brianjkim21

this is sick, thanks for sharing

thanks roanak!

PMs and Execs are pushing devs to do docs classification and extract data from text ("see I can do it on chatGPT!") so they're using Taylor (trytaylor.ai) to build production grade text pipelines ;)

In all seriousness, customer support was the first but the least impactful area for LLMs. Currently, LLMs are primarily used for developer efficiency and for info retrieval.

thanks :) you too!

thanks! primarily classical. we designed an ensemble that considers both lexical & semantic similarity and trained on large datasets of labeled text.

we train our own 'out-of-the-box' models (like the intent classification, IAB, O*NET-SOC, NAICS) or you can create a custom model by just defining what labels you want.

Example? To clarify, I'm referring to product eng and SWEs.

If you have a Data / ML team, they will handle ofc.

thanks. yup, it's on our roadmap :)

yup, we designed an ensemble that considers both lexical & semantic similarity and trained on large datasets of labeled text. also building data pipelines to prevent models going stale.

max 20 docs per request for free api. no official max doc length but recently had issues with large (think book length) docs.

appreciate the feedback. will update, thanks.