What is the primary goal of the step following text chunk extraction in a RAG pipeline?	To find and surface text chunks related to the user's submitted question to use as context in the prompt.
What fundamental type of problem is the process of finding related text chunks considered?	A search problem.
What is the most common technique used to implement this search within a RAG pipeline?	Semantic search.
What component is utilized by semantic search to understand the meaning of text?	Text embeddings.
Define 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 structure and range of values found within a text embedding?	A long list of numbers, which can range from negative one up to positive one.
How should one conceptually interpret the individual numbers within a text embedding?	As scores representing different qualities or features of the input text.
Which external provider is recommended for generating text embeddings, as Anthropic does not currently offer this service?	Voyage AI.
When configuring the Voyage AI API key in the `.env` file, what specific variable name must be used?	voyage_api_key.