Not handled out of request count, save the state instead. #713
Comments
logunovFGP
added
bug
|
To be clear, the main issue here that I have answered already, but gpt-engineer not handled exception lead to the context not saved, so when I started the project again, it started from the same question, which means:
Is that possible to each answer in memory immediately instead waiting for all answer to handle such case as workaround? |
|
Thanks for the report! First of all: @lukaspetersson (as reviewer of ai.py) do we need to add a catch somewhere for RateLimitError? Generally: We are actively working on making gpt-engineer simpler, with shorter prompts etc, for example PR #733 @logunovFGP |
ATheorell
removed
the
triage
|
|
Closing with the merging of #741 . Let us know if the error persists @logunovFGP |
Policy and info
Expected Behavior
gpt-engineer not crashing, saving the state and proposes continue later
Current Behavior
GPT-engineer crashes in endless loop attempting to request the data. The whole conversation is not cached so I need to perform input from scratch and waste credits to re-input information.
Failure Information
GPT-4 LLM.
Steps to Reproduce
Just attempt to give large input when gpt-engineer has lots of questions, I spent 30 mins answering questions.
Failure Logs
Nothing more to clarify.
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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
WARNING:langchain.llms.base:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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..
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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
WARNING:langchain.llms.base:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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..
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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
WARNING:langchain.llms.base:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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..
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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
WARNING:langchain.llms.base:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 8.0 seconds as it raised RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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..
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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
WARNING:langchain.llms.base:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 10.0 seconds as it raised RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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..
INFO:openai:error_code=rate_limit_exceeded error_message='Rate limit reached for 10KTPM-200RPM in organization org-8JuGfI1rBZ1rbbaeM3CSLawd 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 "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Scripts\gpt-engineer.exe_main_.py", line 7, in
sys.exit(app())
^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\gpt_engineer\main.py", line 96, in main
messages = step(ai, dbs)
^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\gpt_engineer\steps.py", line 199, in gen_clarified_code
messages = ai.next(messages, dbs.preprompts["generate"], step_name=curr_fn())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\gpt_engineer\ai.py", line 173, in next
response = self.llm(messages, callbacks=callsbacks) # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\base.py", line 551, in call
generation = self.generate(
^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\base.py", line 309, in generate
raise e
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\base.py", line 299, in generate
self._generate_with_cache(
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\base.py", line 446, in _generate_with_cache
return self._generate(
^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\openai.py", line 334, in _generate
for chunk in self._stream(
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\openai.py", line 305, in _stream
for chunk in self.completion_with_retry(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\openai.py", line 278, in completion_with_retry
return _completion_with_retry(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\tenacity_init_.py", line 289, in wrapped_f
return self(f, *args, **kw)
^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\tenacity_init_.py", line 379, in call
do = self.iter(retry_state=retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\tenacity_init_.py", line 325, in iter
raise retry_exc.reraise()
^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\tenacity_init_.py", line 158, in reraise
raise self.last_attempt.result()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Logun\AppData\Local\Programs\Python\Python311\Lib\concurrent\futures_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "C:\Users\Logun\AppData\Local\Programs\Python\Python311\Lib\concurrent\futures_base.py", line 401, in __get_result
raise self._exception
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\tenacity_init_.py", line 382, in call
result = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\langchain\chat_models\openai.py", line 276, in _completion_with_retry
return self.client.create(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\openai\api_requestor.py", line 298, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\site-packages\openai\api_requestor.py", line 700, in _interpret_response
self._interpret_response_line(
File "G:\REPOS\PROJECTS\aviator-game-test.venv\Lib\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-8JuGfI1rBZ1rbbaeM3CSLawd 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.
The text was updated successfully, but these errors were encountered: