Create option for Azure GPT4-Turbo - Error creating workflow run from prompt #1854
Comments
|
Interesting -- could you try running with GPT-4O instead of GPT-4? |
|
I don't have quota for GPT-4O, just turbo |
|
That's a bummer — 4O is both cheaper and more effective. We were thinking about dropping support for Turbo alltogehter |
|
Alright I understand, but just to allow everyone have access, please can you reconsider? |
I'll take a look tonight / tomorrow -- I think I introduced a regression with turbo! Sorry about that |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Error on UI:
Error creating workflow run from prompt
Request failed with status code 500
Error from docker logs:
xxxx@xxxx:~/Desktop/skyvern$ sudo docker logs e665a018aba3
INFO [alembic.runtime.migration] Context impl PostgresqlImpl.
INFO [alembic.runtime.migration] Will assume transactional DDL.
Alembic mode: online
INFO [alembic.runtime.migration] Context impl PostgresqlImpl.
INFO [alembic.runtime.migration] Will assume transactional DDL.
Alembic mode: online
No new upgrade operations detected.
Creating organization and API token...
.streamlit/secrets.toml file updated with organization details.
Starting Xvfb...
2025-02-28T11:43:03.225782Z [info ] Agent server starting. host=0.0.0.0 port=8000
INFO: Will watch for changes in these directories: ['/app']
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO: Started reloader process [59] using WatchFiles
2025-02-28T11:43:13.747037Z [info ] Initializing ForgeAgent browser_action_timeout_ms=5000 browser_type=chromium-headful debug_mode=False env=local execute_all_steps=True long_running_task_warning_ratio=0.95 max_scraping_retries=0 max_steps_per_run=10 video_path=/data/videos
Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.
2025-02-28T11:45:53.019874Z [error ] LLM request failed unexpectedly llm_key=AZURE_OPENAI
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/litellm/main.py", line 466, in acompletion
response = await init_response
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 660, in acompletion
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 611, in acompletion
headers, response = await self.make_azure_openai_chat_completion_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 324, in make_azure_openai_chat_completion_request
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 316, in make_azure_openai_chat_completion_request
raw_response = await azure_client.chat.completions.with_raw_response.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_legacy_response.py", line 381, in wrapped
return cast(LegacyAPIResponse[R], await func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1927, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1856, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1550, in request
return await self._request(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1651, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Unrecognized request argument supplied: max_completion_tokens', 'type': 'invalid_request_error', 'param': None, 'code': None}}
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/skyvern/forge/sdk/api/llm/api_handler_factory.py", line 297, in llm_api_handler
response = await litellm.acompletion(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/utils.py", line 1358, in wrapper_async
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/utils.py", line 1217, in wrapper_async
result = await original_function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/main.py", line 485, in acompletion
raise exception_type(
^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2201, in exception_type
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 1948, in exception_type
raise BadRequestError(
litellm.exceptions.BadRequestError: litellm.BadRequestError: AzureException BadRequestError - Unrecognized request argument supplied: max_completion_tokens
2025-02-28T11:45:53.031203Z [error ] LLM failure to initialize observer cruise
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/litellm/main.py", line 466, in acompletion
response = await init_response
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 660, in acompletion
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 611, in acompletion
headers, response = await self.make_azure_openai_chat_completion_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 324, in make_azure_openai_chat_completion_request
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/llms/azure/azure.py", line 316, in make_azure_openai_chat_completion_request
raw_response = await azure_client.chat.completions.with_raw_response.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_legacy_response.py", line 381, in wrapped
return cast(LegacyAPIResponse[R], await func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1927, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1856, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1550, in request
return await self._request(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1651, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Unrecognized request argument supplied: max_completion_tokens', 'type': 'invalid_request_error', 'param': None, 'code': None}}
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/skyvern/forge/sdk/api/llm/api_handler_factory.py", line 297, in llm_api_handler
response = await litellm.acompletion(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/utils.py", line 1358, in wrapper_async
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/utils.py", line 1217, in wrapper_async
result = await original_function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/main.py", line 485, in acompletion
raise exception_type(
^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2201, in exception_type
raise e
File "/usr/local/lib/python3.11/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 1948, in exception_type
raise BadRequestError(
litellm.exceptions.BadRequestError: litellm.BadRequestError: AzureException BadRequestError - Unrecognized request argument supplied: max_completion_tokens
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/app/skyvern/forge/sdk/routes/agent_protocol.py", line 1237, in create_task_v2
task_v2 = await task_v2_service.initialize_task_v2(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/skyvern/forge/sdk/services/task_v2_service.py", line 125, in initialize_task_v2
metadata_response = await app.LLM_API_HANDLER(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/skyvern/forge/sdk/api/llm/api_handler_factory.py", line 316, in llm_api_handler
raise LLMProviderError(llm_key) from e
skyvern.forge.sdk.api.llm.exceptions.LLMProviderError: Error while using LLMProvider AZURE_OPENAI
docker-compose.yml:
target URI:
https://xxxx.openai.azure.com/openai/deployments/gpt-4/chat/completions?api-version=2025-01-01-preview
The text was updated successfully, but these errors were encountered: