[Bug]: Internal Server Error in Reasoning Engine Deployment

[avineet123]

File Name

N/A

What happened?

Deployment is successful, but when calling the ReasoningEngine, an InternalServerError occurs with the error message: "create_app() takes 0 positional arguments but 1 was given." This error happens when invoking the agent after creating it using remote_agent.

I am setting up a multi-agent system using create_react_agent as follows:
from langgraph.prebuilt import create_react_agent
tools = [get_weather]
agent1 = create_react_agent(model=llm, state_modifier=format_for_model, tools=tools, state_schema=AgentState)

For deployment, the following code is used:
remote_agent = reasoning_engines.ReasoningEngine.create(
SampleAgent(project=PROJECT_ID, location=LOCATION),
requirements=[
"google-cloud-aiplatform[langchain,reasoningengine]",
"cloudpickle==3.1.0",
"pydantic",
"langgraph",
"langchain-google-community",
"google-cloud-discoveryengine"
],
display_name=INSTANCE_NAME,
description="test langgraph toolnode",
extra_packages=[
"prompt.yaml"
],
)
remote_agent.query(message=message, chat_id="demo_1")

Relevant log output

Log ERROR:
`DEFAULT 2024-12-16T16:39:27.223290Z INFO: Application startup complete.
DEFAULT 2024-12-16T16:39:27.223330Z INFO: Application startup complete.
DEFAULT 2024-12-16T16:39:27.223422Z INFO: ASGI 'lifespan' protocol appears unsupported.
DEFAULT 2024-12-16T16:39:27.223535Z INFO: Application startup complete.
DEFAULT 2024-12-16T16:39:27.224799Z INFO: Started server process [7]
DEFAULT 2024-12-16T16:39:27.224859Z INFO: Waiting for application startup.
DEFAULT 2024-12-16T16:39:27.224984Z INFO: ASGI 'lifespan' protocol appears unsupported.
DEFAULT 2024-12-16T16:39:27.225038Z INFO: Application startup complete.

POST /api/reasoning_engine HTTP/1.1" 500 Internal Server Error"
 create_app() takes 0 positional arguments but 1 were given .`
 




STACK TRACE:
`---------------------------------------------------------------------------
_InactiveRpcError                         Traceback (most recent call last)
File \myenv\Lib\site-packages\google\api_core\grpc_helpers.py:76, in _wrap_unary_errors.<locals>.error_remapped_callable(*args, **kwargs)
     75 try:
---> 76     return callable_(*args, **kwargs)
     77 except grpc.RpcError as exc:

File \myenv\Lib\site-packages\grpc\_channel.py:1181, in _UnaryUnaryMultiCallable.__call__(self, request, timeout, metadata, credentials, wait_for_ready, compression)
   1175 (
   1176     state,
   1177     call,
   1178 ) = self._blocking(
   1179     request, timeout, metadata, credentials, wait_for_ready, compression
   1180 )
-> 1181 return _end_unary_response_blocking(state, call, False, None)

File \myenv\Lib\site-packages\grpc\_channel.py:1006, in _end_unary_response_blocking(state, call, with_call, deadline)
   1005 else:
-> 1006     raise _InactiveRpcError(state)

_InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.FAILED_PRECONDITION
	details = "Reasoning Engine Execution failed.
Please navigate to the Cloud Console Log Explorer page (https://console.cloud.google.com/logs/query;query=resource.type="aiplatform.googleapis.com%2FReasoningEngine"%0Aresource.labels.reasoning_engine_id=~""?project=) to view the specific errors. Additionally, please check our troubleshooting guide (https://cloud.google.com/vertex-ai/generative-ai/docs/reasoning-engine/troubleshooting/use) for more information, or visit our Cloud community forum (https://www.googlecloudcommunity.com/gc/AI-ML/bd-p/cloud-ai-ml) or GitHub repository (https://github.com/googleapis/python-aiplatform/issues) to find answers and ask for help.
Error Details: Internal Server Error"
	debug_error_string = "UNKNOWN:Error received from peer ipv6:%5%5D:43 {grpc_message:"Reasoning Engine Execution failed.\nPlease navigate to the Cloud Console Log Explorer page (https://console.cloud.google.com/logs/query;query=resource.type=\"aiplatform.googleapis.com%2FReasoningEngine\"%0Aresource.labels.reasoning_engine_id=~\"\"?project=) to view the specific errors. Additionally, please check our troubleshooting guide (https://cloud.google.com/vertex-ai/generative-ai/docs/reasoning-engine/troubleshooting/use) for more information, or visit our Cloud community forum (https://www.googlecloudcommunity.com/gc/AI-ML/bd-p/cloud-ai-ml) or GitHub repository (https://github.com/googleapis/python-aiplatform/issues) to find answers and ask for help.\nError Details: Internal Server Error", grpc_status:9, created_time:"2024-12-16T16:05:39.6172289+00:00"}"
>

The above exception was the direct cause of the following exception:

FailedPrecondition                        Traceback (most recent call last)
Cell In[119], line 2
      1 message = "What is weather today?"
----> 2 response=remote_agent.query(message=message, chat_id="demo_1")
      3 display(Markdown(response))

File \myenv\Lib\site-packages\vertexai\reasoning_engines\_reasoning_engines.py:763, in _wrap_query_operation.<locals>._method(self, **kwargs)
    762 def _method(self, **kwargs) -> _utils.JsonDict:
--> 763     response = self.execution_api_client.query_reasoning_engine(
    764         request=aip_types.QueryReasoningEngineRequest(
    765             name=self.resource_name,
    766             input=kwargs,
    767             class_method=method_name,
    768         ),
    769     )
    770     output = _utils.to_dict(response)
    771     return output.get("output", output)

File \myenv\Lib\site-packages\google\cloud\aiplatform_v1beta1\services\reasoning_engine_execution_service\client.py:795, in ReasoningEngineExecutionServiceClient.query_reasoning_engine(self, request, retry, timeout, metadata)
    792 self._validate_universe_domain()
    794 # Send the request.
--> 795 response = rpc(
    796     request,
    797     retry=retry,
    798     timeout=timeout,
    799     metadata=metadata,
    800 )
    802 # Done; return the response.
    803 return response

File \myenv\Lib\site-packages\google\api_core\gapic_v1\method.py:131, in _GapicCallable.__call__(self, timeout, retry, compression, *args, **kwargs)
    128 if self._compression is not None:
    129     kwargs["compression"] = compression
--> 131 return wrapped_func(*args, **kwargs)

File \myenv\Lib\site-packages\google\api_core\grpc_helpers.py:78, in _wrap_unary_errors.<locals>.error_remapped_callable(*args, **kwargs)
     76     return callable_(*args, **kwargs)
     77 except grpc.RpcError as exc:
---> 78     raise exceptions.from_grpc_error(exc) from exc`

Code of Conduct

• I agree to follow this project's Code of Conduct

[koverholt]

Thanks for opening this issue. It appears that you're passing remote_agent.query(message=message), whereas the kwarg to the query method should be remote_agent.query(input=message). And there is not a chat_id kwarg, but rather you can pass a unique session_id via the config kwarg. Then your resulting code will look something like:

response = agent.query(
    input=message,
    config={"configurable": {"session_id": "demo_1"}},
)

Refer to the docs and sample notebook to see how to pass the input as well as the session ID in a chat session for an agent with memory.

[koverholt]

And since this repository deals with sample notebooks and apps rather than direct usage of specific services, you can instead file follow-up bugs or feature requests in the Vertex AI public issue tracker here: https://issuetracker.google.com/issues/new?component=1130925&template=1637248. Hope that helps!