Rate limit reached

[alasharim]

i am receiving this error when trying to run with modal:

openai.error.RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-o8pnXYMZiNBFvGP0dQH0exyg on requests per min. Limit: 3 / min. Please try again in 20s.

[ether8unny]

I am getting a similar error

[ZachHandley]

I reached this error as well, but using GPT4 with 4000 tokens/min rate limit reached

[MohHeader]

I got the same issue, fixed it by minor code adjustment

+import time

-           for filename, filecode in generate_file.map(
-                list_actual, order_outputs=False, kwargs=dict(filepaths_string=filepaths_string, shared_dependencies=shared_dependencies, prompt=prompt)
-            ):
-                write_file(filename, filecode, directory)

+            for actual in list_actual:
+              filename, filecode = generate_file(actual, filepaths_string=filepaths_string, shared_dependencies=shared_dependencies, prompt=prompt)
+              write_file(filename, filecode, directory)
+              time.sleep(30)  # wait for 30 seconds

so it just wait 30 seconds between API calls

[meadow-kun]

Got the issue as well. Would be good with some config parameter as a measure against this.

[teknightstick]

+import time

•       for filename, filecode in generate_file.map(
  

•            list_actual, order_outputs=False, kwargs=dict(filepaths_string=filepaths_string, shared_dependencies=shared_dependencies, prompt=prompt)
  

•        ):
  

•            write_file(filename, filecode, directory)
  

•        for actual in list_actual:
  

•          filename, filecode = generate_file(actual, filepaths_string=filepaths_string, shared_dependencies=shared_dependencies, prompt=prompt)
  

•          write_file(filename, filecode, directory)
  

•          time.sleep(30)  # wait for 30 seconds
  

Where exactly did you put this?

[brucemeek]

import time goes at the top with the other imports line 175 in main.py

[teknightstick]

Awesome I can confirm that adding this delay made the rate limit error disappear. I am using gpt4

[swyxio]

thanks guys, i will try to solve this rate limit issue at the library level