Video ID: friueqL7-LQ
YouTube URL: https://www.youtube.com/watch?v=friueqL7-LQ
Added At: 29-06-25 12:51:27
Processed: No
Sentiment: Error
Categories: Aiagent Artificialintelligence
Tags: vectorreranking, ragagent, artificialintelligence
Summary
Transcript
Here's how to instantly make your rag agent smarter with reranking. Okay, so let's get started. I'm going to real quick hop into an Excalibraw and actually explain what's going on behind the scenes when we do rag so that we all understand how the reranker is going to work. So the first step with rag obviously is we want to get our text document into a vector database. And how that works is the document is split up into smaller manageable chunks. The chunks are then fed into an embeddings model and the embeddings model turns them into a numerical representation of the meaning of what's in this chunk. and then they get placed somewhere in that multi-dimensional space which is our vector database. From there we go to search through it. So let's say this text document right here was the rules of golf. If we now go to ask what do I do if my ball goes out of bounds, this question is getting embedded the same way these chunks did up here with the exact same embeddings model and then it also gets placed in that multi-dimensional vector database. So then our question gets vectorzed and it's placed right here. And then it basically is going to grab the nearest other vectors because that's how it knows they're similar in meaning and it's going to pull them back. So it pulls back these three vectors in this case and then these vectors get turned back into their textbased chunks and those chunks get fed into our rag agent which it's able to use to answer our question. Anyways, what happens when we use a reranker is pretty cool because this allows us to basically pull back way more than just the three nearest neighbors. we can pull back 10, 20 or 30 vectors because all of these are going to get fed into the reranker and then it will basically look at which ones are actually the most relevant. It will assign a relevant score and then it will grab just the top three most relevant answers. So, I know that was quick, but hopefully at least it makes sense. And now let's hop back into nitn and take a look at how we set this up. If you want to watch the full breakdown, click on that play button right here.