[Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models (#5649)
Co-authored-by: constellate <constellate@1-ai-appserver-staging.codereach.com> Co-authored-by: Kyle Mistele <kyle@constellate.ai>
This commit is contained in:
co-authored by
constellate
Kyle Mistele
parent
561d6f8077
commit
e02ce498be
@@ -0,0 +1,32 @@
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
from huggingface_hub import snapshot_download
|
||||
|
||||
from tests.utils import RemoteOpenAIServer
|
||||
|
||||
from .utils import ARGS, CONFIGS, ServerConfig
|
||||
|
||||
|
||||
# for each server config, download the model and return the config
|
||||
@pytest.fixture(scope="session", params=CONFIGS.keys())
|
||||
def server_config(request):
|
||||
config = CONFIGS[request.param]
|
||||
# download model and tokenizer using transformers
|
||||
snapshot_download(config["model"])
|
||||
yield CONFIGS[request.param]
|
||||
|
||||
|
||||
# run this for each server config
|
||||
@pytest.fixture(scope="session")
|
||||
def server(request, server_config: ServerConfig):
|
||||
model = server_config["model"]
|
||||
args_for_model = server_config["arguments"]
|
||||
with RemoteOpenAIServer(model, ARGS + args_for_model,
|
||||
max_wait_seconds=480) as server:
|
||||
yield server
|
||||
|
||||
|
||||
@pytest_asyncio.fixture
|
||||
async def client(server: RemoteOpenAIServer):
|
||||
async with server.get_async_client() as async_client:
|
||||
yield async_client
|
||||
Reference in New Issue
Block a user