LocalAI/backend/python/vllm/test.py
Ettore Di Giacinto 68fc014c6d
feat(vllm): add support for embeddings (#3440)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-09-02 21:44:32 +02:00

99 lines
3.6 KiB
Python

import unittest
import subprocess
import time
import backend_pb2
import backend_pb2_grpc
import grpc
import unittest
import subprocess
import time
import grpc
import backend_pb2_grpc
import backend_pb2
class TestBackendServicer(unittest.TestCase):
"""
TestBackendServicer is the class that tests the gRPC service.
This class contains methods to test the startup and shutdown of the gRPC service.
"""
def setUp(self):
self.service = subprocess.Popen(["python", "backend.py", "--addr", "localhost:50051"])
time.sleep(10)
def tearDown(self) -> None:
self.service.terminate()
self.service.wait()
def test_server_startup(self):
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
"""
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.LoadModel(backend_pb2.ModelOptions(Model="facebook/opt-125m"))
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_text(self):
"""
This method tests if the embeddings are generated successfully
"""
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.LoadModel(backend_pb2.ModelOptions(Model="facebook/opt-125m"))
self.assertTrue(response.success)
req = backend_pb2.PredictOptions(Prompt="The capital of France is")
resp = stub.Predict(req)
self.assertIsNotNone(resp.message)
except Exception as err:
print(err)
self.fail("text service failed")
finally:
self.tearDown()
def test_embedding(self):
"""
This method tests if the embeddings are generated successfully
"""
try:
self.setUp()
with grpc.insecure_channel("localhost:50051") as channel:
stub = backend_pb2_grpc.BackendStub(channel)
response = stub.LoadModel(backend_pb2.ModelOptions(Model="intfloat/e5-mistral-7b-instruct"))
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)
# assert that is a list of floats
self.assertIsInstance(embedding_response.embeddings, list)
# assert that the list is not empty
self.assertTrue(len(embedding_response.embeddings) > 0)
except Exception as err:
print(err)
self.fail("Embedding service failed")
finally:
self.tearDown()