Build and Configure RAG Applications GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 1)

Questions 1–5

1. 1foundation · easy

   Which element of a RAG application specifies the expected input and output format for the model, ensuring that the serving endpoint can correctly parse requests and responses?

   • ARetriever
   • BModel signature
   • CInput examples
   • DEmbedding model
   Reveal Solution Discussion Select an answer first
2. 2foundation · easy

   Which API or SDK method is used to query a Mosaic AI Vector Search index to retrieve documents similar to a given query vector?

   • AVectorSearchClient().delete_index()
   • BVectorSearchClient().get_index().similarity_search()
   • CVectorSearchClient().create_index()
   • DVectorSearchClient().list_indexes()
   Reveal Solution Discussion Select an answer first
4. 3foundation · easy

   In Mosaic AI Vector Search, what is the role of an endpoint?

   • AIt stores the actual vector data and embeddings
   • BIt provides a REST API to query indexes and manage them
   • CIt generates embeddings for text chunks
   • DIt defines the schema for the vector index
   Reveal Solution Discussion Select an answer first
5. 4foundation · easy

   Which configuration option for a Vector Search index determines whether the index is automatically updated when the source Delta table changes?

   • AEmbedding source
   • BIndex schema
   • CSync mode
   • DEndpoint type
   Reveal Solution Discussion Select an answer first
6. 5foundation · easy

   When configuring vector search for a solution with a large number of embeddings and low-latency query requirements, which trade-off is most relevant?

   • ASimpler schema for faster indexing
   • BFewer embeddings for better coverage
   • CLower update frequency for better accuracy
   • DHigher storage cost for faster retrieval
   Reveal Solution Discussion Select an answer first