def test_router_proto_ok():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr))
request = prediction_pb2.SeldonMessage(data=datadef)
resp = app.Route(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
logging.info(j)
assert j["meta"]["tags"] == {"mytag": 1}
# add default type
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics(
)[0]["value"]
assert j["data"]["tensor"]["shape"] == [1, 1]
assert j["data"]["tensor"]["values"] == [22]
def test_proto_feedback():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr))
meta = prediction_pb2.Meta()
metaJson = {}
routing = {"1": 1}
metaJson["routing"] = routing
json_format.ParseDict(metaJson, meta)
request = prediction_pb2.SeldonMessage(data=datadef)
response = prediction_pb2.SeldonMessage(meta=meta, data=datadef)
feedback = prediction_pb2.Feedback(request=request,
response=response,
reward=1.0)
resp = app.SendFeedback(feedback, None)
def test_aggregate_proto_lowlevel_ok():
user_object = UserObjectLowLevelGrpc()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr1 = np.array([1, 2])
datadef1 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr1))
arr2 = np.array([3, 4])
datadef2 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr2))
msg1 = prediction_pb2.SeldonMessage(data=datadef1)
msg2 = prediction_pb2.SeldonMessage(data=datadef2)
request = prediction_pb2.SeldonMessageList(seldonMessages=[msg1, msg2])
resp = app.Aggregate(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
logging.info(j)
assert j["data"]["tensor"]["shape"] == [2, 1]
assert j["data"]["tensor"]["values"] == [9, 9]
def test_proto_requestPath_2nd_node_ok():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr)
)
meta = prediction_pb2.Meta()
json_format.ParseDict({"requestPath": {"earlier-node": "earlier-image"}}, meta)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
resp = app.Predict(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
logging.info(j)
assert j["meta"]["requestPath"] == {
"my-test-model": "my-test-model-image",
"earlier-node": "earlier-image",
}
def test_proto_passes_through_tags():
user_object = UserObject()
app = SeldonModelGRPC(user_object)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(tensor=prediction_pb2.Tensor(
shape=(2, 1), values=arr), )
meta = prediction_pb2.Meta()
json_format.ParseDict({"tags": {"foo": "bar"}}, meta)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
resp = app.Predict(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
logging.info(j)
assert j["meta"]["tags"] == {"foo": "bar", "mytag": 1}
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics(
)[0]["value"]
assert j["data"]["tensor"]["shape"] == [2, 1]
assert j["data"]["tensor"]["values"] == [1, 2]
def test_proto_gets_meta():
user_object = UserObject(ret_meta=True)
app = SeldonModelGRPC(user_object)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr))
meta = prediction_pb2.Meta()
metaJson = {"puid": "abc"}
json_format.ParseDict(metaJson, meta)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
resp = app.Predict(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
print(j)
assert j["meta"]["tags"] == {"inc_meta": {"puid": "abc"}}
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics(
)[0]["value"]
assert j["data"]["tensor"]["shape"] == [2, 1]
assert j["data"]["tensor"]["values"] == [1, 2]
def test_proto_seldon_metrics_route(cls, client_gets_metrics):
user_object = cls()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=np.array([1, 2])))
request = prediction_pb2.SeldonMessage(data=datadef)
resp = app.Route(request, None)
assert ("metrics" in json.loads(
json_format.MessageToJson(resp))["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 1, [0.0202], ROUTER_METRIC_METHOD_TAG)
resp = app.Route(request, None)
assert ("metrics" in json.loads(
json_format.MessageToJson(resp))["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 2, [0.0202, 0.0202], ROUTER_METRIC_METHOD_TAG)
def test_proto_seldon_runtime_data_aggregate(cls, client_gets_metrics):
user_object = cls()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr1 = np.array([1, 2])
datadef1 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr1)
)
arr2 = np.array([3, 4])
datadef2 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr2)
)
msg1 = prediction_pb2.SeldonMessage(data=datadef1)
msg2 = prediction_pb2.SeldonMessage(data=datadef2)
request = prediction_pb2.SeldonMessageList(seldonMessages=[msg1, msg2])
resp = app.Aggregate(request, None)
j = json.loads(json_format.MessageToJson(resp))
assert j["data"] == {
"names": ["t:0"],
"tensor": {"shape": [2, 1], "values": [1.0, 2.0]},
}
assert j["meta"]["tags"] == EXPECTED_TAGS
assert ("metrics" in j["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 1, [0.0202], AGGREGATE_METRIC_METHOD_TAG)
resp = app.Aggregate(request, None)
j = json.loads(json_format.MessageToJson(resp))
assert j["data"] == {
"names": ["t:0"],
"tensor": {"shape": [2, 1], "values": [1.0, 2.0]},
}
assert j["meta"]["tags"] == EXPECTED_TAGS
assert ("metrics" in j["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 2, [0.0202, 0.0202], AGGREGATE_METRIC_METHOD_TAG)
def test_proto_seldon_metrics_aggregate(cls):
user_object = cls()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr1 = np.array([1, 2])
datadef1 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr1))
arr2 = np.array([3, 4])
datadef2 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr2))
msg1 = prediction_pb2.SeldonMessage(data=datadef1)
msg2 = prediction_pb2.SeldonMessage(data=datadef2)
request = prediction_pb2.SeldonMessageList(seldonMessages=[msg1, msg2])
app.Aggregate(request, None)
data = seldon_metrics.data[os.getpid()]
assert data["GAUGE", "mygauge"]["value"] == 100
assert data["GAUGE", "customtag"]["value"] == 200
assert data["GAUGE", "customtag"]["tags"] == {"mytag": "mytagvalue"}
assert data["COUNTER", "mycounter"]["value"] == 1
assert np.allclose(
np.histogram([20.2 / 1000], BINS)[0], data["TIMER",
"mytimer"]["value"][0])
assert np.allclose(data["TIMER", "mytimer"]["value"][1], 0.0202)
app.Aggregate(request, None)
data = seldon_metrics.data[os.getpid()]
assert data["GAUGE", "mygauge"]["value"] == 100
assert data["GAUGE", "customtag"]["value"] == 200
assert data["GAUGE", "customtag"]["tags"] == {"mytag": "mytagvalue"}
assert data["COUNTER", "mycounter"]["value"] == 2
assert np.allclose(
np.histogram([20.2 / 1000, 20.2 / 1000], BINS)[0],
data["TIMER", "mytimer"]["value"][0],
)
assert np.allclose(data["TIMER", "mytimer"]["value"][1], 0.0404)
def test_proto_seldon_runtime_data_transform_output(cls, client_gets_metrics):
user_object = cls()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=np.array([1, 2])))
request = prediction_pb2.SeldonMessage(data=datadef)
resp = app.TransformOutput(request, None)
j = json.loads(json_format.MessageToJson(resp))
assert j["data"] == {
"names": ["t:0"],
"tensor": {
"shape": [2, 1],
"values": [1.0, 2.0]
},
}
assert j["meta"]["tags"] == EXPECTED_TAGS
assert ("metrics" in j["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 1, [0.0202],
OUTPUT_TRANSFORM_METRIC_METHOD_TAG)
resp = app.TransformOutput(request, None)
j = json.loads(json_format.MessageToJson(resp))
assert j["data"] == {
"names": ["t:0"],
"tensor": {
"shape": [2, 1],
"values": [1.0, 2.0]
},
}
assert j["meta"]["tags"] == EXPECTED_TAGS
assert ("metrics" in j["meta"]) == client_gets_metrics
data = seldon_metrics.data[os.getpid()]
verify_seldon_metrics(data, 2, [0.0202, 0.0202],
OUTPUT_TRANSFORM_METRIC_METHOD_TAG)
def test_aggregate_proto_combines_tags():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
arr1 = np.array([1, 2])
meta1 = prediction_pb2.Meta()
json_format.ParseDict({"tags": {"input-1": "yes", "common": 1}}, meta1)
datadef1 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr1)
)
arr2 = np.array([3, 4])
meta2 = prediction_pb2.Meta()
json_format.ParseDict({"tags": {"input-2": "yes", "common": 2}}, meta2)
datadef2 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr2)
)
msg1 = prediction_pb2.SeldonMessage(data=datadef1, meta=meta1)
msg2 = prediction_pb2.SeldonMessage(data=datadef2, meta=meta2)
request = prediction_pb2.SeldonMessageList(seldonMessages=[msg1, msg2])
resp = app.Aggregate(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
logging.info(j)
assert j["meta"]["tags"] == {
"common": 2,
"input-1": "yes",
"input-2": "yes",
"mytag": 1,
}
# add default type
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics()[0]["value"]
assert j["data"]["tensor"]["shape"] == [2, 1]
assert j["data"]["tensor"]["values"] == [1, 2]
def test_aggregate_proto_ok():
user_object = UserObject()
app = SeldonModelGRPC(user_object)
arr1 = np.array([1, 2])
datadef1 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr1))
arr2 = np.array([3, 4])
datadef2 = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr2))
msg1 = prediction_pb2.SeldonMessage(data=datadef1)
msg2 = prediction_pb2.SeldonMessage(data=datadef2)
request = prediction_pb2.SeldonMessageList(seldonMessages=[msg1, msg2])
resp = app.Aggregate(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
print(j)
assert j["meta"]["tags"] == {"mytag": 1}
# add default type
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics(
)[0]["value"]
assert j["data"]["tensor"]["shape"] == [2, 1]
assert j["data"]["tensor"]["values"] == [1, 2]
def test_model_metadata_ok_grpc():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
resp = app.Metadata(None, None)
assert json.loads(json_format.MessageToJson(resp)) == {
"name": "my-model-name",
"versions": ["model-version"],
"platform": "model-platform",
"inputs": [{
"name": "input",
"datatype": "BYTES",
"shape": ["1"]
}],
"outputs": [{
"name": "output",
"datatype": "BYTES",
"shape": ["1"]
}],
"custom": {
"tag-key": "tag-value"
},
}
def test_proto_seldon_metrics_endpoint(cls, client_gets_metrics):
def _match_label(line):
_data, value = line.split()
name, labels = _data.split()[0].split("{")
labels = labels[:-1]
return name, value, eval(f"dict({labels})")
def _iterate_metrics(text):
for line in text.split("\n"):
if not line or line[0] == "#":
continue
yield _match_label(line)
user_object = cls()
seldon_metrics = SeldonMetrics()
app = SeldonModelGRPC(user_object, seldon_metrics)
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=np.array([1, 2])))
request = prediction_pb2.SeldonMessage(data=datadef)
metrics_app = get_metrics_microservice(seldon_metrics)
metrics_client = metrics_app.test_client()
rv = metrics_client.get("/metrics")
assert rv.status_code == 200
assert rv.data.decode() == ""
resp = app.Predict(request, None)
j = json.loads(json_format.MessageToJson(resp))
assert j["data"] == {
"names": ["t:0"],
"tensor": {
"shape": [2, 1],
"values": [1.0, 2.0]
},
}
assert j["meta"]["tags"] == EXPECTED_TAGS
assert ("metrics" in j["meta"]) == client_gets_metrics
rv = metrics_client.get("/metrics")
text = rv.data.decode()
timer_present = False
for name, value, labels in _iterate_metrics(text):
if name == "mytimer_bucket":
timer_present = True
if name == "mycounter_total":
assert value == "1.0"
assert labels["worker_id"] == str(os.getpid())
if name == "mygauge":
assert value == "100.0"
assert labels["worker_id"] == str(os.getpid())
if name == "customtag":
assert value == "200.0"
assert labels["mytag"] == "mytagvalue"
assert timer_present
