adaptiv
November 22, 2023, 12:40am
7
Thanks for this information. Seems that 3.5-turbo is really broken. Also noticed that it re-generates messages over the assistant API up to 20x per run.
Here my bug report:
I am seeing a huge issue with a very basic implementation of the Assitant API on the gpt-3.5-turbo model.
Background-Information to our use case: We try to analyse documents and extract information. For this, we created one assistant with instructions on what to do with the document (document is given over user message).
For every document (roughly 6000 in total) we do the following:
Create a thread on the assistant which we created over the playground
Add the “user” message to the thread. T…