Environment is GCC High but I dont think this matters here.
The step was a straight make deploy with secure flag off using gpt-35-turbo.
The infra and webapp built and deployed but I was seeing this in the logs, failing to startup:
File "/home/site/wwwroot/app.py", line from approaches.mathas File "/home/site/wwwroot/approaches/mathassistant.py", line 1 tools = load_tools(["llm-math","wikipedia ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/langchain_core/load/serializable.py", line 1 super().__init__(* File "/usr/local/lib/python3.12/site-packages/pydantic/main.py", line 2 validated_self = self.__pydantic_validator__.validate_python(data, self ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/pydantic/_internal/_mock_val_ser.py", line 100, raise PydanticUserError(self._error_message, c pydantic.errors.PydanticUserError:LLMMathChainis not fully defined; you should defineBaseCache, then call LLMMathChain.model_rebuild().
Steps To Reproduce
Pull and make deploy from main branch, it is 100% reproducible for me.
Webapp frontend will not be available and fails to startup
Investigate LogStream or Workbook to see above logs
Information Assistant details
Please provide the following details. You can simply include a screenshot of your Info panel as well.
GitHub branch: main as of this ticket creation
What region is your Azure Open AI Service in?
usgovvirginia
What ChatGPT model are you using?
gpt-35-turbo
model name: (i.e. gpt-3.5-turbo, gpt-4)
gpt-35-turbo
model version: (i.e. 0613)
1106
What embeddings model are you using?
text-embedding-ada-02
Additional context
PR Coming for consideration or iteration
If the bug is confirmed, would you be willing to submit a PR?
Bug Details
Environment is GCC High but I dont think this matters here.
The step was a straight make deploy with secure flag off using gpt-35-turbo. The infra and webapp built and deployed but I was seeing this in the logs, failing to startup:
File "/home/site/wwwroot/app.py", line from approaches.mathas File "/home/site/wwwroot/approaches/mathassistant.py", line 1 tools = load_tools(["llm-math","wikipedia ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/langchain_core/load/serializable.py", line 1 super().__init__(* File "/usr/local/lib/python3.12/site-packages/pydantic/main.py", line 2 validated_self = self.__pydantic_validator__.validate_python(data, self ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/pydantic/_internal/_mock_val_ser.py", line 100, raise PydanticUserError(self._error_message, c pydantic.errors.PydanticUserError:LLMMathChainis not fully defined; you should defineBaseCache, then call LLMMathChain.model_rebuild().Steps To Reproduce
Information Assistant details
Please provide the following details. You can simply include a screenshot of your Info panel as well.
Additional context PR Coming for consideration or iteration
If the bug is confirmed, would you be willing to submit a PR?