Fix the type hints of `step_one` and `step_two` in class `MultiStepWorkflow`
#88
by
renwei2024
- opened
If "Bad thing happened", the workflow should go back to method step_one, so the type of ev can be either StartEvent or LoopEvent.
Without this fix, we get the error about MultiStepWorkflow:
ERROR:asyncio:Exception in callback Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-81c386686b78', bound_args=<BoundArguments ()>, instance=<__main__.Mul...x781e13ffc810>, context=<_contextvars...x781e1c891780>)(<WorkflowHand...ate_result'")>) at /usr/local/lib/python3.11/dist-packages/llama_index/core/instrumentation/dispatcher.py:276
handle: <Handle Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-81c386686b78', bound_args=<BoundArguments ()>, instance=<__main__.Mul...x781e13ffc810>, context=<_contextvars...x781e1c891780>)(<WorkflowHand...ate_result'")>) at /usr/local/lib/python3.11/dist-packages/llama_index/core/instrumentation/dispatcher.py:276>
Traceback (most recent call last):
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/events.py", line 88, in __getattr__
return self._data[__name]
~~~~~~~~~~^^^^^^^^
KeyError: 'intermediate_result'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/context.py", line 618, in _step_worker
new_ev = await instrumented_step(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/instrumentation/dispatcher.py", line 370, in async_wrapper
result = await func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<ipython-input-8-e1ea6b7344cb>", line 26, in step_two
final_result = f"Finished processing: {ev.intermediate_result}"
^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/events.py", line 90, in __getattr__
raise AttributeError(
AttributeError: 'LoopEvent' object has no attribute 'intermediate_result'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/lib/python3.11/asyncio/events.py", line 84, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/instrumentation/dispatcher.py", line 288, in handle_future_result
raise exception
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/workflow.py", line 403, in _run_workflow
raise exception_raised
File "/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/context.py", line 627, in _step_worker
raise WorkflowRuntimeError(
llama_index.core.workflow.errors.WorkflowRuntimeError: Error in step 'step_two': 'LoopEvent' object has no attribute 'intermediate_result'
Bad thing happened
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/events.py in __getattr__(self, _Event__name)
87 try:
---> 88 return self._data[__name]
89 except KeyError:
KeyError: 'intermediate_result'
During handling of the above exception, another exception occurred:
AttributeError Traceback (most recent call last)
6 frames
AttributeError: 'LoopEvent' object has no attribute 'intermediate_result'
The above exception was the direct cause of the following exception:
WorkflowRuntimeError Traceback (most recent call last)
/usr/local/lib/python3.11/dist-packages/llama_index/core/workflow/context.py in _step_worker(self, name, step, config, stepwise, verbose, checkpoint_callback, run_id, service_manager, dispatcher)
625 except Exception as e:
626 if config.retry_policy is None:
--> 627 raise WorkflowRuntimeError(
628 f"Error in step '{name}': {e!s}"
629 ) from e
WorkflowRuntimeError: Error in step 'step_two': 'LoopEvent' object has no attribute 'intermediate_result'