< Marvin> I am getting the following warnings on prefect `v2 Prefect Community #ask-marvin

<@ULVA73B9P> I am getting the following warnings o...

Abyaya Lamsal

03/06/2025, 12:26 AM

@Marvin I am getting the following warnings on prefect

v2.20.16

. How do I resolve them?

Copy code

/usr/local/lib/python3.10/site-packages/prefect/utilities/dispatch.py:162: UserWarning: Type 'KubernetesClusterConfig' at /usr/local/lib/python3.10/site-packages/prefect_kubernetes/credentials.py:40 has key 'kubernetes-cluster-config' that matches existing registered type 'KubernetesClusterConfig' from /usr/local/lib/python3.10/site-packages/prefect/blocks/kubernetes.py:28. The existing type will be overridden.
  warnings.warn(
/usr/local/lib/python3.10/site-packages/pydantic/v1/schema.py:631: UserWarning: Callable print_func was excluded from schema since JSON schema has no equivalent type.
  warnings.warn(skip.message, UserWarning)
/usr/local/lib/python3.10/site-packages/pydantic/_internal/_generate_schema.py:775: UserWarning: Mixing V1 models and V2 models (or constructs, like `TypeAdapter`) is not supported. Please upgrade `KubernetesJob` to V2.
  warn(
Worker 'KubernetesWorker 3360fcf9-1016-4cf0-a375-0ba83cc13aa2' started!

Marvin

03/06/2025, 12:27 AM

You're encountering warnings related to Kubernetes configurations and Pydantic model versions. Here's a summary of the issues and potential resolutions: 1. KubernetesClusterConfig Warning: - This warning indicates a collision in the registration of

KubernetesClusterConfig

types between the Prefect core and the Prefect Kubernetes integration. This is a known issue, and it might not affect functionality but can clutter logs. - GitHub Issue on KubernetesClusterConfig Warning: This issue suggests that the warning arises when importing

prefect_kubernetes

. 2. Pydantic V1 and V2 Mixing: - Mixing Pydantic V1 and V2 models is not supported and can lead to validation issues. The warning suggests upgrading models to Pydantic V2. - GitHub Pull Request on Pydantic Validation: This PR addresses issues with Pydantic V1 and V2 model validation, providing insights into how Prefect is handling these changes. ### Recommendations: - For KubernetesClusterConfig: If the warning does not affect your workflow, you might choose to ignore it until a fix is implemented. Otherwise, consider contributing to or following the GitHub issue for updates. - For Pydantic Mixing: Ensure all your models are upgraded to Pydantic V2 if possible. Check your dependencies to ensure they are compatible with Pydantic V2. If you need further assistance or specific code examples, feel free to ask.

Abyaya Lamsal

03/06/2025, 12:59 AM

@Marvin why does it error out after flow completes successfully

Copy code

│ 00:56:19.115 | DEBUG   | prefect.utilities.services.critical_service_loop - Run of functools.partial(<bound method Runner._check_for_cancelled_flow_runs of Runner(name='runner-6361b379-bcd0-466b-815b-795db51c3d31')>, should_stop=<function Ru │
│ Traceback (most recent call last):                                                                                                                                                                                                                │
│   File "/usr/local/lib/python3.10/site-packages/prefect/utilities/services.py", line 61, in critical_service_loop                                                                                                                                 │
│     await workload()                                                                                                                                                                                                                              │
│   File "/usr/local/lib/python3.10/site-packages/prefect/runner/runner.py", line 740, in _check_for_cancelled_flow_runs                                                                                                                            │
│     named_cancelling_flow_runs = await self._client.read_flow_runs(                                                                                                                                                                               │
│   File "/usr/local/lib/python3.10/site-packages/prefect/client/orchestration.py", line 2145, in read_flow_runs                                                                                                                                    │
│     response = await <http://self._client.post|self._client.post>("/flow_runs/filter", json=body)                                                                                                                                                                            │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1861, in post                                                                                                                                                             │
│     return await self.request(                                                                                                                                                                                                                    │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1542, in request                                                                                                                                                          │
│     return await self.send(request, auth=auth, follow_redirects=follow_redirects)                                                                                                                                                                 │
│   File "/usr/local/lib/python3.10/site-packages/prefect/client/base.py", line 327, in send                                                                                                                                                        │
│     response = await self._send_with_retry(                                                                                                                                                                                                       │
│   File "/usr/local/lib/python3.10/site-packages/prefect/client/base.py", line 251, in _send_with_retry                                                                                                                                            │
│     response = await send(request, *send_args, **send_kwargs)                                                                                                                                                                                     │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1631, in send                                                                                                                                                             │
│     response = await self._send_handling_auth(                                                                                                                                                                                                    │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1659, in _send_handling_auth                                                                                                                                              │
│     response = await self._send_handling_redirects(                                                                                                                                                                                               │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1696, in _send_handling_redirects                                                                                                                                         │
│     response = await self._send_single_request(request)                                                                                                                                                                                           │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1732, in _send_single_request                                                                                                                                             │
│     response = await transport.handle_async_request(request)                                                                                                                                                                                      │
│   File "/usr/local/lib/python3.10/site-packages/httpx/_transports/default.py", line 394, in handle_async_request                                                                                                                                  │
│     resp = await self._pool.handle_async_request(req)                                                                                                                                                                                             │
│   File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection_pool.py", line 256, in handle_async_request                                                                                                                            │
│     raise exc from None                                                                                                                                                                                                                           │
│   File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection_pool.py", line 236, in handle_async_request                                                                                                                            │
│     response = await connection.handle_async_request(                                                                                                                                                                                             │
│   File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection.py", line 101, in handle_async_request                                                                                                                                 │
│     raise exc                                                                                                                                                                                                                                     │
│   File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection.py", line 76, in handle_async_request                                                                                                                                  │
│     async with self._request_lock:                                                                                                                                                                                                                │
│   File "/usr/local/lib/python3.10/site-packages/httpcore/_synchronization.py", line 77, in __aenter__                                                                                                                                             │
│     await self._anyio_lock.acquire()                                                                                                                                                                                                              │
│   File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 1735, in acquire                                                                                                                                               │
│     await AsyncIOBackend.checkpoint_if_cancelled()                                                                                                                                                                                                │
│   File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2279, in checkpoint_if_cancelled                                                                                                                               │
│     await sleep(0)                                                                                                                                                                                                                                │
│   File "/usr/local/lib/python3.10/asyncio/tasks.py", line 596, in sleep                                                                                                                                                                           │
│     await __sleep0()                                                                                                                                                                                                                              │
│   File "/usr/local/lib/python3.10/asyncio/tasks.py", line 590, in __sleep0                                                                                                                                                                        │
│     yield                                                                                                                                                                                                                                         │
│ asyncio.exceptions.CancelledError: Cancelled by cancel scope 7f0e4e3d1180                                                                                                                                                                         │
│ 00:56:19.118 | DEBUG   | prefect.runner - Stopping runner...

Marvin

03/06/2025, 12:59 AM

Your message was too long by 679 tokens...

Abyaya Lamsal

03/06/2025, 1:00 AM

@Marvin why do i get this error after a flow completes? I am trying to migrate to prefect

v2.20.16

Copy code

asyncio.exceptions.CancelledError: Cancelled by cancel scope 7f0e4e3d1180

Marvin

03/06/2025, 1:00 AM

The error you're encountering,

asyncio.exceptions.CancelledError: Cancelled by cancel scope

, typically arises when an asyncio task is cancelled. In the context of Prefect, this can occur if the flow or task is being cancelled, possibly due to a timeout or an explicit cancellation request. ### Possible Causes and Solutions: 1. Flow Cancellation: - The flow might be getting cancelled due to a timeout or an explicit cancellation request. Ensure that your flow's timeout settings are configured correctly and that no other system is sending a cancellation signal. 2. Known Issues: - There is a GitHub issue where users reported similar errors after migrating to Prefect Workers. The error might be related to how Prefect handles cancellation checks in the background. - Another related issue is about Docker containers not closing properly, leading to unexpected cancellations. See this issue for more details. 3. Enhanced Cancellation: - Prefect offers an experimental feature for enhanced cancellation. You can enable it by setting the environment variable:

Copy code

bash
     prefect config set PREFECT_EXPERIMENTAL_ENABLE_ENHANCED_CANCELLATION=True

- This might help in handling cancellations more gracefully. 4. Debugging: - Review the flow logs for any explicit cancellation messages or errors that might have triggered the cancellation. - Check for any network or infrastructure issues that might be causing the flow to be cancelled unexpectedly. If these suggestions do not resolve the issue, consider reaching out to the Prefect community or filing a detailed issue on their GitHub repository.

Abyaya Lamsal

03/07/2025, 12:08 AM

@Marvin I am getting this error while running the flow

Copy code

Flow could not be retrieved from deployment.
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/site-packages/prefect/deployments/steps/core.py", line 154, in run_steps
    step_output = await run_step(step, upstream_outputs)
  File "/usr/local/lib/python3.10/site-packages/prefect/deployments/steps/core.py", line 125, in run_step
    result = await from_async.call_soon_in_new_thread(
  File "/usr/local/lib/python3.10/site-packages/prefect/_internal/concurrency/calls.py", line 293, in aresult
    return await asyncio.wrap_future(self.future)
  File "/usr/local/lib/python3.10/site-packages/prefect/_internal/concurrency/calls.py", line 318, in _run_sync
    result = self.fn(*self.args, **self.kwargs)
  File "/usr/local/lib/python3.10/site-packages/prefect_aws/deployments/steps.py", line 181, in pull_from_s3
    session = boto3.Session(**credentials)
TypeError: Session.__init__() got an unexpected keyword argument 'bucket_path'

Marvin

03/07/2025, 12:09 AM

The error you're encountering,

TypeError: Session.__init__() got an unexpected keyword argument 'bucket_path'

, is due to an incorrect argument being passed to the

boto3.Session

initialization. Here's what you need to know: 1. Cause: The

boto3.Session

class does not accept a

bucket_path

argument. This suggests a misconfiguration or an error in the code where the AWS credentials or configuration are being set up. 2. Solution: - Check Configuration: Ensure that the AWS credentials and configuration are correctly set up in your code. The

boto3.Session

should be initialized with valid arguments like

aws_access_key_id

aws_secret_access_key

region_name

, etc., but not

bucket_path

. - Code Review: Inspect the

pull_from_s3

function in your Prefect AWS integration to ensure it is correctly using

boto3

for session creation. Remove or correct the

bucket_path

argument. 3. Documentation: - Review the Prefect AWS S3 integration documentation for guidance on setting up and using S3 with Prefect. If you need further assistance or a specific code example, feel free to ask.

Abyaya Lamsal

03/07/2025, 12:11 AM

@Marvin these are the pull steps defined in prefect.yaml file

Copy code

pull:
- prefect_aws.deployments.steps.pull_from_s3:
    bucket: sample-bucket
    credentials: '{{ prefect.blocks.s3.aws_creds }}'
    folder: sample
    requires: prefect-aws

Marvin

03/07/2025, 12:11 AM

The error you're encountering is related to the incorrect configuration of the

pull_from_s3

step in your

prefect.yaml

file. Here's what you need to know: ### Key Points: 1. Deprecation Notice: The

pull_project_from_s3

and

push_project_to_s3

methods are deprecated. Ensure you are using the correct

pull_from_s3

method as specified in the Prefect AWS integration. 2. Configuration of
pull_from_s3
: - The

credentials

key should contain valid AWS credentials. It seems that the

bucket_path

is incorrectly being passed as part of the credentials. - Ensure that the credentials block reference (

{{ prefect.blocks.s3.aws_creds }}

) is correctly set up to provide AWS credentials without including any invalid keys like

bucket_path

. 3. Example Configuration: - Ensure your

prefect.yaml

is configured correctly. Here's an example configuration for pulling from S3:

Copy code

yaml
     pull:
     - prefect_aws.deployments.steps.pull_from_s3:
         bucket: sample-bucket
         credentials: '{{ prefect.blocks.s3.aws_creds }}'
         folder: sample
         requires: prefect-aws

4. Documentation: - Review the Prefect AWS deployments steps documentation for more details on setting up the pull steps. ### Recommendations: - Double-check the

credentials

block in Prefect to ensure it is set up correctly without any erroneous keys. - If the issue persists, consider reviewing the Prefect AWS integration code or reaching out to the Prefect community for further assistance.

Abyaya Lamsal

03/07/2025, 12:18 AM

@Marvin The prefect block itself has a

Bucket Path

field

Marvin

03/07/2025, 12:18 AM

The

Bucket Path

field in the Prefect block configuration is part of the S3 block setup. Here's how it fits into the broader configuration: ### Key Points: 1. Bucket Path Field: - The

Bucket Path

field is part of the S3 block configuration and is used to specify a default path within the bucket where objects are stored or retrieved from. - This field is not directly used in the

boto3.Session

initialization, which is why passing it there causes an error. 2. Correct Block Configuration: - When setting up your S3 block in Prefect, ensure that the

Bucket Path

is configured within the block itself, not passed as a credential to

boto3.Session

. - You can configure the

Bucket Path

when creating or updating the S3 block in Prefect, as shown in this example:

Copy code

python
     from prefect_aws.s3 import S3Bucket

     # Load an existing S3 block
     my_s3_bucket_block = S3Bucket.load("my-s3-bucket")

     # Set the bucket path
     my_s3_bucket_block.bucket_path = "my-default-bucket-path"

     # Save the updated block
     my_s3_bucket_block.save("my-s3-bucket", overwrite=True)

3. Documentation: - Review the Prefect Blocks Documentation for more details on setting up and managing blocks. ### Recommendations: - Ensure that your Prefect block for S3 is correctly set up with the

Bucket Path

field within the block itself. - Avoid passing the

Bucket Path

as part of the credentials to AWS sessions, as this is not supported by

boto3

. - If you continue to encounter issues, verify that your Prefect block configurations align with the expected setup in the Prefect documentation.

Abyaya Lamsal

03/12/2025, 12:16 AM

@Marvin can you omit "schedule" keyword from prefect yaml file?

Marvin

03/12/2025, 12:16 AM

Yes, you can omit the "schedule" keyword from a Prefect YAML file if you do not wish to define any scheduling for your deployment. The "schedule" section is optional and only needed if you want to automate the execution of runs at specific intervals or times. For more details on how scheduling works in Prefect, you can refer to their scheduling documentation.

24 Views

Open in Slack

Previous Next