anirudhb99

member of the gemini team here -- personally, i'd recommend directly using gemini vs the document understanding services for OCR & general docs understanding tasks. From our internal evals gemini is now stronger than these solutions and is only going to get much better (higher precision, lower hallucination rates) from here.

thanks a ton for all the amazing feedback on this thread! if

(a) you have document understanding use cases that you'd like to use gemini for (the more aspirational the better) and/or

(b) there are loss cases for which gemini doesn't work well today,

please feel free to email [email protected] and we'd love to help get your use case working & improve quality for our next series of model updates!

(from the gemini team) we're working on it! semantic chunking & extraction will definitely be possible in the coming months.