What is the fundamental problem that needs to be solved after text chunks are extracted in a RAG pipeline?	Finding text chunks related to the user's question to add as context.
What is the most common method used to implement the search for related text chunks in a RAG pipeline?	Semantic search.
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 output format of an embedding model?	A long list of numbers (the embedding).
How should one conceptually view the individual numbers within a text embedding?	As scores of some quality of the input text.
What is the primary function of text embeddings within the RAG pipeline?	To allow the system to find text chunks semantically related to a user's question.
What is a common default length for the list of numbers (embedding) returned by an embedding model?	1024 elements.