Question 390
A SQL change-tracking stream should trigger an Azure Function that calls an approved embedding model. The team is considering this step: Create an idempotent function that updates versioned embeddings for changed records. What evidence should they review before proceeding?
Explanation
Correct Answer
Review binding configuration, worker identity, model access and deduplication keys. Azure Functions with SQL trigger binding can react to database changes but may retry deliveries. Replayed notifications do not duplicate active embeddings and updates become searchable.
Incorrect Answers
Binding deliveries can be retried; stable document/version keys and idempotent upsert prevent duplicate active embeddings.
Model calls need source key/version correlation and validation before a vector is attached to a record.
Change Tracking retention has limits; expired tokens require controlled full reconciliation or rebuild.