Closed pdavis68 closed 1 year ago
Same thing here. I spent an hour writing a detailed prompt then another one answering 15 questions. Then ... CRASH
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-******* on tokens per min. Limit: 10000 / min. Please try again in 6ms. Contact us through our help center at help.openai.com if you continue to have issues.' error_param=None error_type=tokens message='OpenAI API error received' stream_error=False
Traceback (most recent call last):
File "/Users/robert.stone/.pyenv/versions/3.11.1/bin/gpt-engineer", line 8, in <module>
sys.exit(app())
^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/gpt_engineer/main.py", line 64, in main
messages = step(ai, dbs)
^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/gpt_engineer/steps.py", line 154, in gen_clarified_code
messages = ai.next(messages, dbs.preprompts["use_qa"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/gpt_engineer/ai.py", line 37, in next
response = openai.ChatCompletion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/openai/api_requestor.py", line 298, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/openai/api_requestor.py", line 700, in _interpret_response
self._interpret_response_line(
File "/Users/robert.stone/.pyenv/versions/3.11.1/lib/python3.11/site-packages/openai/api_requestor.py", line 763, in _interpret_response_line
raise self.handle_error_response(
openai.error.RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-******* on tokens per min. Limit: 10000 / min. Please try again in 6ms. Contact us through our help center at help.openai.com if you continue to have issues.
Anyone found solution for this?
I tried using sleep for upto 5 mins... Still not working...
seeing same issue ^^ :(
Same. Need to solve or at least know if I break into smaller components will it work.
same issue. any suggestions?
Doesn't seem like an issue with gpt-engineer but openai, happy to hear suggestions will close otherwise
I rotated my openai api key and that seemed to fix the issue...at least for now
I rotated my openai api key and that seemed to fix the issue...at least for now @snlamm Hey Can you please elaborate? Rotate the openai key like how?
The problem is that your prompt and clarifications are too extensive for your OpenAI plan. Depending on your OpenAI plan, your token limit can be around 10K/min and if you have written a long prompt or the application has too many lines of code generated, you can easily get over this limit.
On Azure OpenAI for gpt-4-32k you have a token limit of 60K/min and can use 32K token per request by default. I think OpenAI also enabled such sizes for enterprises now.
The only thing gpt-engineer could do is already warn upfront that your prompt is probably too too long, but I don’t think this is worth the effort at the moment, because the OpenAI error already explains the issue.
Expected Behavior
Expected GPT Engineer to do it's thing!
Current Behavior
It read my prompt. Asked a dozen questions which I answered in detail. Then:
Nothing more to clarify.
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-[orgid here] on tokens per min. Limit: 10000 / min. Please try again in 6ms. Contact us through our help center at help.openai.com if you continue to have issues.' error_param=None error_type=tokens message='OpenAI API error received' stream_error=False
Failure Information (for bugs)
This, I believe is the relevant portion of the stack:
File "c:\python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "c:\python310\scripts\gpt-engineer.exe__main__.py", line 7, in
sys.exit(app())
File "c:\python310\lib\site-packages\gpt_engineer\main.py", line 64, in main
messages = step(ai, dbs)
File "c:\python310\lib\site-packages\gpt_engineer\steps.py", line 154, in gen_clarified_code
messages = ai.next(messages, dbs.preprompts["use_qa"])
File "c:\python310\lib\site-packages\gpt_engineer\ai.py", line 37, in next
response = openai.ChatCompletion.create(
File "c:\python310\lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
Is there a way to rate limit the app? This is the only thing I was using it for.
My prompt was pretty detailed. About 150 lines.