Building LLM Apps & the Challenges that come with it. The What's AI Podcast Episode 16: Jay Alammar
What's AI Podcast by Louis-François Bouchard
How to Power Your Search With LLMs
The re-ranker is basically a classifier that classifies, it has two parts of text. It's what's called the crossing code. And once you train it, you just plug it into an existing search system. The previous step can use embeddings or cannot. But then it gives a relevance score for each of the 100 results. And then you just sort by that relevance. That becomes just one signal for your search that you can either just use and sort by the most relevant or then you can use other signals. If you're rolling out actual search systems, you want other signals. So assign a signal for recent documents. Or if you're building search for Google Maps
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
