Vector Podcast cover image

Connor Shorten - Research Scientist, Weaviate - ChatGPT, LLMs, Form vs Meaning

Vector Podcast

CHAPTER

How to Solve a Query That Hits in a Wrong Language Field

The only way to know this is to print that query execution formally if you will right and so you will see okay ah it hit in that in that let's say i don't know a french uh but i wasn't intending french i was doing jormana something why did it do that. When you tokenize your text it's the same problem as in dense search in a way like when you split text into paragraph so sentences there you need to split the tokens how you do split the tokens is dependent on how you model the semantics of what you are converting to to a token. If you have two documents which occur like one is like million times and the other one and one million plus one

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode