What are the three core topics merged to form the complete RAG pipeline?	High-level overview of the RAG process, text embeddings, and text chunking.
What is the first step in the RAG pipeline when processing a source document?	Chunking the source document into separate pieces of text.
What is the purpose of generating embeddings for text chunks?	To convert the text chunks into numerical vectors that capture their meaning and context.
What does the normalization step do to the generated embeddings?	It scales the magnitude of each vector to 1.0.
What is a vector database optimized for?	Storing, comparing, and looking up long lists of numbers (embeddings).
How is a user query prepared before searching the vector database?	It is run through the exact same embedding model used for the source chunks.
What mathematical calculation is used to determine the relevance between the query and stored chunks?	Cosine similarity.
What does a high cosine similarity score (close to 1) indicate?	The two embeddings (query and chunk) are very similar.
How is Cosine Distance calculated, and what does a value close to zero indicate?	It is calculated as 1 minus the cosine similarity; a value close to zero indicates high similarity.
What is the final step in the RAG pipeline after a relevant text chunk is retrieved?	Adding the user's question and the relevant text chunk to the prompt and sending it to the LLM.