LocalAI/backend/python/transformers/test_transformers_server.py
Ettore Di Giacinto 887b3dff04
feat: cuda transformers (#1401)
* Use cuda in transformers if available

tensorflow probably needs a different check.

Signed-off-by: Erich Schubert <kno10@users.noreply.github.com>

* feat: expose CUDA at top level

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* tests: add to tests and create workflow for py extra backends

* doc: update note on how to use core images

---------

Signed-off-by: Erich Schubert <kno10@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Erich Schubert <kno10@users.noreply.github.com>
2023-12-08 15:45:04 +01:00

84 lines
2.8 KiB
Python

"""
A test script to test the gRPC service
"""
import unittest
import subprocess
import time
import backend_pb2
import backend_pb2_grpc
import grpc
class TestBackendServicer(unittest.TestCase):
"""
TestBackendServicer is the class that tests the gRPC service
"""
def setUp(self):
"""
This method sets up the gRPC service by starting the server
"""
self.service = subprocess.Popen(["python3", "transformers_server.py", "--addr", "localhost:50051"])
def tearDown(self) -> None:
"""
This method tears down the gRPC service by terminating the server
"""
self.service.terminate()
self.service.wait()
def test_server_startup(self):
"""
This method tests if the server starts up successfully
"""
time.sleep(10)
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.Health(backend_pb2.HealthMessage())
self.assertEqual(response.message, b'OK')
except Exception as err:
print(err)
self.fail("Server failed to start")
finally:
self.tearDown()
def test_load_model(self):
"""
This method tests if the model is loaded successfully
"""
time.sleep(10)
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-cased"))
self.assertTrue(response.success)
self.assertEqual(response.message, "Model loaded successfully")
except Exception as err:
print(err)
self.fail("LoadModel service failed")
finally:
self.tearDown()
def test_embedding(self):
"""
This method tests if the embeddings are generated successfully
"""
time.sleep(10)
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-cased"))
print(response.message)
self.assertTrue(response.success)
embedding_request = backend_pb2.PredictOptions(Embeddings="This is a test sentence.")
embedding_response = stub.Embedding(embedding_request)
self.assertIsNotNone(embedding_response.embeddings)
except Exception as err:
print(err)
self.fail("Embedding service failed")
finally:
self.tearDown()