def ingest_feature_set(
request: Request,
project: str,
name: str,
reference: str,
ingest_parameters: Optional[
schemas.FeatureSetIngestInput
] = schemas.FeatureSetIngestInput(),
username: str = Header(None, alias="x-remote-user"),
auth_verifier: deps.AuthVerifier = Depends(deps.AuthVerifier),
db_session: Session = Depends(deps.get_db_session),
):
tag, uid = parse_reference(reference)
feature_set_record = get_db().get_feature_set(db_session, project, name, tag, uid)
feature_set = mlrun.feature_store.FeatureSet.from_dict(feature_set_record.dict())
# Need to override the default rundb since we're in the server.
feature_set._override_run_db(db_session, auth_verifier.auth_info.session)
data_source = data_targets = None
if ingest_parameters.source:
data_source = DataSource.from_dict(ingest_parameters.source.dict())
if ingest_parameters.targets:
data_targets = [
DataTargetBase.from_dict(data_target.dict())
for data_target in ingest_parameters.targets
]
run_config = RunConfig()
# Try to deduce whether the ingest job will need v3io mount, by analyzing the paths to the source and
# targets. If it needs it, apply v3io mount to the run_config. Note that the access-key and username are
# user-context parameters, we cannot use the api context.
if _has_v3io_path(data_source, data_targets, feature_set):
secrets = get_secrets(request)
access_key = secrets.get("V3IO_ACCESS_KEY", None)
if not access_key or not username:
log_and_raise(
HTTPStatus.BAD_REQUEST.value,
reason="Request needs v3io access key and username in header",
)
run_config = run_config.apply(v3io_cred(access_key=access_key, user=username))
infer_options = ingest_parameters.infer_options or InferOptions.default()
run_params = ingest(
feature_set,
data_source,
data_targets,
infer_options=infer_options,
return_df=False,
run_config=run_config,
)
# ingest may modify the feature-set contents, so returning the updated feature-set.
result_feature_set = schemas.FeatureSet(**feature_set.to_dict())
return schemas.FeatureSetIngestOutput(
feature_set=result_feature_set, run_object=run_params.to_dict()
)
def get_default_targets():
"""initialize the default feature set targets list"""
return [
DataTargetBase(target, name=str(target))
for target in default_target_names()
]
def get_target_driver(target_spec, resource=None):
if isinstance(target_spec, dict):
target_spec = DataTargetBase.from_dict(target_spec)
driver_class = kind_to_driver[target_spec.kind]
return driver_class.from_spec(target_spec, resource)
def ingest_feature_set(
project: str,
name: str,
reference: str,
ingest_parameters: Optional[
schemas.FeatureSetIngestInput
] = schemas.FeatureSetIngestInput(),
username: str = Header(None, alias="x-remote-user"),
auth_verifier: deps.AuthVerifierDep = Depends(deps.AuthVerifierDep),
db_session: Session = Depends(deps.get_db_session),
):
mlrun.api.utils.clients.opa.Client().query_project_resource_permissions(
mlrun.api.schemas.AuthorizationResourceTypes.feature_set,
project,
name,
mlrun.api.schemas.AuthorizationAction.update,
auth_verifier.auth_info,
)
mlrun.api.utils.clients.opa.Client().query_project_resource_permissions(
mlrun.api.schemas.AuthorizationResourceTypes.run,
project,
"",
mlrun.api.schemas.AuthorizationAction.create,
auth_verifier.auth_info,
)
data_source = data_targets = None
if ingest_parameters.source:
data_source = DataSource.from_dict(ingest_parameters.source.dict())
if data_source.schedule:
mlrun.api.utils.clients.opa.Client().query_project_resource_permissions(
mlrun.api.schemas.AuthorizationResourceTypes.schedule,
project,
"",
mlrun.api.schemas.AuthorizationAction.create,
auth_verifier.auth_info,
)
tag, uid = parse_reference(reference)
feature_set_record = mlrun.api.crud.FeatureStore().get_feature_set(
db_session, project, name, tag, uid
)
feature_set = mlrun.feature_store.FeatureSet.from_dict(feature_set_record.dict())
if feature_set.spec.function and feature_set.spec.function.function_object:
function = feature_set.spec.function.function_object
mlrun.api.utils.clients.opa.Client().query_project_resource_permissions(
mlrun.api.schemas.AuthorizationResourceTypes.function,
function.metadata.project,
function.metadata.name,
mlrun.api.schemas.AuthorizationAction.read,
auth_verifier.auth_info,
)
# Need to override the default rundb since we're in the server.
feature_set._override_run_db(db_session)
if ingest_parameters.targets:
data_targets = [
DataTargetBase.from_dict(data_target.dict())
for data_target in ingest_parameters.targets
]
run_config = RunConfig(owner=username)
# Try to deduce whether the ingest job will need v3io mount, by analyzing the paths to the source and
# targets. If it needs it, apply v3io mount to the run_config. Note that the access-key and username are
# user-context parameters, we cannot use the api context.
if _has_v3io_path(data_source, data_targets, feature_set):
access_key = auth_verifier.auth_info.data_session
if not access_key or not username:
log_and_raise(
HTTPStatus.BAD_REQUEST.value,
reason="Request needs v3io access key and username in header",
)
run_config = run_config.apply(v3io_cred(access_key=access_key, user=username))
infer_options = ingest_parameters.infer_options or InferOptions.default()
run_params = ingest(
feature_set,
data_source,
data_targets,
infer_options=infer_options,
return_df=False,
run_config=run_config,
)
# ingest may modify the feature-set contents, so returning the updated feature-set.
result_feature_set = schemas.FeatureSet(**feature_set.to_dict())
return schemas.FeatureSetIngestOutput(
feature_set=result_feature_set, run_object=run_params.to_dict()
)
