires at least one searchable Edm.String field in the index so the query can perform BM25-scored term matching via the inverted index. Option C is correct because the vector half of a hybrid query needs a vector field of type Collection(Edm.Single) (Edm.SingleCollection) plus an attached vector profile (with HNSW or exhaustive KNN algorithm and a vectorizer if integrated vectorization is used) so the query engine can run the approximate nearest neighbor search. Option E is correct because semantic ranking is not automatic — it requires a semanticConfiguration defined on the index (specifying title, content, and keyword priority fields) that is referenced in the query's semanticSearch settings to invoke the L2 semantic reranker. Option A is not required: Azure Blob Storage is only an optional data source for indexers/pull-based ingestion, and hybrid queries can run against any populated index regardless of origin. Option D is not required: Azure AI Search natively performs reciprocal rank fusion (RRF) to merge keyword and vector scores internally, so no external Azure Functions score-merging logic is needed.

Answer

Azure Blob Storage configured as an external data source

Answer

An Azure Functions application for manual score merging

Question 14

Which distance metric in Azure Cosmos DB vector search calculates the shortest straight-line segment between two points in a multi-dimensional space?

Accepted Answer

euclidean. Euclidean distance (D) measures the straight-line (L2) distance between two vectors in multi-dimensional space, computed as the square root of the sum of squared differences across dimensions. It is the metric that literally corresponds to the geometric 'shortest straight-line segment' between two points, making it the correct answer for Cosmos DB vector search.

Answer

dotproduct

Answer

hamming

Answer

cosine

Question 15

You are designing the data architecture for an AI-powered document search application. You choose Azure AI Search because you need multi-lingual support, faceted navigation, and vector search. What is the maximum number of vector fields allowed per index in Azure AI Search?

Accepted Answer

Multiple vector fields are supported per index. Azure AI Search supports multiple vector fields per index, allowing you to store and query different embeddings (e.g., text, image, or multi-model vectors) within the same index. Each vector field is defined with its own dimensions and similarity metric, and you can target specific fields in vector queries. This flexibility is essential for hybrid and multi-modal search scenarios.

Answer

Exactly one vector field per index

Answer

A maximum of two vector fields

Answer

Vector fields are not supported in Azure AI Search