Hello, when reproducing the results of ChatGPT in BIRD dataset, I use the src/get_request.py script. However, due to the API's rate limit, I still encounter rate limit issues when using this script. It seems that @backoff.on_exception() is not working as expected, and I continue to receive the error: "Rate limit reached for default-global-with-image-limits in organization org-CMicAqnTI2tgJqouosQgKqup on requests per min. Limit: 3 / min. Please try again in 20s." It appears that I may need to modify the code within the connect_gpt function by removing the try-except statements and keeping only return openai.Completion.create(engine=engine, prompt=prompt, max_tokens=max_tokens, temperature=temperature, stop=stop) to resolve this issue.
Hello, when reproducing the results of ChatGPT in BIRD dataset, I use the
src/get_request.py
script. However, due to the API's rate limit, I still encounter rate limit issues when using this script. It seems that@backoff.on_exception()
is not working as expected, and I continue to receive the error: "Rate limit reached for default-global-with-image-limits in organization org-CMicAqnTI2tgJqouosQgKqup on requests per min. Limit: 3 / min. Please try again in 20s." It appears that I may need to modify the code within the connect_gpt function by removing the try-except statements and keeping onlyreturn openai.Completion.create(engine=engine, prompt=prompt, max_tokens=max_tokens, temperature=temperature, stop=stop)
to resolve this issue.