What is the primary goal of the process that follows text chunk extraction in a RAG pipeline?	To find text chunks related to the user's query to add as context to the prompt.
What is the most common method used to implement the search for relevant text chunks in a RAG pipeline?	Semantic search.
What is a text embedding?	A numerical representation of the meaning contained in some text.
What component is responsible for generating text embeddings?	An embedding model.
What is the typical range of values found within a text embedding?	Negative 1 up to positive 1.
How should one conceptually think about the individual numbers within a text embedding?	They represent scores of some quality of the input text.
What specific model is used for generating text embeddings on Vertex?	text embedding 005.
What SDK is required to access the text embedding model on Vertex?	Vertex SDK (installed via pip install google-genai).