Model Deploy

Organizations manage model deployments through pipelines.

Pipelines represent how data is submitted to your uploaded Machine Learning (ML) models. Pipelines allow you to:

• Submit information through an uploaded file or through the Pipeline’s Deployment URL.
• Have the Pipeline submit the information to one or more models in sequence.
• Once complete, output the result from the model(s).

How to Manage Pipelines via the Wallaroo Dashboard

The Wallaroo Dashboard provides users methods to create, deploy, and other pipeline operations through the Wallaroo Dashboard user interface.

How to Create a Pipeline Using the Wallaroo Dashboard

To create a pipeline:

1. From the Wallaroo Dashboard, set the current workspace from the top left dropdown list.

2. Select View Pipelines from the pipeline’s row.

3. From the upper right hand corner, select Create Pipeline.

   

4. Enter the following:

   1. Pipeline Name: The name of the new pipeline. Pipeline names should be unique across the Wallaroo instance.
   2. Add Pipeline Step: Select the models to be used as the pipeline steps.

   

   When finished, select Next.

5. Review the name of the pipeline and the steps. If any adjustments need to be made, select either Back to rename the pipeline or Add Step(s) to change the pipeline’s steps.

   

6. When finished, select Build to create the pipeline in this workspace. The pipeline will be built and be ready for deployment within a minute.

   

How to Deploy and Undeploy a Pipeline using the Wallaroo Dashboard

Deployed pipelines create new namespaces in the Kubernetes environment where the Wallaroo instance is deployed, and allocate resources from the Kubernetes environment to run the pipeline and its steps.

To deploy a pipeline:

1. From the Wallaroo Dashboard, set the current workspace from the top left dropdown list.

2. Select View Pipelines from the pipeline’s row.

3. Select the pipeline to deploy.

4. From the right navigation panel, select Deploy.

   

5. A popup module will request verification to deploy the pipeline. Select Deploy again to deploy the pipeline.

Undeploying a pipeline returns resources back to the Kubernetes environment and removes the namespaces created when the pipeline was deployed.

To undeploy a pipeline:

1. From the Wallaroo Dashboard, set the current workspace from the top left dropdown list.

2. Select View Pipelines from the pipeline’s row.

3. Select the pipeline to deploy.

4. From the right navigation panel, select Undeploy.

   

5. A popup module will request verification to undeploy the pipeline. Select Undeploy again to undeploy the pipeline.

How to View a Pipeline Details and Metrics using the Wallaroo Dashboard

To view a pipeline’s details:

1. From the Wallaroo Dashboard, set the current workspace from the top left dropdown list.
2. Select View Pipelines from the pipeline’s row.
3. To view details on the pipeline, select the name of the pipeline.
4. A list of the pipeline’s details will be displayed.

To view a pipeline’s metrics:

1. From the Wallaroo Dashboard, set the current workspace from the top left dropdown list.
2. Select View Pipelines from the pipeline’s row.
3. To view details on the pipeline, select the name of the pipeline.
4. A list of the pipeline’s details will be displayed.
5. Select Metrics to view the following information. From here you can select the time period to display metrics from through the drop down to display the following:
   1. Requests per second
   2. Cluster inference rate
   3. Inference latency
6. The Audit Log and Anomaly Log are available to view further details of the pipeline’s activities.

Viewing Pipeline Details through the Wallaroo Dashboard

The following is available from the Pipeline Details page:

• The name of the pipeline.
• The pipeline ID: This is in UUID format.
• Pipeline steps: The steps and the models in each pipeline step.
• Version History: how the pipeline has been updated over time.

How to Manage Pipelines via the Wallaroo SDK

Pipelines are the method of taking submitting data and processing that data through the models. Each pipeline can have one or more steps that submit the data from the previous step to the next one. Information can be submitted to a pipeline as a file, or through the pipeline’s URL.

A pipeline’s metrics can be viewed through the Wallaroo Dashboard Pipeline Details and Metrics page.

Pipeline Naming Requirements

Pipeline names map onto Kubernetes objects, and must be DNS compliant. Pipeline names must be ASCII alpha-numeric characters or dash (-) only. . and _ are not allowed.

Create a Pipeline

New pipelines are created in the current workspace.

To create a new pipeline, use the Wallaroo Client build_pipeline("{Pipeline Name}") command.

The following example creates a new pipeline imdb-pipeline through a Wallaroo Client connection wl:

imdb_pipeline = wl.build_pipeline("imdb-pipeline")

imdb_pipeline.status()
{'status': 'Pipeline imdb-pipeline is not deployed'}

Get Pipeline

Pipelines are retrieved via the method wallaroo.client.get_pipeline. This retrieves the most recent version of the specified pipeline in the current workspace that that matches the requested parameters.

For more details on workspaces, see How to Set the Current Workspace.

Get Pipeline Parameters

wallaroo.client.get_pipeline takes the following parameters.

Get Pipeline Returns

wallaroo.client.get_pipeline returns wallaroo.pipeline_version.PipelineVersion for the specified pipeline and version in the current workspace.

If the pipeline or pipeline version do not match the requested parameters, an error is returned.

Get Pipeline Examples

Get Pipeline by Name Example

The following demonstrates retrieving the most recent pipeline version of the requested pipeline in the current workspace.

pipeline_name="helper-demo-pipeline-1"

wl.get_pipeline(name=pipeline_name)

Get Pipeline By Name Error Example

The following demonstrates requesting a pipeline when no pipeline matching the name exists in the current workspace.

wl.get_pipeline(name="no-such-pipeline")

---------------------------------------------------------------------------

Exception                                 Traceback (most recent call last)

/tmp/ipykernel_208/1835144440.py in <module>
----> 1 wl.get_pipeline(name="no-such-pipeline")


~/.local/lib/python3.9/site-packages/wallaroo/client.py in get_pipeline(self, name, version)
   1357         )
   1358         if pipeline is None:
-> 1359             raise Exception(f"Pipeline {name} not found in this workspace.")
   1360         if version is not None:
   1361             pipeline_version = next(

Exception: Pipeline no-such-pipeline not found in this workspace.

Get Specific Pipeline Version Example

pipeline_name="helper-demo-pipeline-1"

wl.get_pipeline(name=pipeline_name, version="1647a8bd-4ed8-45bc-a2b8-b14ace57e490")

Get Specific Pipeline Version Error Example

The following demonstrates requesting a pipeline version when no pipeline version matching the requested version parameter exists in the current workspace and pipeline.

pipeline_name="helper-demo-pipeline-1"

wl.get_pipeline(name=pipeline_name, version="no-such-version")

---------------------------------------------------------------------------

Exception                                 Traceback (most recent call last)

/tmp/ipykernel_208/2171664880.py in <module>
----> 1 wl.get_pipeline(name=pipeline_name, version="no-such-version")


~/.local/lib/python3.9/site-packages/wallaroo/client.py in get_pipeline(self, name, version)
   1366                 return pipeline
   1367             else:
-> 1368                 raise Exception(
   1369                     f"Pipeline version {version} not found in this workspace."
   1370                 )

Exception: Pipeline version no-such-version not found in this workspace.

List All Pipelines

The Wallaroo Client method list_pipelines() lists all pipelines in a Wallaroo Instance.

List All Pipelines Parameters

N/A

List All Pipelines Returns

The following fields are returned from the list_pipeline method.

List All Pipelines Example

wl.list_pipelines()

Pipeline Steps

Once a pipeline has been created, or during its creation process, a pipeline step can be added. The pipeline step refers to the model that will perform an inference off of the data submitted to it. Each time a step is added, it is added to the pipeline’s models array.

Pipeline steps are not saved until the pipeline is deployed. Until then, pipeline steps are stored in local memory as a potential pipeline configuration until the pipeline is deployed.

Add a Step to a Pipeline

A pipeline step is added through the pipeline add_model_step({Model}) command.

In the following example, two models uploaded to the workspace are added as pipeline step:

imdb_pipeline.add_model_step(embedder)
imdb_pipeline.add_model_step(smodel)

imdb_pipeline.status()

{'name': 'imdb-pipeline', 'create_time': datetime.datetime(2022, 3, 30, 21, 21, 31, 127756, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'embedder-o', 'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d', 'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4'}]}}, {'ModelInference': {'models': [{'name': 'smodel-o', 'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19', 'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650'}]}}]"}

Replace a Pipeline Step

The model specified in a pipeline step can be replaced with the pipeline method replace_with_model_step(index, model).

The following parameters are used for replacing a pipeline step:

In the following example, a deployed pipeline will have the initial model step replaced with a new one. A status of the pipeline will be displayed after deployment and after the pipeline swap to show the model has been replaced from ccfraudoriginal to ccfraudreplacement, each with their own versions.

pipeline.deploy()

pipeline.status()

{'status': 'Running',
 'details': [],
 'engines': [{'ip': '10.244.2.145',
   'name': 'engine-75bfd7dc9d-7p9qk',
   'status': 'Running',
   'reason': None,
   'details': [],
   'pipeline_statuses': {'pipelines': [{'id': 'hotswappipeline',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'ccfraudoriginal',
      'version': '3a03dc94-716e-46bb-84c8-91bc99ceb2c3',
      'sha': 'bc85ce596945f876256f41515c7501c399fd97ebcb9ab3dd41bf03f8937b4507',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.244.2.144',
   'name': 'engine-lb-55dcdff64c-vf74s',
   'status': 'Running',
   'reason': None,
   'details': []}],
 'sidekicks': []}

pipeline.replace_with_model_step(0, replacement_model).deploy()

pipeline.status()

{'status': 'Running',
 'details': [],
 'engines': [{'ip': '10.244.2.153',
   'name': 'engine-96486c95d-zfchr',
   'status': 'Running',
   'reason': None,
   'details': [],
   'pipeline_statuses': {'pipelines': [{'id': 'hotswappipeline',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'ccfraudreplacement',
      'version': '714efd19-5c83-42a8-aece-24b4ba530925',
      'sha': 'bc85ce596945f876256f41515c7501c399fd97ebcb9ab3dd41bf03f8937b4507',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.244.2.154',
   'name': 'engine-lb-55dcdff64c-9np9k',
   'status': 'Running',
   'reason': None,
   'details': []}],
 'sidekicks': []}

Pre and Post Processing Steps

A Pipeline Step can be more than models - they can also be pre processing and post processing steps. For example, this preprocessing step uses the following code:

import numpy
import pandas

import json

# add interaction terms for the model
def actual_preprocess(pdata):
    pd = pdata.copy()
    # convert boolean cust_known to 0/1
    pd.cust_known = numpy.where(pd.cust_known, 1, 0)
    # interact UnitPrice and cust_known
    pd['UnitPriceXcust_known'] = pd.UnitPrice * pd.cust_known
    return pd.loc[:, ['UnitPrice', 'cust_known', 'UnitPriceXcust_known']]

# If the data is a json string, call this wrapper instead
# Expected input:
# a dictionary with fields 'colnames', 'data'

# test that the code works here
def wallaroo_json(data):
    obj = json.loads(data)
    pdata = pandas.DataFrame(obj['query'],
                             columns=obj['colnames'])
    pprocessed = actual_preprocess(pdata)
    
   # return a dictionary, with the fields the model expect
    return {
       'tensor_fields': ['model_input'],
       'model_input': pprocessed.to_numpy().tolist()
    }

It is added as a Python module by uploading it as a model:

# load the preprocess module
module_pre = wl.upload_model("preprocess", "./preprocess.py").configure('python')

And then added to the pipeline as a step:

# now make a pipeline
demandcurve_pipeline = (wl.build_pipeline("demand-curve-pipeline")
                        .add_model_step(module_pre)
                        .add_model_step(demand_curve_model)
                        .add_model_step(module_post))

Remove a Pipeline Step

To remove a step from the pipeline, use the Pipeline remove_step(index) command, where the index is the array index for the pipeline’s steps.

In the following example the pipeline imdb_pipeline will have the step with the model smodel-o removed.

imdb_pipeline.status

<bound method Pipeline.status of {'name': 'imdb-pipeline', 'create_time': datetime.datetime(2022, 3, 30, 21, 21, 31, 127756, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'embedder-o', 'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d', 'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4'}]}}, {'ModelInference': {'models': [{'name': 'smodel-o', 'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19', 'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650'}]}}]"}>

imdb_pipeline.remove_step(1)
{'name': 'imdb-pipeline', 'create_time': datetime.datetime(2022, 3, 30, 21, 21, 31, 127756, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'embedder-o', 'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d', 'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4'}]}}]"}

Clear All Pipeline Steps

The Pipeline clear() method removes all pipeline steps from a pipeline. Note that pipeline steps are not saved until the pipeline is deployed.

Pipeline Versions

Each time the pipeline steps are updated and the pipeline is either deployed or a pipeline version is manually created, a new pipeline version is created. This each Pipeline version includes the following:

Create Pipeline Versions

Pipeline versions are saved automatically when the method wallaroo.pipeline.deploy(deployment_configuration) is called. Pipeline versions are stored manually with the wallaroo.pipeline.create_versions() method, which stores the current pipeline steps and other details stored in the local SDK session into the Wallaroo pipeline database.

The following example demonstrates setting a model as a pipeline step, then saving the pipeline configuration in the local SDK session to Wallaroo as a new pipeline version.

display("Current pipeline.")
display(pipeline) # display the current pipeline
pipeline.clear() #clear the current steps
pipeline.add_model_step(houseprice_rf_model_version) #set a different model as a pipeline step
new_pipeline_version = pipeline.create_version()
display("New pipeline version.")
display(new_pipeline_version)

Current pipeline.

New pipeline version.

List Pipeline Versions

Pipeline versions are retrieved with the method wallaroo.pipeline.versions() and returns a List of the versions of the pipelines listed in descending creation order, with the most recent version stored in position 0.

The following example demonstrates retrieving the list of pipeline version, then storing a specific version to a variable and displaying its version id and other details.

for pipeline_version in pipeline.versions():
    display(pipeline_version)

pipeline_version_01 = pipeline.versions()[7]

display(pipeline_version_01.name())
display(pipeline_version_01)

…

‘92f2b4f3-494b-4d69-895f-9e767ac1869d’

Deploy a Pipeline

When a pipeline step is added or removed, the pipeline must be deployed through the pipeline deploy(deployment_config). This allocates resources to the pipeline from the Kubernetes environment and make it available to submit information to perform inferences. For full details on pipeline deployment configurations, see Wallaroo SDK Essentials Guide: Pipeline Deployment Configuration.

Deployment configurations default to the following^*.

*: For Kubernetes limits and requests.
**: Resources are always allocated for the Wallaroo Native Runtime engine even if there are no Wallaroo Native Runtimes included in the deployment, so it is recommended to decrease these resources when pipelines use Containerized Runtimes.
***: Resources for Wallaroo Containerized Runtimes only apply with a Wallaroo Containerized Runtime is part of the deployment.

Pipelines do not need to be undeployed to deploy new pipeline versions or pipeline deployment configurations. For example, the following pipeline is deployed, new pipeline steps are set, and the pipeline deploy command is issues again. This creates a new version of the pipeline and updates the deployed pipeline with the new configuration.

# clear all steps
pipeline.clear()
# set modelA as the step
pipeline.add_model_step(modelA)
# deploy the pipeline - the version is saved and the resources allocated to the pipeline
pipeline.deploy()
# clear the steps - this configuration is only stored in the local SDK session until the deploy or create_version command is given
pipeline.clear()
# set modelB as the step
pipeline.add_model_step(modelB)
# deploy the pipeline - the pipeline configuration is saved and the pipeline deployment updated without significant downtime
pipeline.deploy()

Model Deployment Architecture Inheritance

Deployment configurations inherit the model’s architecture setting. This is set during model upload by specifying the arch parameter. By default, models uploaded to Wallaroo default to the x86 architecture.

The following model operations inherit the model’s architecture setting.

• Model Deployment: Model deployment and Model Deployment Deployment Configuration inherit the the model’s architecture. No specification of the architecture is required for model deployment.
• Pipeline Publishing: The Wallaroo engine set when a pipeline is containerized and published to an Open Container Initiative (OCI) Registry inherits the model’s architecture setting.

The following example shows uploading a model set with the architecture set to ARM, and how the deployment inherits that architecture without additional deployment configuration changes. For this example, an ONNX model is uploaded.

import wallaroo

housing_model_control_arm = (wl.upload_model(model_name_arm, 
                                        model_file_name, 
                                        framework=Framework.ONNX,
                                        arch=wallaroo.engine_config.Architecture.ARM)
                                        .configure(tensor_fields=["tensor"])
                        )

display(housing_model_control_arm)

Note that the deployment configuration settings, no architecture is specified. When pipeline_arm is displayed, we see the arch setting inherited the model’s arch setting.

pipeline_arm = wl.build_pipeline(arm_pipeline_name)

# set the model step with the ARM targeted model
pipeline_arm.add_model_step(housing_model_control_arm)

#minimum deployment config for this model
deploy_config = wallaroo.DeploymentConfigBuilder().replica_count(1).cpus(1).memory("1Gi").build()

pipeline_arm.deploy(deployment_config = deploy_config)

    Waiting for deployment - this will take up to 45s .......... ok

display(pipeline_arm)

pipeline_arm.status()

    {'status': 'Running',
     'details': [],
     'engines': [{'ip': '10.124.0.45',
       'name': 'engine-5d94d89b5d-gbr9h',
       'status': 'Running',
       'reason': None,
       'details': [],
       'pipeline_statuses': {'pipelines': [{'id': 'architecture-demonstration-arm',
          'status': 'Running'}]},
       'model_statuses': {'models': [{'config': {'batch_config': None,
           'filter_threshold': None,
           'id': 76,
           'input_schema': None,
           'model_version_id': 43,
           'output_schema': None,
           'runtime': 'onnx',
           'sidekick_uri': None,
           'tensor_fields': ['tensor']},
          'model_version': {'conversion': {'arch': 'arm',
            'framework': 'onnx',
            'python_version': '3.8',
            'requirements': []},
           'file_info': {'file_name': 'rf_model.onnx',
            'sha': 'e22a0831aafd9917f3cc87a15ed267797f80e2afa12ad7d8810ca58f173b8cc6',
            'version': '163ff0a9-0f1a-4229-bbf2-a19e4385f10f'},
           'id': 43,
           'image_path': None,
           'name': 'house-price-estimator-arm',
           'status': 'ready',
           'task_id': None,
           'visibility': 'private',
           'workspace_id': 62},
          'status': 'Running'}]}}],
     'engine_lbs': [{'ip': '10.124.0.44',
       'name': 'engine-lb-d7cc8fc9c-4s9fc',
       'status': 'Running',
       'reason': None,
       'details': []}],
     'sidekicks': []}

Deploy Current Pipeline Version

By default, deploying a Wallaroo pipeline will deploy the most current version. For example:

sample_pipeline = wl.build_pipeline("test-pipeline")
sample_pipeline.add_model_step(model)
sample_pipeline.deploy()
sample_pipeline.status()

{'status': 'Running',
 'details': None,
 'engines': [{'ip': '10.12.1.65',
   'name': 'engine-778b65459-f9mt5',
   'status': 'Running',
   'reason': None,
   'pipeline_statuses': {'pipelines': [{'id': 'imdb-pipeline',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'embedder-o',
      'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d',
      'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4',
      'status': 'Running'},
     {'name': 'smodel-o',
      'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19',
      'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.12.1.66',
   'name': 'engine-lb-85846c64f8-ggg2t',
   'status': 'Running',
   'reason': None}]}

Deploy Previous Pipeline Version

Pipeline versions are deployed with the method wallaroo.pipeline_variant.deploy(deployment_name, model_configs, config: Optional[wallaroo.deployment_config.DeploymentConfig]). Note that the deployment_name and model_configs are required. The model_configs are retrieved with the wallaroo.pipeline_variant.model_configs() method.

The following demonstrates retrieving a previous version of a pipeline, deploying it, and retrieving the deployment status.

pipeline_version = pipeline.versions()[7]

display(pipeline_version.name())
display(pipeline_version)
pipeline_version.deploy("houseprice-estimator", pipeline_version.model_configs())
display(pipeline.status())

{'status': 'Running',
 'details': [],
 'engines': [{'ip': '10.244.3.211',
   'name': 'engine-578dc7cdcf-qkx5n',
   'status': 'Running',
   'reason': None,
   'details': [],
   'pipeline_statuses': {'pipelines': [{'id': 'houseprice-estimator',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'house-price-rf-model',
      'version': '616c2306-bf93-417b-9656-37bee6f14379',
      'sha': 'e22a0831aafd9917f3cc87a15ed267797f80e2afa12ad7d8810ca58f173b8cc6',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.244.4.243',
   'name': 'engine-lb-584f54c899-2rtvg',
   'status': 'Running',
   'reason': None,
   'details': []}],
 'sidekicks': []}

Pipeline Status

Once complete, the pipeline status() command will show 'status':'Running'.

Pipeline deployments can be modified to enable auto-scaling to allow pipelines to allocate more or fewer resources based on need by setting the pipeline’s This will then be applied to the deployment of the pipelineccfraudPipelineby specifying it'sdeployment_config` optional parameter. If this optional parameter is not passed, then the deployment will defer to default values. For more information, see Manage Pipeline Deployment Configuration.

In the following example, the pipeline imdb-pipeline that contains two steps will be deployed with default deployment configuration:

imdb_pipeline.status

<bound method Pipeline.status of {'name': 'imdb-pipeline', 'create_time': datetime.datetime(2022, 3, 30, 21, 21, 31, 127756, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'embedder-o', 'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d', 'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4'}]}}, {'ModelInference': {'models': [{'name': 'smodel-o', 'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19', 'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650'}]}}]"}>

imdb_pipeline.deploy()
Waiting for deployment - this will take up to 45s ...... ok

imdb_pipeline.status()

{'status': 'Running',
 'details': None,
 'engines': [{'ip': '10.12.1.65',
   'name': 'engine-778b65459-f9mt5',
   'status': 'Running',
   'reason': None,
   'pipeline_statuses': {'pipelines': [{'id': 'imdb-pipeline',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'embedder-o',
      'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d',
      'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4',
      'status': 'Running'},
     {'name': 'smodel-o',
      'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19',
      'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.12.1.66',
   'name': 'engine-lb-85846c64f8-ggg2t',
   'status': 'Running',
   'reason': None}]}

Manage Pipeline Deployment Configuration

For full details on pipeline deployment configurations, see Wallaroo SDK Essentials Guide: Pipeline Deployment Configuration.

Troubleshooting Pipeline Deployment

If you deploy more pipelines than your environment can handle, or if you deploy more pipelines than your license allows, you may see an error like the following:

LimitError: You have reached a license limit in your Wallaroo instance. In order to add additional resources, you can remove some of your existing resources. If you have any questions contact us at community@wallaroo.ai: MAX_PIPELINES_LIMIT_EXCEEDED

Undeploy any unnecessary pipelines either through the SDK or through the Wallaroo Pipeline Dashboard, then attempt to redeploy the pipeline in question again.

Undeploy a Pipeline

When a pipeline is not currently needed, it can be undeployed and its resources turned back to the Kubernetes environment. To undeploy a pipeline, use the pipeline undeploy() command.

In this example, the aloha_pipeline will be undeployed:

aloha_pipeline.undeploy()

{'name': 'aloha-test-demo', 'create_time': datetime.datetime(2022, 3, 29, 20, 34, 3, 960957, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'aloha-2', 'version': 'a8e8abdc-c22f-416c-a13c-5fe162357430', 'sha': 'fd998cd5e4964bbbb4f8d29d245a8ac67df81b62be767afbceb96a03d1a01520'}]}}]"}

Get Pipeline Status

The pipeline status() command shows the current status, models, and other information on a pipeline.

The following example shows the pipeline imdb_pipeline status before and after it is deployed:

imdb_pipeline.status

<bound method Pipeline.status of {'name': 'imdb-pipeline', 'create_time': datetime.datetime(2022, 3, 30, 21, 21, 31, 127756, tzinfo=tzutc()), 'definition': "[{'ModelInference': {'models': [{'name': 'embedder-o', 'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d', 'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4'}]}}, {'ModelInference': {'models': [{'name': 'smodel-o', 'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19', 'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650'}]}}]"}>

imdb_pipeline.deploy()
Waiting for deployment - this will take up to 45s ...... ok

imdb_pipeline.status()

{'status': 'Running',
 'details': None,
 'engines': [{'ip': '10.12.1.65',
   'name': 'engine-778b65459-f9mt5',
   'status': 'Running',
   'reason': None,
   'pipeline_statuses': {'pipelines': [{'id': 'imdb-pipeline',
      'status': 'Running'}]},
   'model_statuses': {'models': [{'name': 'embedder-o',
      'version': '1c16d21d-fe4c-4081-98bc-65fefa465f7d',
      'sha': 'd083fd87fa84451904f71ab8b9adfa88580beb92ca77c046800f79780a20b7e4',
      'status': 'Running'},
     {'name': 'smodel-o',
      'version': '8d311ba3-c336-48d3-99cd-85d95baa6f19',
      'sha': '3473ea8700fbf1a1a8bfb112554a0dde8aab36758030dcde94a9357a83fd5650',
      'status': 'Running'}]}}],
 'engine_lbs': [{'ip': '10.12.1.66',
   'name': 'engine-lb-85846c64f8-ggg2t',
   'status': 'Running',
   'reason': None}]}

A/B Testing

A/B testing is a method that provides the ability to test competing ML models for performance, accuracy or other useful benchmarks. Different models are added to the same pipeline steps as follows:

• Control or Champion model: The model currently used for inferences.
• Challenger model(s): The model or set of models compared to the challenger model.

A/B testing splits a portion of the inference requests between the champion model and the one or more challengers through the add_random_split method. This method splits the inferences submitted to the model through a randomly weighted step.

Each model receives inputs that are approximately proportional to the weight it is assigned. For example, with two models having weights 1 and 1, each will receive roughly equal amounts of inference inputs. If the weights were changed to 1 and 2, the models would receive roughly 33% and 66% respectively instead.

When choosing the model to use, a random number between 0.0 and 1.0 is generated. The weighted inputs are mapped to that range, and the random input is then used to select the model to use. For example, for the two-models equal-weight case, a random key of 0.4 would route to the first model, 0.6 would route to the second.

Add Random Split

A random split step can be added to a pipeline through the add_random_split method.

The following parameters are used when adding a random split step to a pipeline:

Note that multiple challenger models with different weights can be added as the random split step.

add_random_split([(champion_weight, champion_model), (challenger_weight, challenger_model),  (challenger_weight2, challenger_model2),...], hash_key)

In this example, a pipeline will be built with a 2:1 weighted ratio between the champion and a single challenger model.

pipeline = (wl.build_pipeline("randomsplitpipeline-demo")
            .add_random_split([(2, control), (1, challenger)]))

The results for a series of single are displayed to show the random weighted split between the two models in action:

results = []
results.append(experiment_pipeline.infer_from_file("data/data-1.json"))
results.append(experiment_pipeline.infer_from_file("data/data-1.json"))
results.append(experiment_pipeline.infer_from_file("data/data-1.json"))
results.append(experiment_pipeline.infer_from_file("data/data-1.json"))
results.append(experiment_pipeline.infer_from_file("data/data-1.json"))

for result in results:
    print(result[0].model())
    print(result[0].data())

('aloha-control', 'ff81f634-8fb4-4a62-b873-93b02eb86ab4')
[array([[0.00151959]]), array([[0.98291481]]), array([[0.01209957]]), array([[4.75912966e-05]]), array([[2.02893716e-05]]), array([[0.00031977]]), array([[0.01102928]]), array([[0.99756402]]), array([[0.01034162]]), array([[0.00803896]]), array([[0.01615506]]), array([[0.00623623]]), array([[0.00099858]]), array([[1.79337805e-26]]), array([[1.38899512e-27]])]

('aloha-control', 'ff81f634-8fb4-4a62-b873-93b02eb86ab4')
[array([[0.00151959]]), array([[0.98291481]]), array([[0.01209957]]), array([[4.75912966e-05]]), array([[2.02893716e-05]]), array([[0.00031977]]), array([[0.01102928]]), array([[0.99756402]]), array([[0.01034162]]), array([[0.00803896]]), array([[0.01615506]]), array([[0.00623623]]), array([[0.00099858]]), array([[1.79337805e-26]]), array([[1.38899512e-27]])]

('aloha-challenger', '87fdfe08-170e-4231-a0b9-543728d6fc57')
[array([[0.00151959]]), array([[0.98291481]]), array([[0.01209957]]), array([[4.75912966e-05]]), array([[2.02893716e-05]]), array([[0.00031977]]), array([[0.01102928]]), array([[0.99756402]]), array([[0.01034162]]), array([[0.00803896]]), array([[0.01615506]]), array([[0.00623623]]), array([[0.00099858]]), array([[1.79337805e-26]]), array([[1.38899512e-27]])]

('aloha-challenger', '87fdfe08-170e-4231-a0b9-543728d6fc57')
[array([[0.00151959]]), array([[0.98291481]]), array([[0.01209957]]), array([[4.75912966e-05]]), array([[2.02893716e-05]]), array([[0.00031977]]), array([[0.01102928]]), array([[0.99756402]]), array([[0.01034162]]), array([[0.00803896]]), array([[0.01615506]]), array([[0.00623623]]), array([[0.00099858]]), array([[1.79337805e-26]]), array([[1.38899512e-27]])]

('aloha-challenger', '87fdfe08-170e-4231-a0b9-543728d6fc57')
[array([[0.00151959]]), array([[0.98291481]]), array([[0.01209957]]), array([[4.75912966e-05]]), array([[2.02893716e-05]]), array([[0.00031977]]), array([[0.01102928]]), array([[0.99756402]]), array([[0.01034162]]), array([[0.00803896]]), array([[0.01615506]]), array([[0.00623623]]), array([[0.00099858]]), array([[1.79337805e-26]]), array([[1.38899512e-27]])]

Replace With Random Split

If a pipeline already had steps as detailed in Add a Step to a Pipeline, this step can be replaced with a random split with the replace_with_random_split method.

The following parameters are used when adding a random split step to a pipeline:

Note that one or more challenger models can be added for the random split step:

replace_with_random_split(index, [(champion_weight, champion_model), (challenger_weight, challenger_model)], (challenger_weight2, challenger_model2),...], hash_key)

A/B Testing Logs

A/B Testing logs entries contain the model used for the inferences in the column out._model_split.

logs = experiment_pipeline.logs(limit=5)
display(logs.loc[:,['time', 'out._model_split', 'out.main']])

Pipeline Shadow Deployments

Wallaroo provides a method of testing the same data against two different models or sets of models at the same time through shadow deployments otherwise known as parallel deployments or A/B test. This allows data to be submitted to a pipeline with inferences running on several different sets of models. Typically this is performed on a model that is known to provide accurate results - the champion - and a model or set of models that is being tested to see if it provides more accurate or faster responses depending on the criteria known as the challenger(s). Multiple challengers can be tested against a single champion to determine which is “better” based on the organization’s criteria.

As described in the Wallaroo blog post The What, Why, and How of Model A/B Testing:

In data science, A/B tests can also be used to choose between two models in production, by measuring which model performs better in the real world. In this formulation, the control is often an existing model that is currently in production, sometimes called the champion. The treatment is a new model being considered to replace the old one. This new model is sometimes called the challenger….
Keep in mind that in machine learning, the terms experiments and trials also often refer to the process of finding a training configuration that works best for the problem at hand (this is sometimes called hyperparameter optimization).

When a shadow deployment is created, only the inference from the champion is returned in the InferenceResult Object data, while the result data for the shadow deployments is stored in the InferenceResult Object shadow_data.

Create Shadow Deployment

Create a parallel or shadow deployment for a pipeline with the pipeline.add_shadow_deploy(champion, challengers[]) method, where the champion is a Wallaroo Model object, and challengers[] is one or more Wallaroo Model objects.

Each inference request sent to the pipeline is sent to all the models. The prediction from the champion is returned by the pipeline, while the predictions from the challengers are not part of the standard output, but are kept stored in the shadow_data attribute and in the logs for later comparison.

In this example, a shadow deployment is created with the champion versus two challenger models.

champion = wl.upload_model(champion_model_name, champion_model_file).configure()
model2 = wl.upload_model(shadow_model_01_name, shadow_model_01_file).configure()
model3 = wl.upload_model(shadow_model_02_name, shadow_model_02_file).configure()
   
pipeline.add_shadow_deploy(champion, [model2, model3])
pipeline.deploy()

An alternate method is with the pipeline.replace_with_shadow_deploy(index, champion, challengers[]) method, where the index is the pipeline step to replace.

Shadow Deploy Outputs

Model outputs are listed by column based on the model’s outputs. The output data is set by the term out, followed by the name of the model. For the default model, this is out.{variable_name}, while the shadow deployed models are in the format out_{model name}.variable, where {model name} is the name of the shadow deployed model.

sample_data_file = './smoke_test.df.json'
response = pipeline.infer_from_file(sample_data_file)

Retrieve Shadow Deployment Logs

Shadow deploy results are part of the Pipeline.logs() method. The output data is set by the term out, followed by the name of the model. For the default model, this is out.dense_1, while the shadow deployed models are in the format out_{model name}.variable, where {model name} is the name of the shadow deployed model.

logs = pipeline.logs()
display(logs)

Get Pipeline URL Endpoint

The Pipeline URL Endpoint or the Pipeline Deploy URL is used to submit data to a pipeline to use for an inference. This is done through the pipeline _deployment._url() method.

In this example, the pipeline URL endpoint for the pipeline ccfraud_pipeline will be displayed:

ccfraud_pipeline._deployment._url()

'http://engine-lb.ccfraud-pipeline-1:29502/pipelines/ccfraud-pipeline'