nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #314

You work for a media company that operates a streaming movie platform where users can search for movies in a database. The existing search algorithm uses keyword matching to return results…

The correct answer is B. Configure Vertex AI Vector Search as the search platform's backend. Vertex AI Vector Search is specifically designed for semantic search. It allows you to index metadata-rich data, such as movie details, and enables advanced query capabilities by embedding search queries and indexed data into vector space for similarity matching. This solution…

Submitted by mike_84· Apr 18, 2026ML model development

Question

You work for a media company that operates a streaming movie platform where users can search for movies in a database. The existing search algorithm uses keyword matching to return results. Recently, you have observed an increase in searches using complex semantic queries that include the movies' metadata such as the actor, genre, and director. You need to build a revamped search solution that will provide better results, and you need to build this proof of concept as quickly as possible. How should you build the search platform?

Options

  • AUse a foundational large language model (LLM) from Model Garden as the search platform's
  • BConfigure Vertex AI Vector Search as the search platform's backend.
  • CUse a BERT-based model and host it on a Vertex AI endpoint.
  • DCreate the search platform through Vertex AI Agent Builder.

How the community answered

(14 responses)
  • B
    86% (12)
  • C
    7% (1)
  • D
    7% (1)

Explanation

Vertex AI Vector Search is specifically designed for semantic search. It allows you to index metadata-rich data, such as movie details, and enables advanced query capabilities by embedding search queries and indexed data into vector space for similarity matching. This solution is well-suited for handling complex semantic queries based on metadata (e.g., actor, genre, director) and can be quickly implemented for a proof of concept. It is also scalable and can integrate seamlessly with the existing search infrastructure.

Topics

#Semantic Search#Vector Search#Vertex AI Vector Search#ML System Design

Community Discussion

No community discussion yet for this question.

Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice