This tutorial and the assets can be downloaded as part of the Wallaroo Tutorials repository.

Wallaroo SDK Tag Tutorial

The following tutorial demonstrates how to use Wallaroo Tags. Tags are applied to either model versions or pipelines. This allows organizations to track different versions of models, and search for what pipelines have been used for specific purposes such as testing versus production use.

The following will be demonstrated:

• List all tags in a Wallaroo instance.
• List all tags applied to a model.
• List all tags applied to a pipeline.
• Apply a tag to a model.
• Remove a tag from a model.
• Apply a tag to a pipeline.
• Remove a tag from a pipeline.
• Search for a model version by a tag.
• Search for a pipeline by a tag.

This demonstration provides the following through the Wallaroo Tutorials Github Repository:

• models/ccfraud.onnx: a sample model used as part of the Wallaroo 101 Tutorials.

Steps

The following steps are performed use to connect to a Wallaroo instance and demonstrate how to use tags with models and pipelines.

Load Libraries

The first step is to load the libraries used to connect and use a Wallaroo instance.

import wallaroo
from wallaroo.object import EntityNotFoundError
import pandas as pd

# used to display dataframe information without truncating
from IPython.display import display
pd.set_option('display.max_colwidth', None)

Connect to Wallaroo

The following command is used to connect to a Wallaroo instance from within a Wallaroo Jupyter Hub service. For more information on connecting to a Wallaroo instance, see the Wallaroo SDK Guides.

# Client connection from local Wallaroo instance

wl = wallaroo.Client()

# SSO login through keycloak

# wallarooPrefix = "YOUR PREFIX"
# wallarooSuffix = "YOUR SUFFIX"

# wl = wallaroo.Client(api_endpoint=f"https://{wallarooPrefix}.api.{wallarooSuffix}", 
#                     auth_endpoint=f"https://{wallarooPrefix}.keycloak.{wallarooSuffix}", 
#                     auth_type="sso")

Arrow Support

As of the 2023.1 release, Wallaroo provides support for dataframe and Arrow for inference inputs. This tutorial allows users to adjust their experience based on whether they have enabled Arrow support in their Wallaroo instance or not.

If Arrow support has been enabled, arrowEnabled=True. If disabled or you’re not sure, set it to arrowEnabled=False

The examples below will be shown in an arrow enabled environment.

import os
# Only set the below to make the OS environment ARROW_ENABLED to TRUE.  Otherwise, leave as is.
# os.environ["ARROW_ENABLED"]="True"

if "ARROW_ENABLED" not in os.environ or os.environ["ARROW_ENABLED"].casefold() == "False".casefold():
    arrowEnabled = False
else:
    arrowEnabled = True
print(arrowEnabled)

True

Set Variables

The following variables are used to create or connect to existing workspace and pipeline. The model name and model file are set as well. Adjust as required for your organization’s needs.

The methods get_workspace and get_pipeline are used to either create a new workspace and pipeline based on the variables below, or connect to an existing workspace and pipeline with the same name. Once complete, the workspace will be set as the current workspace where pipelines and models are used.

To allow this tutorial to be run multiple times or by multiple users in the same Wallaroo instance, a random 4 character prefix will be added to the workspace, pipeline, and model.

import string
import random

# make a random 4 character prefix
prefix= ''.join(random.choice(string.ascii_lowercase) for i in range(4))

workspace_name = f'{prefix}tagtestworkspace'
pipeline_name = f'{prefix}tagtestpipeline'
model_name = f'{prefix}tagtestmodel'
model_file_name = './models/ccfraud.onnx'

def get_workspace(name):
    workspace = None
    for ws in wl.list_workspaces():
        if ws.name() == name:
            workspace= ws
    if(workspace == None):
        workspace = wl.create_workspace(name)
    return workspace

def get_pipeline(name):
    try:
        pipeline = wl.pipelines_by_name(pipeline_name)[0]
    except EntityNotFoundError:
        pipeline = wl.build_pipeline(pipeline_name)
    return pipeline

workspace = get_workspace(workspace_name)

wl.set_current_workspace(workspace)

{'name': 'efxvtagtestworkspace', 'id': 15, 'archived': False, 'created_by': '435da905-31e2-4e74-b423-45c38edb5889', 'created_at': '2023-02-27T18:02:16.272068+00:00', 'models': [], 'pipelines': []}

Upload Model and Create Pipeline

The tagtest_model and tagtest_pipeline will be created (or connected if already existing) based on the variables set earlier.

tagtest_model = wl.upload_model(model_name, model_file_name).configure()
tagtest_model

{'name': 'efxvtagtestmodel', 'version': '254a2888-0c8b-4172-97c3-c3547bbe6644', 'file_name': 'ccfraud.onnx', 'image_path': None, 'last_update_time': datetime.datetime(2023, 2, 27, 18, 2, 19, 155698, tzinfo=tzutc())}

tagtest_pipeline = get_pipeline(pipeline_name)
tagtest_pipeline

List Pipeline and Model Tags

This tutorial assumes that no tags are currently existing, but that can be verified through the Wallaroo client list_pipelines and list_models commands. For this demonstration, it is recommended to use unique tags to verify each example.

wl.list_pipelines()

wl.list_models()

Create Tag

Tags are created with the Wallaroo client command create_tag(String tagname). This creates the tag and makes it available for use.

The tag will be saved to the variable currentTag to be used in the rest of these examples.

# Now we create our tag
currentTag = wl.create_tag("My Great Tag")

List Tags

Tags are listed with the Wallaroo client command list_tags(), which shows all tags and what models and pipelines they have been assigned to. Note that if a tag has not been assigned, it will not be displayed.

# List all tags

wl.list_tags()

(no tags)

Assign Tag to a Model

Tags are assigned to a model through the Wallaroo Tag add_to_model(model_id) command, where model_id is the model’s numerical ID number. The tag is applied to the most current version of the model.

For this example, the currentTag will be applied to the tagtest_model. All tags will then be listed to show it has been assigned to this model.

# add tag to model

currentTag.add_to_model(tagtest_model.id())

{'model_id': 10, 'tag_id': 1}

# list all tags to verify

wl.list_tags()

Search Models by Tag

Model versions can be searched via tags using the Wallaroo Client method search_models(search_term), where search_term is a string value. All models versions containing the tag will be displayed. In this example, we will be using the text from our tag to list all models that have the text from currentTag in them.

# Search models by tag

wl.search_models('My Great Tag')

Remove Tag from Model

Tags are removed from models using the Wallaroo Tag remove_from_model(model_id) command.

In this example, the currentTag will be removed from tagtest_model. A list of all tags will be shown with the list_tags command, followed by searching the models for the tag to verify it has been removed.

### remove tag from model

currentTag.remove_from_model(tagtest_model.id())

{'model_id': 10, 'tag_id': 1}

# list all tags to verify it has been removed from `tagtest_model`.

wl.list_tags()

(no tags)

# search models for currentTag to verify it has been removed from `tagtest_model`.

wl.search_models('My Great Tag')

(no model versions)

Add Tag to Pipeline

Tags are added to a pipeline through the Wallaroo Tag add_to_pipeline(pipeline_id) method, where pipeline_id is the pipeline’s integer id.

For this example, we will add currentTag to testtest_pipeline, then verify it has been added through the list_tags command and list_pipelines command.

# add this tag to the pipeline
currentTag.add_to_pipeline(tagtest_pipeline.id())

{'pipeline_pk_id': 20, 'tag_pk_id': 1}

# list tags to verify it was added to tagtest_pipeline

wl.list_tags()

# get all of the pipelines to show the tag was added to tagtest-pipeline

wl.list_pipelines()

Search Pipelines by Tag

Pipelines can be searched through the Wallaroo Client search_pipelines(search_term) method, where search_term is a string value for tags assigned to the pipelines.

In this example, the text “My Great Tag” that corresponds to currentTag will be searched for and displayed.

wl.search_pipelines('My Great Tag')

Remove Tag from Pipeline

Tags are removed from a pipeline with the Wallaroo Tag remove_from_pipeline(pipeline_id) command, where pipeline_id is the integer value of the pipeline’s id.

For this example, currentTag will be removed from tagtest_pipeline. This will be verified through the list_tags and search_pipelines command.

## remove from pipeline
currentTag.remove_from_pipeline(tagtest_pipeline.id())

{'pipeline_pk_id': 20, 'tag_pk_id': 1}

wl.list_tags()

(no tags)

## Verify it was removed
wl.search_pipelines('My Great Tag')

(no pipelines)