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_feedback_custom():
user_object = UserObjectLowLevel()
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)
feedback = prediction_pb2.Feedback(request=request, reward=1.0)
resp = app.SendFeedback(feedback, None)
def json_to_feedback(message_json: Dict) -> prediction_pb2.Feedback:
"""
Parse a JSON message to a Feedback proto
Parameters
----------
message_json
Input json message
Returns
-------
A SeldonMessage
"""
message_proto = prediction_pb2.Feedback()
try:
json_format.ParseDict(message_json, message_proto)
return message_proto
except json_format.ParseError as pbExc:
raise SeldonMicroserviceException("Invalid JSON: " + str(pbExc))
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_model_template_app_grpc(microservice):
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 = 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
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 run_send_feedback(args):
contract = json.load(open(args.contract, 'r'))
contract = unfold_contract(contract)
feature_names = [feature["name"] for feature in contract["features"]]
response_names = [feature["name"] for feature in contract["targets"]]
REST_url = "http://" + args.host + ":" + str(args.port) + "/send-feedback"
for i in range(args.n_requests):
batch = generate_batch(contract, args.batch_size, 'features')
response = generate_batch(contract, args.batch_size, 'targets')
if args.prnt:
print('-' * 40)
print("SENDING NEW REQUEST:")
if not args.grpc and not args.fbs:
REST_request = gen_REST_request(batch,
features=feature_names,
tensor=args.tensor)
REST_response = gen_REST_request(response,
features=response_names,
tensor=args.tensor)
reward = 1.0
REST_feedback = {
"request": REST_request,
"response": REST_response,
"reward": reward
}
if args.prnt:
print(REST_feedback)
t1 = time()
response = requests.post(REST_url,
data={"json": json.dumps(REST_feedback)})
t2 = time()
if args.prnt:
print("Time " + str(t2 - t1))
print(response)
elif args.grpc:
GRPC_request = gen_GRPC_request(batch,
features=feature_names,
tensor=args.tensor)
GRPC_response = gen_GRPC_request(response,
features=response_names,
tensor=args.tensor)
reward = 1.0
GRPC_feedback = prediction_pb2.Feedback(request=GRPC_request,
response=GRPC_response,
reward=reward)
if args.prnt:
print(GRPC_feedback)
channel = grpc.insecure_channel('{}:{}'.format(
args.host, args.port))
stub = prediction_pb2_grpc.ModelStub(channel)
response = stub.SendFeedback(GRPC_feedback)
if args.prnt:
print("RECEIVED RESPONSE:")
print()
def run_send_feedback(args):
contract = json.load(open(args.contract, 'r'))
contract = unfold_contract(contract)
feature_names = [feature["name"] for feature in contract["features"]]
response_names = [feature["name"] for feature in contract["targets"]]
REST_url = "http://" + args.host + ":" + str(args.port) + "/send-feedback"
for i in range(args.n_requests):
batch = generate_batch(contract, args.batch_size, 'features')
response = generate_batch(contract, args.batch_size, 'targets')
if args.prnt:
print('-' * 40)
print("SENDING NEW REQUEST:")
if not args.grpc:
REST_request = gen_REST_request(batch,
features=feature_names,
tensor=args.tensor)
REST_response = gen_REST_request(response,
features=response_names,
tensor=args.tensor)
reward = 1.0
REST_feedback = {
"request": REST_request,
"response": REST_response,
"reward": reward
}
if args.prnt:
print(REST_feedback)
if args.oauth_key:
token = get_token(args)
headers = {'Authorization': 'Bearer ' + token}
response = requests.post("http://" + args.host + ":" +
str(args.port) + "/api/v0.1/feedback",
json=REST_feedback,
headers=headers)
else:
response = requests.post(
"http://" + args.host + ":" + str(args.port) +
args.ambassador_path + "/api/v0.1/feedback",
json=REST_feedback,
headers=headers)
if args.prnt:
print(response)
elif args.grpc:
GRPC_request = gen_GRPC_request(batch,
features=feature_names,
tensor=args.tensor)
GRPC_response = gen_GRPC_request(response,
features=response_names,
tensor=args.tensor)
reward = 1.0
GRPC_feedback = prediction_pb2.Feedback(request=GRPC_request,
response=GRPC_response,
reward=reward)
if args.prnt:
print(GRPC_feedback)
channel = grpc.insecure_channel('{}:{}'.format(
args.host, args.port))
stub = prediction_pb2_grpc.SeldonStub(channel)
if args.oauth_key:
token = get_token(args)
metadata = [('oauth_token', token)]
response = stub.SendFeedback(request=GRPC_feedback,
metadata=metadata)
else:
response = stub.SendFeedback(request=GRPC_feedback)
if args.prnt:
print("RECEIVED RESPONSE:")
print()