def test_artifacts(db: RunDBInterface):
k1, u1, art1 = "k1", "u1", {"a": 1}
db.store_artifact(k1, art1, u1)
art = db.read_artifact(k1, u1)
assert art1["a"] == art["a"], "get artifact"
art = db.read_artifact(k1)
assert art1["a"] == art["a"], "get latest artifact"
prj = "p1"
k2, u2, art2 = "k2", "u2", {"a": 2}
db.store_artifact(k2, art2, u2, project=prj)
k3, u3, art3 = "k3", "u3", {"a": 3}
db.store_artifact(k3, art3, u3, project=prj)
arts = db.list_artifacts(project=prj, tag="*")
expected = 2 if isinstance(db, SQLDB) else 4 # FIXME
assert expected == len(arts), "list artifacts length"
assert {2, 3} == {a["a"] for a in arts}, "list artifact a"
db.del_artifact(key=k1)
with pytest.raises((sqldb.RunDBError, mlrun.errors.MLRunNotFoundError)):
db.read_artifact(k1)
def _create_resources_of_all_kinds(db: DBInterface,
db_session: sqlalchemy.orm.Session,
project: str):
# Create several functions with several tags
labels = {
"name": "value",
"name2": "value2",
}
function = {
"bla": "blabla",
"metadata": {
"labels": labels
},
"status": {
"bla": "blabla"
},
}
function_names = ["function_name_1", "function_name_2", "function_name_3"]
function_tags = ["some_tag", "some_tag2", "some_tag3"]
for function_name in function_names:
for function_tag in function_tags:
db.store_function(
db_session,
function,
function_name,
project,
tag=function_tag,
versioned=True,
)
# Create several artifacts with several tags
artifact = {
"bla": "blabla",
"labels": labels,
"status": {
"bla": "blabla"
},
}
artifact_keys = ["artifact_key_1", "artifact_key_2", "artifact_key_3"]
artifact_uids = ["some_uid", "some_uid2", "some_uid3"]
artifact_tags = ["some_tag", "some_tag2", "some_tag3"]
for artifact_key in artifact_keys:
for artifact_uid in artifact_uids:
for artifact_tag in artifact_tags:
for artifact_iter in range(3):
db.store_artifact(
db_session,
artifact_key,
artifact,
artifact_uid,
artifact_iter,
artifact_tag,
project,
)
# Create several runs
run = {
"bla": "blabla",
"metadata": {
"labels": labels
},
"status": {
"bla": "blabla"
},
}
run_uids = ["some_uid", "some_uid2", "some_uid3"]
for run_uid in run_uids:
for run_iter in range(3):
db.store_run(db_session, run, run_uid, project, run_iter)
# Create several logs
log = b"some random log"
log_uids = ["some_uid", "some_uid2", "some_uid3"]
for log_uid in log_uids:
db.store_log(db_session, log_uid, project, log)
# Create several schedule
schedule = {
"bla": "blabla",
"status": {
"bla": "blabla"
},
}
schedule_cron_trigger = schemas.ScheduleCronTrigger(year=1999)
schedule_names = ["schedule_name_1", "schedule_name_2", "schedule_name_3"]
for schedule_name in schedule_names:
db.create_schedule(
db_session,
project,
schedule_name,
schemas.ScheduleKinds.job,
schedule,
schedule_cron_trigger,
labels,
)
feature_set = schemas.FeatureSet(
metadata=schemas.ObjectMetadata(name="dummy",
tag="latest",
labels={"owner": "nobody"}),
spec=schemas.FeatureSetSpec(
entities=[
schemas.Entity(name="ent1",
value_type="str",
labels={"label": "1"})
],
features=[
schemas.Feature(name="feat1",
value_type="str",
labels={"label": "1"})
],
),
status={},
)
db.create_feature_set(db_session, project, feature_set)
feature_vector = schemas.FeatureVector(
metadata=schemas.ObjectMetadata(name="dummy",
tag="latest",
labels={"owner": "somebody"}),
spec=schemas.ObjectSpec(),
status=schemas.ObjectStatus(state="created"),
)
db.create_feature_vector(db_session, project, feature_vector)
def _create_resources_of_all_kinds(
db_session: Session,
k8s_secrets_mock: tests.api.conftest.K8sSecretsMock,
project: str,
):
db = mlrun.api.utils.singletons.db.get_db()
# add labels to project
project_schema = mlrun.api.schemas.Project(
metadata=mlrun.api.schemas.ProjectMetadata(
name=project, labels={"key": "value"}
),
spec=mlrun.api.schemas.ProjectSpec(description="some desc"),
)
mlrun.api.utils.singletons.project_member.get_project_member().store_project(
db_session, project, project_schema
)
# Create several functions with several tags
labels = {
"name": "value",
"name2": "value2",
}
function = {
"bla": "blabla",
"metadata": {"labels": labels},
"spec": {"asd": "asdasd"},
"status": {"bla": "blabla"},
}
function_names = ["function_name_1", "function_name_2", "function_name_3"]
function_tags = ["some_tag", "some_tag2", "some_tag3"]
for function_name in function_names:
for function_tag in function_tags:
# change spec a bit so different (un-tagged) versions will be created
for index in range(3):
function["spec"]["index"] = index
db.store_function(
db_session,
function,
function_name,
project,
tag=function_tag,
versioned=True,
)
# Create several artifacts with several tags
artifact = {
"bla": "blabla",
"labels": labels,
"status": {"bla": "blabla"},
}
artifact_keys = ["artifact_key_1", "artifact_key_2", "artifact_key_3"]
artifact_uids = ["some_uid", "some_uid2", "some_uid3"]
artifact_tags = ["some_tag", "some_tag2", "some_tag3"]
for artifact_key in artifact_keys:
for artifact_uid in artifact_uids:
for artifact_tag in artifact_tags:
for artifact_iter in range(3):
artifact["iter"] = artifact_iter
artifact["tag"] = artifact_tag
artifact["uid"] = artifact_uid
db.store_artifact(
db_session,
artifact_key,
artifact,
artifact_uid,
artifact_iter,
artifact_tag,
project,
)
# Create several runs
run = {
"bla": "blabla",
"metadata": {"labels": labels},
"status": {"bla": "blabla"},
}
run_uids = ["some_uid", "some_uid2", "some_uid3"]
for run_uid in run_uids:
for run_iter in range(3):
db.store_run(db_session, run, run_uid, project, run_iter)
# Create several logs
log = b"some random log"
log_uids = ["some_uid", "some_uid2", "some_uid3"]
for log_uid in log_uids:
mlrun.api.crud.Logs().store_log(log, project, log_uid)
# Create several schedule
schedule = {
"bla": "blabla",
"status": {"bla": "blabla"},
}
schedule_cron_trigger = mlrun.api.schemas.ScheduleCronTrigger(year=1999)
schedule_names = ["schedule_name_1", "schedule_name_2", "schedule_name_3"]
for schedule_name in schedule_names:
mlrun.api.utils.singletons.scheduler.get_scheduler().create_schedule(
db_session,
mlrun.api.schemas.AuthInfo(),
project,
schedule_name,
mlrun.api.schemas.ScheduleKinds.job,
schedule,
schedule_cron_trigger,
labels,
)
# Create several feature sets with several tags
labels = {
"owner": "nobody",
}
feature_set = mlrun.api.schemas.FeatureSet(
metadata=mlrun.api.schemas.ObjectMetadata(
name="dummy", tag="latest", labels=labels
),
spec=mlrun.api.schemas.FeatureSetSpec(
entities=[
mlrun.api.schemas.Entity(
name="ent1", value_type="str", labels={"label": "1"}
)
],
features=[
mlrun.api.schemas.Feature(
name="feat1", value_type="str", labels={"label": "1"}
)
],
),
status={},
)
feature_set_names = ["feature_set_1", "feature_set_2", "feature_set_3"]
feature_set_tags = ["some_tag", "some_tag2", "some_tag3"]
for feature_set_name in feature_set_names:
for feature_set_tag in feature_set_tags:
# change spec a bit so different (un-tagged) versions will be created
for index in range(3):
feature_set.metadata.name = feature_set_name
feature_set.metadata.tag = feature_set_tag
feature_set.spec.index = index
db.store_feature_set(db_session, project, feature_set_name, feature_set)
feature_vector = mlrun.api.schemas.FeatureVector(
metadata=mlrun.api.schemas.ObjectMetadata(
name="dummy", tag="latest", labels=labels
),
spec=mlrun.api.schemas.ObjectSpec(),
status=mlrun.api.schemas.ObjectStatus(state="created"),
)
feature_vector_names = ["feature_vector_1", "feature_vector_2", "feature_vector_3"]
feature_vector_tags = ["some_tag", "some_tag2", "some_tag3"]
for feature_vector_name in feature_vector_names:
for feature_vector_tag in feature_vector_tags:
# change spec a bit so different (un-tagged) versions will be created
for index in range(3):
feature_vector.metadata.name = feature_vector_name
feature_vector.metadata.tag = feature_vector_tag
feature_vector.spec.index = index
db.store_feature_vector(
db_session, project, feature_vector_name, feature_vector
)
secrets = {f"secret_{i}": "a secret" for i in range(5)}
k8s_secrets_mock.store_project_secrets(project, secrets)
def _create_resources_of_all_kinds(db_session: Session, project: str):
db = mlrun.api.utils.singletons.db.get_db()
# add labels to project
project_schema = mlrun.api.schemas.Project(
metadata=mlrun.api.schemas.ProjectMetadata(name=project,
labels={"key": "value"}),
spec=mlrun.api.schemas.ProjectSpec(description="some desc"),
)
db.store_project(db_session, project, project_schema)
# Create several functions with several tags
labels = {
"name": "value",
"name2": "value2",
}
function = {
"bla": "blabla",
"metadata": {
"labels": labels
},
"status": {
"bla": "blabla"
},
}
function_names = ["function_name_1", "function_name_2", "function_name_3"]
function_tags = ["some_tag", "some_tag2", "some_tag3"]
for function_name in function_names:
for function_tag in function_tags:
db.store_function(
db_session,
function,
function_name,
project,
tag=function_tag,
versioned=True,
)
# Create several artifacts with several tags
artifact = {
"bla": "blabla",
"labels": labels,
"status": {
"bla": "blabla"
},
}
artifact_keys = ["artifact_key_1", "artifact_key_2", "artifact_key_3"]
artifact_uids = ["some_uid", "some_uid2", "some_uid3"]
artifact_tags = ["some_tag", "some_tag2", "some_tag3"]
for artifact_key in artifact_keys:
for artifact_uid in artifact_uids:
for artifact_tag in artifact_tags:
for artifact_iter in range(3):
db.store_artifact(
db_session,
artifact_key,
artifact,
artifact_uid,
artifact_iter,
artifact_tag,
project,
)
# Create several runs
run = {
"bla": "blabla",
"metadata": {
"labels": labels
},
"status": {
"bla": "blabla"
},
}
run_uids = ["some_uid", "some_uid2", "some_uid3"]
for run_uid in run_uids:
for run_iter in range(3):
db.store_run(db_session, run, run_uid, project, run_iter)
# Create several logs
log = b"some random log"
log_uids = ["some_uid", "some_uid2", "some_uid3"]
for log_uid in log_uids:
db.store_log(db_session, log_uid, project, log)
# Create several schedule
schedule = {
"bla": "blabla",
"status": {
"bla": "blabla"
},
}
schedule_cron_trigger = mlrun.api.schemas.ScheduleCronTrigger(year=1999)
schedule_names = ["schedule_name_1", "schedule_name_2", "schedule_name_3"]
for schedule_name in schedule_names:
db.create_schedule(
db_session,
project,
schedule_name,
mlrun.api.schemas.ScheduleKinds.job,
schedule,
schedule_cron_trigger,
mlrun.config.config.httpdb.scheduling.default_concurrency_limit,
labels,
)
feature_set = mlrun.api.schemas.FeatureSet(
metadata=mlrun.api.schemas.ObjectMetadata(name="dummy",
tag="latest",
labels={"owner": "nobody"}),
spec=mlrun.api.schemas.FeatureSetSpec(
entities=[
mlrun.api.schemas.Entity(name="ent1",
value_type="str",
labels={"label": "1"})
],
features=[
mlrun.api.schemas.Feature(name="feat1",
value_type="str",
labels={"label": "1"})
],
),
status={},
)
db.create_feature_set(db_session, project, feature_set)
feature_vector = mlrun.api.schemas.FeatureVector(
metadata=mlrun.api.schemas.ObjectMetadata(name="dummy",
tag="latest",
labels={"owner":
"somebody"}),
spec=mlrun.api.schemas.ObjectSpec(),
status=mlrun.api.schemas.ObjectStatus(state="created"),
)
db.create_feature_vector(db_session, project, feature_vector)