mirror of
https://github.com/mudler/LocalAI.git
synced 2024-06-07 19:40:48 +00:00
92cbc4d516
* Update huggingface.py Switch SentenceTransformer for AutoModel in order to set trust_remote_code needed to use the encode method with embeddings models like jinai-v2 Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu> * feat(transformers): split in separate backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
81 lines
2.7 KiB
Python
81 lines
2.7 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", "sentencetransformers.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(2)
|
|
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="bert-base-nli-mean-tokens"))
|
|
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
|
|
"""
|
|
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-nli-mean-tokens"))
|
|
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() |