QuestionQ21

Implement AI capabilities in database solutions

HOTSPOT -

Your company has an ecommerce catalog in a Microsoft SQL Server 2025 database called SalesDB. SalesDB includes a table named products. The products table has these columns: product_id (int), product_name (nvarchar(200)), description (nvarchar(max)), category (nvarchar(50)), brand (nvarchar(50)), price (decimal), and sku (nvarchar(40)).

The description fields are updated each day, and price may change several times daily. You want customers to submit natural-language queries and use 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 statement, select Yes if it is true. Otherwise, select No.

Yes or No
StatementsYesNo
Generating an embedding by concatenating product_name, category, and description will support the customer requirements.
Including price in the text used to generate embeddings is required.
The underlying base type of the embeddings will be float(32).
Explanation

Product name, category, and description provide semantic product context for cosine similarity search. Brand and price remain structured columns that can be filtered independently; embedding the frequently changing price is not required. SQL Server 2025 uses float32 as the default base type for the VECTOR data type, with float16 available only when explicitly specified.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!