Esecuzione di query su entità di lineage

from sagemaker.lineage.context import Context, EndpointContext
from sagemaker.lineage.action import Action
from sagemaker.lineage.association import Association
from sagemaker.lineage.artifact import Artifact, ModelArtifact, DatasetArtifact

from sagemaker.lineage.query import (
    LineageQuery,
    LineageFilter,
    LineageSourceEnum,
    LineageEntityEnum,
    LineageQueryDirectionEnum,
)
# Find the endpoint context and model artifact that should be used for the lineage queries.

contexts = Context.list(source_uri=endpoint_arn)
context_name = list(contexts)[0].context_name
endpoint_context = EndpointContext.load(context_name=context_name)
        

# Define the LineageFilter to look for entities of type `ARTIFACT` and the source of type `DATASET`.

query_filter = LineageFilter(
    entities=[LineageEntityEnum.ARTIFACT], sources=[LineageSourceEnum.DATASET]
)

# Providing this `LineageFilter` to the `LineageQuery` constructs a query that traverses through the given context `endpoint_context`
# and find all datasets.

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[endpoint_context.context_arn],
    query_filter=query_filter,
    direction=LineageQueryDirectionEnum.ASCENDANTS,
    include_edges=False,
)

# Parse through the query results to get the lineage objects corresponding to the datasets
dataset_artifacts = []
for vertex in query_result.vertices:
    dataset_artifacts.append(vertex.to_lineage_object().source.source_uri)

pp.pprint(dataset_artifacts)

# Define the LineageFilter to look for entities of type `ARTIFACT` and the source of type `MODEL`.

query_filter = LineageFilter(
    entities=[LineageEntityEnum.ARTIFACT], sources=[LineageSourceEnum.MODEL]
)

# Providing this `LineageFilter` to the `LineageQuery` constructs a query that traverses through the given context `endpoint_context`
# and find all datasets.

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[endpoint_context.context_arn],
    query_filter=query_filter,
    direction=LineageQueryDirectionEnum.ASCENDANTS,
    include_edges=False,
)

# Parse through the query results to get the lineage objects corresponding to the model
model_artifacts = []
for vertex in query_result.vertices:
    model_artifacts.append(vertex.to_lineage_object().source.source_uri)

# The results of the `LineageQuery` API call return the ARN of the model deployed to the endpoint along with
# the S3 URI to the model.tar.gz file associated with the model
pp.pprint(model_artifacts)

# Define the LineageFilter to look for entities of type `TRIAL_COMPONENT` and the source of type `TRAINING_JOB`.

query_filter = LineageFilter(
    entities=[LineageEntityEnum.TRIAL_COMPONENT],
    sources=[LineageSourceEnum.TRAINING_JOB],
)

# Providing this `LineageFilter` to the `LineageQuery` constructs a query that traverses through the given context `endpoint_context`
# and find all datasets.

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[endpoint_context.context_arn],
    query_filter=query_filter,
    direction=LineageQueryDirectionEnum.ASCENDANTS,
    include_edges=False,
)

# Parse through the query results to get the ARNs of the training jobs associated with this Endpoint
trial_components = []
for vertex in query_result.vertices:
    trial_components.append(vertex.arn)

pp.pprint(trial_components)

LineageQuery può essere modificato in modo che abbia un diverso start_arns, il che cambia il punto focale del lineage. Inoltre, LineageFilter può utilizzare origini ed entità molteplici per espandere l'ambito della query.

Di seguito utilizziamo il modello come punto focale del lineage e troviamo gli endpoint e i set di dati ad esso associati.

# Get the ModelArtifact

model_artifact_summary = list(Artifact.list(source_uri=model_package_arn))[0]
model_artifact = ModelArtifact.load(artifact_arn=model_artifact_summary.artifact_arn)
query_filter = LineageFilter(
    entities=[LineageEntityEnum.ARTIFACT],
    sources=[LineageSourceEnum.ENDPOINT, LineageSourceEnum.DATASET],
)

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[model_artifact.artifact_arn],  # Model is the starting artifact
    query_filter=query_filter,
    # Find all the entities that descend from the model, i.e. the endpoint
    direction=LineageQueryDirectionEnum.DESCENDANTS,
    include_edges=False,
)

associations = []
for vertex in query_result.vertices:
    associations.append(vertex.to_lineage_object().source.source_uri)

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[model_artifact.artifact_arn],  # Model is the starting artifact
    query_filter=query_filter,
    # Find all the entities that ascend from the model, i.e. the datasets
    direction=LineageQueryDirectionEnum.ASCENDANTS,
    include_edges=False,
)

for vertex in query_result.vertices:
    associations.append(vertex.to_lineage_object().source.source_uri)

pp.pprint(associations)

Quando la direzione è impostata su BOTH, la query attraversa il grafico per trovare le relazioni di ascendenza e discendenza. Questo attraversamento avviene non solo dal nodo iniziale, ma da ogni nodo visitato. Ad esempio, se un processo di addestramento viene eseguito due volte ed entrambi i modelli generati dal processo di addestramento vengono implementati sugli endpoint, il risultato della query con direzione impostata su BOTH mostra entrambi gli endpoint. Questo perché la stessa immagine viene utilizzata per il addestramento e l'implementazione del modello. Poiché l'immagine è comune al modello, nel risultato della query vengono visualizzati start_arn ed entrambi gli endpoint.

query_filter = LineageFilter(
    entities=[LineageEntityEnum.ARTIFACT],
    sources=[LineageSourceEnum.ENDPOINT, LineageSourceEnum.DATASET],
)

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[model_artifact.artifact_arn],  # Model is the starting artifact
    query_filter=query_filter,
    # This specifies that the query should look for associations both ascending and descending for the start
    direction=LineageQueryDirectionEnum.BOTH,
    include_edges=False,
)

associations = []
for vertex in query_result.vertices:
    associations.append(vertex.to_lineage_object().source.source_uri)

pp.pprint(associations)

Per capire la direzione del grafico di lineage, prendi il seguente grafico delle relazioni tra entità: Set di dati -> Processo di addestramento -> Modello -> Endpoint

L'endpoint è una discendenza del modello e il modello è una discendenza del set di dati. Analogamente, il modello è un'ascendenza dell'endpoint. Il parametro direction può essere utilizzato per specificare se la query deve restituire entità che rappresentano discendenze o ascendenze dell'entità in start_arns. Se start_arns contiene un modello e la direzione è DESCENDANTS, la query restituisce l'endpoint. Se la direzione è ASCENDANTS, la query restituisce il set di dati.

# In this example, we'll look at the impact of specifying the direction as ASCENDANT or DESCENDANT in a `LineageQuery`.

query_filter = LineageFilter(
    entities=[LineageEntityEnum.ARTIFACT],
    sources=[
        LineageSourceEnum.ENDPOINT,
        LineageSourceEnum.MODEL,
        LineageSourceEnum.DATASET,
        LineageSourceEnum.TRAINING_JOB,
    ],
)

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[model_artifact.artifact_arn],
    query_filter=query_filter,
    direction=LineageQueryDirectionEnum.ASCENDANTS,
    include_edges=False,
)

ascendant_artifacts = []

# The lineage entity returned for the Training Job is a TrialComponent which can't be converted to a
# lineage object using the method `to_lineage_object()` so we extract the TrialComponent ARN.
for vertex in query_result.vertices:
    try:
        ascendant_artifacts.append(vertex.to_lineage_object().source.source_uri)
    except:
        ascendant_artifacts.append(vertex.arn)

print("Ascendant artifacts : ")
pp.pprint(ascendant_artifacts)

query_result = LineageQuery(sagemaker_session).query(
    start_arns=[model_artifact.artifact_arn],
    query_filter=query_filter,
    direction=LineageQueryDirectionEnum.DESCENDANTS,
    include_edges=False,
)

descendant_artifacts = []
for vertex in query_result.vertices:
    try:
        descendant_artifacts.append(vertex.to_lineage_object().source.source_uri)
    except:
        # Handling TrialComponents.
        descendant_artifacts.append(vertex.arn)

print("Descendant artifacts : ")
pp.pprint(descendant_artifacts)

Le classi EndpointContext, ModelArtifact e DatasetArtifact dispongono di funzioni di supporto che fungono da wrapper sull'API LineageQuery per semplificare l'utilizzo di determinate query di lineage. Il seguente esempio illustra come utilizzare queste funzioni di supporto.

# Find all the datasets associated with this endpoint

datasets = []
dataset_artifacts = endpoint_context.dataset_artifacts()
for dataset in dataset_artifacts:
    datasets.append(dataset.source.source_uri)
print("Datasets : ", datasets)

# Find the training jobs associated with the endpoint
training_job_artifacts = endpoint_context.training_job_arns()
training_jobs = []
for training_job in training_job_artifacts:
    training_jobs.append(training_job)
print("Training Jobs : ", training_jobs)

# Get the ARN for the pipeline execution associated with this endpoint (if any)
pipeline_executions = endpoint_context.pipeline_execution_arn()
if pipeline_executions:
    for pipeline in pipelines_executions:
        print(pipeline)

# Here we use the `ModelArtifact` class to find all the datasets and endpoints associated with the model

dataset_artifacts = model_artifact.dataset_artifacts()
endpoint_contexts = model_artifact.endpoint_contexts()

datasets = [dataset.source.source_uri for dataset in dataset_artifacts]
endpoints = [endpoint.source.source_uri for endpoint in endpoint_contexts]

print("Datasets associated with this model : ")
pp.pprint(datasets)

print("Endpoints associated with this model : ")
pp.pprint(endpoints)

# Here we use the `DatasetArtifact` class to find all the endpoints hosting models that were trained with a particular dataset
# Find the artifact associated with the dataset

dataset_artifact_arn = list(Artifact.list(source_uri=training_data))[0].artifact_arn
dataset_artifact = DatasetArtifact.load(artifact_arn=dataset_artifact_arn)

# Find the endpoints that used this training dataset
endpoint_contexts = dataset_artifact.endpoint_contexts()
endpoints = [endpoint.source.source_uri for endpoint in endpoint_contexts]

print("Endpoints associated with the training dataset {}".format(training_data))
pp.pprint(endpoints)

Una classe di supporto Visualizer viene fornita nel notebook di esempio visualizer.py per aiutare a tracciare il grafico di lineage. Quando viene renderizzata la risposta alla query, viene visualizzato un grafico con le relazioni di lineage da StartArns. Da StartArns la visualizzazione mostra le relazioni con le altre entità di lineage restituite nell'operazione API query_lineage.

# Graph APIs
# Here we use the boto3 `query_lineage` API to generate the query response to plot.

from visualizer import Visualizer

query_response = sm_client.query_lineage(
    StartArns=[endpoint_context.context_arn], Direction="Ascendants", IncludeEdges=True
)

viz = Visualizer()
viz.render(query_response, "Endpoint")
        
        query_response = sm_client.query_lineage(
    StartArns=[model_artifact.artifact_arn], Direction="Ascendants", IncludeEdges=True
)
viz.render(query_response, "Model")