I just came across an instance where I was trying to get aa bunch of info back based upon an input.
I got an error saying that the input was to large and exceeded the tokens.
Is there somewhere that this can be adjusted up ?
@ihmunro you can adjust the token input / output length in the configure tab of the pickaxe.
Having said that be aware of the underlying model context limit. GPT-4-turbo and GPT-4o have a context length of 128k
1 Like
thanks AB
Will take a look