def test_router_proto_lowlevel_raw_ok():
user_object = UserObjectLowLevelRaw()
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["data"]["tensor"]["shape"] == [1, 1]
assert j["data"]["tensor"]["values"] == [1]
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_transform_output_proto_lowlevel_ok():
user_object = UserObjectLowLevelGrpc()
app = SeldonModelGRPC(user_object)
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.TransformOutput(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 transform_input_raw(
self, request: Union[prediction_pb2.SeldonMessage, List, Dict]
) -> Union[prediction_pb2.SeldonMessage, List, Dict]:
is_proto = isinstance(request, prediction_pb2.SeldonMessage)
arr = np.array([9, 9])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr))
response = prediction_pb2.SeldonMessage(data=datadef)
if is_proto:
return response
else:
return seldon_message_to_json(response)
def array_to_grpc_datadef(
data_type: str,
array: np.ndarray,
names: Optional[Iterable[str]] = []) -> prediction_pb2.DefaultData:
"""
Convert numpy array and optional column names into a SeldonMessage DefaultData proto
Parameters
----------
array
numpy array
names
column names
data_type
The SeldonMessage type to convert to
Returns
-------
SeldonMessage DefaultData
"""
if data_type == "tensor":
datadef = prediction_pb2.DefaultData(
names=names,
tensor=prediction_pb2.Tensor(shape=array.shape,
values=array.ravel().tolist()))
elif data_type == "ndarray":
datadef = prediction_pb2.DefaultData(
names=names, ndarray=array_to_list_value(array))
elif data_type == "tftensor":
datadef = prediction_pb2.DefaultData(
names=names, tftensor=tf.make_tensor_proto(array))
else:
datadef = prediction_pb2.DefaultData(
names=names, ndarray=array_to_list_value(array))
return datadef
def predict_grpc(self,request):
"""
predict_grpc will be called only when there is a GRPC call to the server
which in this case, the request will be sent to the TFServer directly.
"""
log.debug("Preprocessing contents for predict function")
request_data_type = request.WhichOneof("data_oneof")
default_data_type = request.data.WhichOneof("data_oneof")
log.debug(f"Request data type: {request_data_type}, Default data type: {default_data_type}")
if request_data_type != "data":
raise Exception("strData, binData and jsonData not supported.")
tfrequest = predict_pb2.PredictRequest()
tfrequest.model_spec.name = self.model_name
tfrequest.model_spec.signature_name = self.signature_name
# For GRPC case, if we have a TFTensor message we can pass it directly
if default_data_type == "tftensor":
tfrequest.inputs[self.model_input].CopyFrom(request.data.tftensor)
result = self.stub.Predict(tfrequest)
datadef = prediction_pb2.DefaultData(
tftensor=result.outputs[self.model_output]
)
return prediction_pb2.SeldonMessage(data=datadef)
else:
data_arr = grpc_datadef_to_array(request.data)
tfrequest.inputs[self.model_input].CopyFrom(
tf.contrib.util.make_tensor_proto(
data_arr.tolist(),
shape=data_arr.shape))
result = self.stub.Predict(tfrequest)
datadef = prediction_pb2.DefaultData(
tftensor=result.outputs[self.model_output]
)
return prediction_pb2.SeldonMessage(data=datadef)
def test_aggregate_proto_combines_tags():
user_object = UserObject()
app = SeldonModelGRPC(user_object)
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_model_template_app_grpc(tracing):
with start_microservice(
join(dirname(__file__), "model-template-app"), tracing=tracing, grpc=True
):
data = np.array([[1, 2]])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=data.shape, values=data.flatten())
)
request = prediction_pb2.SeldonMessage(data=datadef)
channel = grpc.insecure_channel("0.0.0.0:5000")
stub = prediction_pb2_grpc.ModelStub(channel)
response = stub.Predict(request=request)
assert response.data.tensor.shape[0] == 1
assert response.data.tensor.shape[1] == 2
assert response.data.tensor.values[0] == 1
assert response.data.tensor.values[1] == 2
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr)
)
request = prediction_pb2.SeldonMessage(data=datadef)
feedback = prediction_pb2.Feedback(request=request, reward=1.0)
response = stub.SendFeedback(request=request)
def test_proto_requestPath_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({"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"]["requestPath"] == {"my-test-model": "my-test-model-image"}
def test_proto_tftensor_ok():
user_object = UserObject()
app = SeldonModelGRPC(user_object)
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(tftensor=tf.make_tensor_proto(arr))
request = prediction_pb2.SeldonMessage(data=datadef)
resp = app.Predict(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
print(j)
assert j["meta"]["tags"] == {"mytag": 1}
assert j["meta"]["metrics"][0]["key"] == user_object.metrics()[0]["key"]
assert j["meta"]["metrics"][0]["value"] == user_object.metrics(
)[0]["value"]
arr2 = tf.make_ndarray(resp.data.tftensor)
assert np.array_equal(arr, arr2)
def test_proto_ok():
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))
request = prediction_pb2.SeldonMessage(data=datadef)
resp = app.Predict(request, None)
jStr = json_format.MessageToJson(resp)
j = json.loads(jStr)
print(j)
assert j["meta"]["tags"] == {"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_model_template_app_grpc_tags(microservice):
data = np.array([[1, 2]])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=data.shape, values=data.flatten()))
meta = prediction_pb2.Meta()
json_format.ParseDict({"tags": {"foo": "bar"}}, meta)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
channel = grpc.insecure_channel("0.0.0.0:5000")
stub = prediction_pb2_grpc.ModelStub(channel)
response = retry_method(stub.Predict, kwargs=dict(request=request))
assert response.data.tensor.shape[0] == 1
assert response.data.tensor.shape[1] == 2
assert response.data.tensor.values[0] == 1
assert response.data.tensor.values[1] == 2
assert response.meta.tags["foo"].string_value == "bar"
def test_proto_feedback():
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()
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_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 grpc_request_api_gateway(oauth_key,oauth_secret,namespace,rest_endpoint="localhost:8002",grpc_endpoint="localhost:8003",data_size=5,rows=1,data=None):
token = get_token(oauth_key,oauth_secret,namespace,rest_endpoint)
if data is None:
shape, arr = create_random_data(data_size,rows)
else:
shape = data.shape
arr = data.flatten()
datadef = prediction_pb2.DefaultData(
tensor = prediction_pb2.Tensor(
shape = shape,
values = arr
)
)
request = prediction_pb2.SeldonMessage(data = datadef)
channel = grpc.insecure_channel(grpc_endpoint)
stub = prediction_pb2_grpc.SeldonStub(channel)
metadata = [('oauth_token', token)]
response = stub.Predict(request=request,metadata=metadata)
return response
def test_transform_output_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.TransformOutput(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"] == [2, 1]
assert j["data"]["tensor"]["values"] == [1, 2]
def transform_input_grpc(self, request):
logger.info("Transform called")
start_time = datetime.datetime.now()
X = np.frombuffer(request.binData, dtype=np.uint8)
X = cv2.imdecode(X, cv2.IMREAD_COLOR) # BGR format
X = self.crop_resize(X, self.size, self.size)
X = X.astype(self.dtype)
X = X.transpose(2, 0, 1).reshape(1, 3, self.size, self.size)
logger.info("Shape: %s; Dtype: %s; Min: %s; Max: %s", X.shape, X.dtype,
np.amin(X), np.amax(X))
jpeg_time = datetime.datetime.now()
jpeg_duration = (jpeg_time - start_time).total_seconds() * 1000
logger.info("jpeg preprocessing: %s ms", jpeg_duration)
datadef = prediction_pb2.DefaultData(names='x',
tftensor=tf.make_tensor_proto(X))
end_time = datetime.datetime.now()
duration = (end_time - start_time).total_seconds() * 1000
logger.info("Total transformation: %s ms", duration)
request = prediction_pb2.SeldonMessage(data=datadef)
return request
def grpc_request_ambassador(
deploymentName, namespace, endpoint="localhost:8004", data_size=5, rows=1, data=None
):
if data is None:
shape, arr = create_random_data(data_size, rows)
else:
shape = data.shape
arr = data.flatten()
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=shape, values=arr)
)
request = prediction_pb2.SeldonMessage(data=datadef)
channel = grpc.insecure_channel(endpoint)
stub = prediction_pb2_grpc.SeldonStub(channel)
if namespace is None:
metadata = [("seldon", deploymentName)]
else:
metadata = [("seldon", deploymentName), ("namespace", namespace)]
response = stub.Predict(request=request, metadata=metadata)
return response
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_model_template_app_grpc_tags(tracing):
with start_microservice(join(dirname(__file__), "model-template-app"),
tracing=tracing,
grpc=True):
data = np.array([[1, 2]])
datadef = prediction_pb2.DefaultData(tensor=prediction_pb2.Tensor(
shape=data.shape, values=data.flatten()))
meta = prediction_pb2.Meta()
json_format.ParseDict({"tags": {"foo": "bar"}}, meta)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
channel = grpc.insecure_channel("0.0.0.0:5000")
stub = prediction_pb2_grpc.ModelStub(channel)
response = stub.Predict(request=request)
assert response.data.tensor.shape[0] == 1
assert response.data.tensor.shape[1] == 2
assert response.data.tensor.values[0] == 1
assert response.data.tensor.values[1] == 2
assert response.meta.tags["foo"].string_value == "bar"
def test_model_tftensor_ok():
user_object = UserObject()
seldon_metrics = SeldonMetrics()
app = get_rest_microservice(user_object, seldon_metrics)
client = app.test_client()
arr = np.array([1, 2])
datadef = prediction_pb2.DefaultData(tftensor=tf.make_tensor_proto(arr))
request = prediction_pb2.SeldonMessage(data=datadef)
jStr = json_format.MessageToJson(request)
rv = client.get("/predict?json=" + jStr)
j = json.loads(rv.data)
logging.info(j)
assert rv.status_code == 200
assert j["meta"]["tags"] == {"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 "tftensor" in j["data"]
tfp = TensorProto()
json_format.ParseDict(j["data"].get("tftensor"), tfp, ignore_unknown_fields=False)
arr2 = tf.make_ndarray(tfp)
assert np.array_equal(arr, arr2)
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_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_model_template_app_grpc_metrics(microservice):
data = np.array([[1, 2]])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=data.shape, values=data.flatten())
)
meta = prediction_pb2.Meta()
json_format.ParseDict(
{"metrics": [{"key": "mygauge", "type": "GAUGE", "value": 100}]}, meta
)
request = prediction_pb2.SeldonMessage(data=datadef, meta=meta)
channel = grpc.insecure_channel("0.0.0.0:5000")
stub = prediction_pb2_grpc.ModelStub(channel)
response = retry_method(stub.Predict, kwargs=dict(request=request))
assert response.data.tensor.shape[0] == 1
assert response.data.tensor.shape[1] == 2
assert response.data.tensor.values[0] == 1
assert response.data.tensor.values[1] == 2
assert response.meta.metrics[0].key == "mygauge"
assert response.meta.metrics[0].value == 100
def predict_raw(self, request):
log.debug("Predict raw")
request_data_type = request.WhichOneof("data_oneof")
default_data_type = request.data.WhichOneof("data_oneof")
log.debug(str(request_data_type), str(default_data_type))
if default_data_type == "tftensor" and self.grpc:
tfrequest = predict_pb2.PredictRequest()
tfrequest.model_spec.name = self.model_name
tfrequest.model_spec.signature_name = self.signature_name
tfrequest.inputs[self.model_input].CopyFrom(request.data.tftensor)
result = self.stub.Predict(tfrequest)
log.debug(result)
datadef = prediction_pb2.DefaultData(
tftensor=result.outputs[self.model_output])
return prediction_pb2.SeldonMessage(data=datadef)
elif request_data_type == "jsonData":
features = get_data_from_proto(request)
predictions = self.predict(features, features_names=[])
try:
sm = json_to_seldon_message({"jsonData": predictions})
except ParseError as e:
sm = prediction_pb2.SeldonMessage(strData=predictions)
return sm
else:
features = get_data_from_proto(request)
datadef = request.data
predictions = self.predict(features, datadef.names)
predictions = np.array(predictions)
if request_data_type is not "data":
default_data_type = "tensor"
class_names = []
data = array_to_grpc_datadef(predictions, class_names,
default_data_type)
return prediction_pb2.SeldonMessage(data=data)
def _predict_grpc_data(self, request, default_data_type):
tfrequest = predict_pb2.PredictRequest()
# handle input
if default_data_type == "tftensor":
# For GRPC case, if we have a TFTensor message we can pass it directly
tfrequest.inputs[self.model_input].CopyFrom(request.data.tftensor)
else:
data_arr = grpc_datadef_to_array(request.data)
tfrequest.inputs[self.model_input].CopyFrom(
tf.make_tensor_proto(data_arr.tolist(), shape=data_arr.shape)
)
# handle prediction
tfresponse = self._handle_grpc_prediction(tfrequest)
# handle result
datadef = prediction_pb2.DefaultData(
tftensor=tfresponse.outputs[self.model_output]
)
return prediction_pb2.SeldonMessage(data=datadef)
def transform_output_grpc(self, X):
arr = np.array([9, 9])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(2, 1), values=arr))
request = prediction_pb2.SeldonMessage(data=datadef)
return request
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
def route_grpc(self, request):
arr = np.array([1])
datadef = prediction_pb2.DefaultData(
tensor=prediction_pb2.Tensor(shape=(1, 1), values=arr))
request = prediction_pb2.SeldonMessage(data=datadef)
return request
