The post is a question from a community member asking if there is a way to set a max_token in the OpenAI block, as their assistant is using 19k tokens per query which is too expensive. The comments discuss the potential impact of setting a max_token limit, with some community members advising against it as it could cut off the assistant's response. Instead, they suggest instructing the model to not generate long answers. There is also a discussion about whether the max_token affects the input or output, and a suggestion to add a limit within the "send message" block to prevent users from sending messages that are too long.
Isn’t the max token affecting the input memory instead of the output? Also conversely, I know it’s possible to make a check for a long message sent by the user and ask them to write a shorter message but is it on your radar to add a limit within the send message block? Otherwise a user has to retype their message if they send a message that is too long
