Comment by Parth Kamal on "What the Heck is RAG? And How to Build It"

Feb 27, 2024

so does rag acts like a new training data which llm uses to give the response. aur it is just to make the query more contextualised. during rag enabled user interaction with a llm. does llm runs on that vector db which rag gives to it? just a query , I am new into it.

Sam Borges

shadowy super coder

Feb 27, 2024

That's a great question. The LLM does not interact with the vector database. The query is more contextualize before going to the LLM.

The original query gets augmented/changed but appending the additional context BEFORE it gets to the LLM.

Here's a quick example:

Original query: "what is my sick leave policy?" RAG query: "using the provided context, answer the question. Question: what is my sick leave policy? Context: <TEXT RETRIEVED FROM DOCUMENTS IN RAG>"

Then this RAG query is sent to the LLM.

Hope that helps! Let me know if you have any other questions.

now I understood. thanks for replying !

Search Hashnode