the `isWithinTokenLimit` may be broken
Closed this issue · 1 comments
zhouhan760503 commented
the `isWithinTokenLimit` may be broken
running
import { isWithinTokenLimit } from 'gpt-tokenizer';
isWithinTokenLimit(
lastMessage.message,
1000,
);
throws Model name must be provided either during initialization or passed in to the method
for
"gpt-tokenizer": "^2.1.2",
cc @thdoan
Originally posted by @michaelfarrell76 in https://github.sheincorp.cn/niieani/gpt-tokenizer/issues/37#issuecomment-1778736225
ngo275 commented
import { isWithinTokenLimit } from "gpt-tokenizer/model/gpt-3.5-turbo";
I got the same issue. You will need to specify the model when importing functions.