Connor Shorten - Research Scientist, Weaviate - ChatGPT, LLMs, Form vs Meaning
Vector Podcast
00:00
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
Transcript
Play full episode
