Given this code

@job(config=build_and_validate_electrothermal_models_config)
def build_and_validate_electrothermal_models_job():
    model_assembly_results: Optional[ModelAssemblyResults] = \
        electrothermal_model_phase_group_op()
    electrothermal_model_selection_config = \
        DagsterElectrothermalModelSelectionConfig(
            single_cell_model_ids=model_assembly_results.single_cell_model_ids,
            consensus_model_ids=model_assembly_results.consensus_model_ids
        )

How do I fix the 'InvokedNodeOutputHandle' object has no attribute error

The error you're encountering suggests that you're trying to access attributes on an

InvokedNodeOutputHandle

object, which is not allowed. This object represents the output of an op or graph when it is invoked within a job or another graph, and it does not have the attributes you're trying to access. In the code snippet you provided, you're attempting to access

single_cell_model_ids

and

consensus_model_ids

attributes on the

model_assembly_results

variable, which seems to be the output of the

electrothermal_model_phase_group_op()

op. However, if

electrothermal_model_phase_group_op

is an op that yields an

Output

, you cannot directly access attributes on its result like this. To fix this issue, you need to ensure that the

electrothermal_model_phase_group_op

op is yielding an

Output

object that can be passed to downstream ops. If

electrothermal_model_phase_group_op

needs to yield multiple outputs, you should define it with multiple

Out

objects and yield

Output

objects accordingly. Here's an example of how you might structure an op with multiple outputs:

python from dagster import job, op, Out, Output  @op(out={"single_cell_model_ids": Out(), "consensus_model_ids": Out()}) def electrothermal_model_phase_group_op():     # Your logic here     yield Output(value=single_cell_model_ids, output_name="single_cell_model_ids")     yield Output(value=consensus_model_ids, output_name="consensus_model_ids")  @job def build_and_validate_electrothermal_models_job():     results = electrothermal_model_phase_group_op()     electrothermal_model_selection_config = DagsterElectrothermalModelSelectionConfig(         single_cell_model_ids=results.single_cell_model_ids,         consensus_model_ids=results.consensus_model_ids     )     # Use electrothermal_model_selection_config in subsequent ops

In this example,

electrothermal_model_phase_group_op

is defined with two named outputs. When you invoke this op within a job, you can access these outputs by their names. If you need to pass these outputs to another op, you would connect them in the job definition like so:

python @op def downstream_op(single_cell_model_ids, consensus_model_ids):     # Your logic here  @job def build_and_validate_electrothermal_models_job():     results = electrothermal_model_phase_group_op()     downstream_op(         single_cell_model_ids=results.single_cell_model_ids,         consensus_model_ids=results.consensus_model_ids     )

Make sure that the downstream ops are expecting the correct inputs and that the outputs from

electrothermal_model_phase_group_op

are connected correctly. If you continue to encounter issues, please check the documentation for the latest guidance on defining and connecting ops with multiple outputs.