New RunLLM response generated >>> Question Hello for an ML p Flyte #runllm-flyte-trial

New RunLLM response generated: >>>*# Question* He...

jolly-florist-66728

11/11/2024, 6:15 PM

New RunLLM response generated: >>>*# Question* Hello, for an ML project I am trying to divide work across multiple workers using

map_task

Copy code

@workflow
def ntrk_mutation_analysis_workflow() -> None:
    load_dotenv()
    mlflow_run_id = create_run()
    raw_data: pd.DataFrame = ingest_data(
        project_name=PROJECT_NAME, bucket_name=BUCKET_NAME, file_name=FILE_NAME
    )
    preprocessed_data: FlyteFile = preprocess(raw_data=raw_data)

    log_parameters(mlflow_run_id=mlflow_run_id)

    batches = create_batches(flyte_file=preprocessed_data)
    predicted_responses: list[int] = map_task(generate_ai_response)(
        batch=batches
    )

where

create_batches

returns a

list[int]

of indexing for the batches. In

generate_ai_response

I am trying to read a

FlyteFile

and then index using the

batches

. for now I am getting this error:

Copy code

[32]: code:"Error" message:"\r\n[fe32955ef6b4c42b984b-n5-0-32] terminated with exit code (1). Reason [Error]. Message: \n                                                 │\n│ /opt/venv/lib/python3.11/site-packages/flytekit/exceptions/scopes.py:178 in  │\n│ system_entry_point                                                           │\n│                                                                              │\n│ ❱ 178 │   │   │   │   return wrapped(*args, **kwargs)                        │\n│                                                                              │\n│ /opt/venv/lib/python3.11/site-packages/flytekit/bin/entrypoint.py:426 in     │\n│ _execute_map_task                                                            │\n│                                                                              │\n│ ❱ 426 │   │   mtr = load_object_from_module(resolver)()                      │\n│                                                                              │\n│ /opt/venv/lib/python3.11/site-packages/flytekit/tools/module_loader.py:43 in │\n│ load_object_from_module                                                      │\n│                                                                              │\n│ ❱ 43 │   class_obj_mod = importlib.import_module(\".\".join(class_obj_mod))    │\n│                                                                              │\n│ /usr/local/lib/python3.11/importlib/__init__.py:126 in import_module         │\n│                                                                              │\n│ ❱ 126 │   return _bootstrap._gcd_import(name[level:], package, level)        │\n│ in _gcd_import:1201                                                          │\n│ in _sanity_check:1114                                                        │\n╰──────────────────────────────────────────────────────────────────────────────╯\nValueError: Empty module name\n."
... and many more.

where

generate_ai_response

just does this for now:

Copy code

@task
def generate_ai_response(batch: int) -> int:
    return batch

jolly-florist-66728

11/11/2024, 6:15 PM

>>

What could the issue be? # Answer The error

ValueError: Empty module name

suggests that there might be an issue with how the module or task is being referenced or imported. This is a common issue when using

map_task

in Flyte, as seen in similar cases where the module path is not correctly specified or the environment setup is incorrect. 1. Check Module Path: Ensure that the module path for

generate_ai_response

is correctly specified in your Flyte project. The task should be properly imported and referenced in the workflow. 2. Environment Setup: Verify that your Python environment is correctly set up and that all necessary packages are installed. Issues can arise if the virtual environment is not correctly configured or if the

pyflyte

command is not executed in the right context. 3. Directory Structure: Make sure that your directory structure is correct and that all necessary

__init__.py

files are present to ensure Python recognizes the directories as packages. Would you like more detail on any of these points? Sources: - Flyte GitHub Issue - Flyte Community Discussion Slack Link https://.slack.com/archives/CP2HDHKE1/p1731348894.967559 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.

Open in Slack

Previous Next