Discussion on "What the Heck is RAG? And How to Build It"

Sam Borges · 2024-02-27T04:30:01.691Z

What You’ll Learn Overview of Retrieval-Augmented Generation (RAG) Components of RAG (indexing, retrieval, augmentation, generation) How to build a naive RAG workflow in Python TL;DR Retrieval-Augmented Generation (RAG) is a technique that enhan...

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.

Search Hashnode

What the Heck is RAG? And How to Build It

Responses