Exam DP-800 Topic 4 Question 61 Discussion

Actual exam question for Microsoft's DP-800 exam
Question #: 61
Topic #: 4
Hotspot Question
Your company has an ecommerce catalog in a Microsoft SQL Server 2025 database named SalesDB. SalesDB contains a table named products. products contains the following columns:
- product_id (int)
- product_name (nvarchar(200))
- description (nvarchar(max))
- category (nvarchar(50))
- brand (nvarchar(50))
- price (decimal)
- sku (nvarchar(40))
The description fields are updated daily by a content pipeline, and price can change multiple times per day.
You want customers to be able to submit natural language queries and apply structured filters for brand and price.
You plan to store embeddings in a new VECTOR(1536) column and use VECTOR_SEARCH(...
METRIC='cosine' ...).
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.

Suggested Answer:

by zakmarli at Jul 16, 2026, 04:03 AM

Limited Time Offer

15%

Off

Get Premium DP-800 Questions as Interactive Self Test Engine or PDF

Comments

Chosen Answer:
This is a voting comment (?) , you can switch to a simple comment.
Switch to a voting comment New
Nick name: Submit Cancel
zakmarli
2026-07-16 04:03:46
Yes/No/Yes

1. Generating an embedding by concatenating product_name, category, and description
✅ Yes
For semantic product search, embeddings should be generated from the textual attributes that describe the product's meaning and context. Combining:

product_name
category
description

provides rich semantic information for natural-language searches.

2. Including price in the text used to generate embeddings is required
❌ No
The requirement states:

customers submit natural language queries and apply structured filters for brand and price.

Price is a structured attribute, not semantic content.
A better pattern is:
SQLSELECT *FROM VECTOR_SEARCH(...)WHERE brand = 'Contoso' AND price < 100;Show more lines
Since price changes multiple times per day, embedding it into the vector would require frequent re-embedding and provides little semantic value.

3. The underlying base type of the embeddings will be float(32)
✅ Yes
SQL Server's VECTOR(1536) stores embedding values as a vector of 32-bit floating-point numbers (float32). Embedding models such as text-embedding-ada-002 and text-embedding-3-small return float vectors that map directly to this representation.
upvoted 1 times
...
A voting comment increases the vote count for the chosen answer by one.

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.
0
0
0
10