Exam DP-800 Topic 1 Question 15 Discussion
Actual exam question for Microsoft's DP-800 exam
Question #: 15
Topic #: 1
Question #: 15
Topic #: 1
Case Study 1 - Contoso
Existing Environment
Azure Environment
Contoso has an Azure subscription in North Europe that contains the corporate infrastructure.
The current infrastructure contains a Microsoft SQL Server 2017 database. The database contains the following tables.
The FeedbackJsoncolumn has a full-text index and stores JSON documents in the following format.
The support staff at Contoso never has the UNMASKpermission.
Problem Statements
Contoso is deploying a new Azure SQL database that will become the authoritative data store for the following:
* AI workloads
* Vector search
* Modernized API access
* Retrieval Augmented Generation (RAG) pipelines
Sometimes the ingestion pipeline fails due to malformed JSON and duplicate payloads.
The engineers at Contoso report that the following dashboard query runs slowly.
You review the execution plan and discover that the plan shows a clustered index scan.
VehicleIncidentReportsoften contains details about the weather, traffic conditions, and location. Analysts report that it is difficult to find similar incidents based on these details.
Requirements
Planned Changes
Contoso wants to modernize Fleet Intelligence Platform to support AI-powered semantic search over incident reports.
Security Requirements
Contoso identifies the following security requirements:
* Restrict the support staff from viewing Personally Identifiable Information (PII) data, which is full email addresses and phone numbers.
* Enforce row-level filtering so that analysts see only incidents for the fleets to which they are assigned. The analysts can be assigned to multiple fleets.
Database Performance and Requirements
Contoso identifies the following telemetry requirements:
* Telemetry data must be stored in a partitioned table.
* Telemetry data must provide predictable performance for ingestion and retention operations.
* latitude, longitude, and accuracyJSON properties must be filtered by using an index seek.
Contoso identifies the following maintenance data requirements:
* Ensure that any changes to a row in the MaintenanceEventstable updates the corresponding value in the LastModifiedUtccolumn to the time of the change.
* Avoid recursive updates.
AI Search, Embeddings, and Vector Indexing
Contoso plans to implement semantic search over incident data to meet the following requirements:
* Embeddings must be stored in dedicated Azure SQL Database tables.
* Embeddings must be generated from rich natural language fields.
* Chunking must preserve semantic coherence.
* Hybrid search must combine the following:
- Vector similarity
- Keyword filtering or boosting
Development Requirements
The development team at Contoso will use Microsoft Visual Studio Code and GitHub Copilot and will retrieve live metadata from the databases.
Contoso identifies the following requirements for querying data in the FeedbackJsoncolumn of the CustomerFeedbacktable:
* Extract the customer feedback text from the JSON document.
* Filter rows where the JSON text contains a keyword.
* Calculate a fuzzy similarity score between the feedback text and a known issue description.
* Order the results by similarity score, with the highest score first.
You need to enable similarity search to provide the analysts with the ability to retrieve the most relevant health summary reports. The solution must minimize latency. What should you include in the solution?
Existing Environment
Azure Environment
Contoso has an Azure subscription in North Europe that contains the corporate infrastructure.
The current infrastructure contains a Microsoft SQL Server 2017 database. The database contains the following tables.
The FeedbackJsoncolumn has a full-text index and stores JSON documents in the following format.
The support staff at Contoso never has the UNMASKpermission.
Problem Statements
Contoso is deploying a new Azure SQL database that will become the authoritative data store for the following:
* AI workloads
* Vector search
* Modernized API access
* Retrieval Augmented Generation (RAG) pipelines
Sometimes the ingestion pipeline fails due to malformed JSON and duplicate payloads.
The engineers at Contoso report that the following dashboard query runs slowly.
You review the execution plan and discover that the plan shows a clustered index scan.
VehicleIncidentReportsoften contains details about the weather, traffic conditions, and location. Analysts report that it is difficult to find similar incidents based on these details.
Requirements
Planned Changes
Contoso wants to modernize Fleet Intelligence Platform to support AI-powered semantic search over incident reports.
Security Requirements
Contoso identifies the following security requirements:
* Restrict the support staff from viewing Personally Identifiable Information (PII) data, which is full email addresses and phone numbers.
* Enforce row-level filtering so that analysts see only incidents for the fleets to which they are assigned. The analysts can be assigned to multiple fleets.
Database Performance and Requirements
Contoso identifies the following telemetry requirements:
* Telemetry data must be stored in a partitioned table.
* Telemetry data must provide predictable performance for ingestion and retention operations.
* latitude, longitude, and accuracyJSON properties must be filtered by using an index seek.
Contoso identifies the following maintenance data requirements:
* Ensure that any changes to a row in the MaintenanceEventstable updates the corresponding value in the LastModifiedUtccolumn to the time of the change.
* Avoid recursive updates.
AI Search, Embeddings, and Vector Indexing
Contoso plans to implement semantic search over incident data to meet the following requirements:
* Embeddings must be stored in dedicated Azure SQL Database tables.
* Embeddings must be generated from rich natural language fields.
* Chunking must preserve semantic coherence.
* Hybrid search must combine the following:
- Vector similarity
- Keyword filtering or boosting
Development Requirements
The development team at Contoso will use Microsoft Visual Studio Code and GitHub Copilot and will retrieve live metadata from the databases.
Contoso identifies the following requirements for querying data in the FeedbackJsoncolumn of the CustomerFeedbacktable:
* Extract the customer feedback text from the JSON document.
* Filter rows where the JSON text contains a keyword.
* Calculate a fuzzy similarity score between the feedback text and a known issue description.
* Order the results by similarity score, with the highest score first.
You need to enable similarity search to provide the analysts with the ability to retrieve the most relevant health summary reports. The solution must minimize latency. What should you include in the solution?
Suggested Answer: D Vote an answer
Scenario: There is a VehicleHealthSummary table.
To enable similarity search on your health summary data while minimizing latency, you should use the native VECTOR data type and a DiskANN vector index, which are now available in public preview for Azure SQL Database.
Solution Implementation
1. Define the Vector Column: Ensure your embeddings are stored using the native VECTOR(1536) type rather than NVARCHAR or VARBINARY. This format is optimized for high- dimensional data and mathematical operations.
ALTER TABLE HealthSummaries
ADD SummaryVector VECTOR(1536);
2. Create the Vector Index: Use the CREATE VECTOR INDEX statement. In Azure SQL, this uses the DiskANN algorithm, which is specifically designed to provide high-speed Approximate Nearest Neighbor (ANN) searches for large datasets.
CREATE VECTOR INDEX idx_health_summary_vector
ON HealthSummaries (SummaryVector)
WITH ( METRIC = 'COSINE', TYPE = 'DISKANN' );
3. Perform the Similarity Search: To leverage the index for low-latency retrieval, use the VECTOR_SEARCH function rather than VECTOR_DISTANCE. While VECTOR_DISTANCE calculates exact values (resulting in a full table scan), VECTOR_SEARCH utilizes the DiskANN index to find the most relevant reports quickly.
SELECT TOP(10) *
FROM HealthSummaries
ORDER BY VECTOR_DISTANCE('cosine', SummaryVector, @query_vector);
Reference:
https://learn.microsoft.com/en-us/samples/azure-samples/azure-sql-db-openai/azure-sql-db- openai/
To enable similarity search on your health summary data while minimizing latency, you should use the native VECTOR data type and a DiskANN vector index, which are now available in public preview for Azure SQL Database.
Solution Implementation
1. Define the Vector Column: Ensure your embeddings are stored using the native VECTOR(1536) type rather than NVARCHAR or VARBINARY. This format is optimized for high- dimensional data and mathematical operations.
ALTER TABLE HealthSummaries
ADD SummaryVector VECTOR(1536);
2. Create the Vector Index: Use the CREATE VECTOR INDEX statement. In Azure SQL, this uses the DiskANN algorithm, which is specifically designed to provide high-speed Approximate Nearest Neighbor (ANN) searches for large datasets.
CREATE VECTOR INDEX idx_health_summary_vector
ON HealthSummaries (SummaryVector)
WITH ( METRIC = 'COSINE', TYPE = 'DISKANN' );
3. Perform the Similarity Search: To leverage the index for low-latency retrieval, use the VECTOR_SEARCH function rather than VECTOR_DISTANCE. While VECTOR_DISTANCE calculates exact values (resulting in a full table scan), VECTOR_SEARCH utilizes the DiskANN index to find the most relevant reports quickly.
SELECT TOP(10) *
FROM HealthSummaries
ORDER BY VECTOR_DISTANCE('cosine', SummaryVector, @query_vector);
Reference:
https://learn.microsoft.com/en-us/samples/azure-samples/azure-sql-db-openai/azure-sql-db- openai/
by Kennedy at Sep 01, 2026, 07:05 AM
0
0
0
10
Comments
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
Report Comment
Commenting
You can sign-up / login (it's free).