You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- content: "Semantic search uses text embeddings to determine result relevance. What is an embedding vector?"
20
-
choices:
21
-
- content: "An array of n numbers that capture the text's meaning."
22
-
isCorrect: true
23
-
explanation: "Correct. Semantic search uses numeric vector distance to measure semantic distance. A vector of definition or topic words is like lexical search (augmenting a query with synonyms or searching by tag or topic)."
24
-
- content: "An array of n words that summarize the text's meaning."
25
-
isCorrect: false
26
-
explanation: "Incorrect. Semantic search uses a quantitative representation of text meaning derived from a language model, not synonyms or definitions. The core of semantic search is to represent semantics quantitatively so that normal vector operations can be used to measure semantic distance."
27
-
- content: "An array of n text strings embedded in the text."
28
-
isCorrect: false
29
-
explanation: "Incorrect. Semantic search uses a quantitative representation of text meaning derived from a language model, not a list of ideas or topics. The core of semantic search is to represent semantics quantitatively so that normal vector operations can be used to measure semantic distance."
30
-
- content: "An application's text data is stored in an Azure Database for PostgreSQL flexible server. The application needs a vector database to store the text embeddings and perform a semantic search. What is the most straightforward database choice?"
31
-
choices:
32
-
- content: "Use Azure Database for PostgreSQL."
33
-
isCorrect: true
34
-
explanation: "Correct. PostgreSQL is a suitable storage layer for vectors with the `vector` extension installed. It doesn't require new services or data migration."
35
-
- content: "Use Vector Database in Azure Cosmos DB for MongoDB."
36
-
isCorrect: false
37
-
explanation: "Incorrect. While the Vector Database in Azure Cosmos DB for MongoDB is a good choice for storing & querying vectors, it requires deploying & maintaining a separate service and performing ETL between the application database and Cosmos DB. The most straightforward option is to use the `vector` extension to handle vectors directly in the PostgreSQL database."
38
-
- content: "Use Azure AI Search's vector store."
39
-
isCorrect: false
40
-
explanation: "Incorrect. While Azure AI Search's vector store is a good choice for storing & querying vectors, it requires deploying a separate service and performing ETL between the application database and Azure AI Search. The most straightforward choice is to use the `vector` extension to store vectors directly in the PostgreSQL database."
41
-
- content: "An application has stored embedding vectors in a PostgreSQL flexible server database and is ready to query them. The user has supplied a query string. What is the simplest way to run a semantic search?"
42
-
choices:
43
-
- content: "The application calls a stored function to return ranked results."
44
-
isCorrect: true
45
-
explanation: "Correct. This approach requires minimal changes to the application code and encapsulates concepts like embedding vectors and cosine distance to application code."
46
-
- content: "Use Azure OpenAI Embeddings API in the application, and use the result as a query parameter to rank cosine distance."
47
-
isCorrect: false
48
-
explanation: "Incorrect. While this would work, it isn't the simplest approach: it introduces new services to applications and requires application developers to understand at least the basics of vector search."
49
-
- content: "Use Azure AI Search's integrated vectorization to generate the query embedding and use the SQL in-line."
50
-
isCorrect: false
51
-
explanation: "Incorrect. While this is a viable approach to running semantic search with Azure AI Search, it isn't the simplest approach for data already stored in a PostgreSQL flexible server."
- content: "Semantic search uses text embeddings to determine result relevance. What is an embedding vector?"
22
+
choices:
23
+
- content: "An array of n numbers that capture the text's meaning."
24
+
isCorrect: true
25
+
explanation: "Correct. Semantic search uses numeric vector distance to measure semantic distance. A vector of definition or topic words is like lexical search (augmenting a query with synonyms or searching by tag or topic)."
26
+
- content: "An array of n words that summarize the text's meaning."
27
+
isCorrect: false
28
+
explanation: "Incorrect. Semantic search uses a quantitative representation of text meaning derived from a language model, not synonyms or definitions. The core of semantic search is to represent semantics quantitatively so that normal vector operations can be used to measure semantic distance."
29
+
- content: "An array of n text strings embedded in the text."
30
+
isCorrect: false
31
+
explanation: "Incorrect. Semantic search uses a quantitative representation of text meaning derived from a language model, not a list of ideas or topics. The core of semantic search is to represent semantics quantitatively so that normal vector operations can be used to measure semantic distance."
32
+
- content: "An application's text data is stored in an Azure Database for PostgreSQL flexible server. The application needs a vector database to store the text embeddings and perform a semantic search. What is the most straightforward database choice?"
33
+
choices:
34
+
- content: "Use Azure Database for PostgreSQL."
35
+
isCorrect: true
36
+
explanation: "Correct. PostgreSQL is a suitable storage layer for vectors with the `vector` extension installed. It doesn't require new services or data migration."
37
+
- content: "Use Vector Database in Azure Cosmos DB for MongoDB."
38
+
isCorrect: false
39
+
explanation: "Incorrect. While the Vector Database in Azure Cosmos DB for MongoDB is a good choice for storing & querying vectors, it requires deploying & maintaining a separate service and performing ETL between the application database and Cosmos DB. The most straightforward option is to use the `vector` extension to handle vectors directly in the PostgreSQL database."
40
+
- content: "Use Azure AI Search's vector store."
41
+
isCorrect: false
42
+
explanation: "Incorrect. While Azure AI Search's vector store is a good choice for storing & querying vectors, it requires deploying a separate service and performing ETL between the application database and Azure AI Search. The most straightforward choice is to use the `vector` extension to store vectors directly in the PostgreSQL database."
43
+
- content: "An application has stored embedding vectors in a PostgreSQL flexible server database and is ready to query them. The user has supplied a query string. What is the simplest way to run a semantic search?"
44
+
choices:
45
+
- content: "The application calls a stored function to return ranked results."
46
+
isCorrect: true
47
+
explanation: "Correct. This approach requires minimal changes to the application code and encapsulates concepts like embedding vectors and cosine distance to application code."
48
+
- content: "Use Azure OpenAI Embeddings API in the application, and use the result as a query parameter to rank cosine distance."
49
+
isCorrect: false
50
+
explanation: "Incorrect. While this would work, it isn't the simplest approach: it introduces new services to applications and requires application developers to understand at least the basics of vector search."
51
+
- content: "Use Azure AI Search's integrated vectorization to generate the query embedding and use the SQL in-line."
52
+
isCorrect: false
53
+
explanation: "Incorrect. While this is a viable approach to running semantic search with Azure AI Search, it isn't the simplest approach for data already stored in a PostgreSQL flexible server."
0 commit comments