🤖AI & MLadvanced
Question 1 of 10
# RAG pipeline: # 1. Embed query # 2. Search vector DB # 3. Retrieve top-k docs # 4. LLM(query + docs) # Step 4 reduces?
What's the output?
Question 1 of 10
# RAG pipeline: # 1. Embed query # 2. Search vector DB # 3. Retrieve top-k docs # 4. LLM(query + docs) # Step 4 reduces?
What's the output?