<@ULVA73B9P> Where's a list of all the packages I ...
# ask-marvin
m
@Marvin Where's a list of all the packages I can pass to
PREFECT_LOGGING_EXTRA_LOGGERS
?
m
To include logs from other libraries in Prefect, you can use the
PREFECT_LOGGING_EXTRA_LOGGERS
setting. Specify one or more Python library names as a comma-separated list. For example, if you want Prefect to capture logging statements from
dask
and
scipy
, you would configure it as follows:
Copy code
PREFECT_LOGGING_EXTRA_LOGGERS=dask,scipy
This setting can be configured as an environment variable or in a Prefect profile. For more details on configuring logging, you can check out the Prefect documentation: - Prefect 2.x: https://docs-2.prefect.io/latest/guides/logs/ - Prefect 3.x: https://docs-3.prefect.io/3.0/develop/logging
m
@Marvin But where's a list of the packages I can specify?
m
There isn't an exhaustive list of packages you can specify for
PREFECT_LOGGING_EXTRA_LOGGERS
. You can include any Python library that uses the standard logging module. Here are a few commonly used libraries that you might consider: -
dask
-
scipy
-
pandas
-
numpy
-
requests
-
boto3
-
sqlalchemy
These libraries typically have their own logging that can provide valuable insights when troubleshooting or monitoring. For documentation, see: - Prefect 2.x: https://docs-2.prefect.io/latest/guides/logs/ - Prefect 3.x: https://docs-3.prefect.io/3.0/develop/logging You can specify them by setting the environment variable or a profile configuration like this:
Copy code
PREFECT_LOGGING_EXTRA_LOGGERS=dask,scipy,pandas,numpy,requests,boto3,sqlalchemy
If you want to find more loggers, you can refer to the respective libraries' documentation and their logging configurations.
m
@Marvin I'd want to know how to specify them. Like, is Tensorflow
tensorflow
or
tf
or something else?
m
For TensorFlow, you would typically use its root logger name, which is
tensorflow
. Here's how you can specify TensorFlow along with other libraries in the
PREFECT_LOGGING_EXTRA_LOGGERS
setting:
Copy code
PREFECT_LOGGING_EXTRA_LOGGERS=tensorflow,dask,scipy,pandas,numpy,requests,boto3,sqlalchemy
In general, the logger names correspond to the top-level module names of the libraries. If you're unsure, you can usually find the logger name by checking the library's documentation or source code, generally looking for how they configure their logging. For more details on logging configuration in Prefect, visit the related documentation pages: - Prefect 2.x: https://docs-2.prefect.io/latest/guides/logs/ - Prefect 3.x: https://docs-3.prefect.io/3.0/develop/logging