Skip to content

fix: check that llama stack client plain can be used as a subst for OpenAI client #2032

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ashwinb merged 1 commit into from
Apr 25, 2025
Merged

fix: check that llama stack client plain can be used as a subst for OpenAI client #2032

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 20 additions & 12 deletions tests/integration/inference/test_openai_completion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,19 +75,24 @@ def openai_client(client_with_models):
return OpenAI(base_url=base_url, api_key="bar")


@pytest.fixture(params=["openai_client", "llama_stack_client"])
def compat_client(request):
return request.getfixturevalue(request.param)


@pytest.mark.parametrize(
"test_case",
[
"inference:completion:sanity",
],
)
def test_openai_completion_non_streaming(openai_client, client_with_models, text_model_id, test_case):
def test_openai_completion_non_streaming(llama_stack_client, client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
tc = TestCase(test_case)

# ollama needs more verbose prompting for some reason here...
prompt = "Respond to this question and explain your answer. " + tc["content"]
response = openai_client.completions.create(
response = llama_stack_client.completions.create(
model=text_model_id,
prompt=prompt,
stream=False,
Expand All @@ -103,13 +108,13 @@ def test_openai_completion_non_streaming(openai_client, client_with_models, text
"inference:completion:sanity",
],
)
def test_openai_completion_streaming(openai_client, client_with_models, text_model_id, test_case):
def test_openai_completion_streaming(llama_stack_client, client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
tc = TestCase(test_case)

# ollama needs more verbose prompting for some reason here...
prompt = "Respond to this question and explain your answer. " + tc["content"]
response = openai_client.completions.create(
response = llama_stack_client.completions.create(
model=text_model_id,
prompt=prompt,
stream=True,
Expand All @@ -127,11 +132,11 @@ def test_openai_completion_streaming(openai_client, client_with_models, text_mod
0,
],
)
def test_openai_completion_prompt_logprobs(openai_client, client_with_models, text_model_id, prompt_logprobs):
def test_openai_completion_prompt_logprobs(llama_stack_client, client_with_models, text_model_id, prompt_logprobs):
skip_if_provider_isnt_vllm(client_with_models, text_model_id)

prompt = "Hello, world!"
response = openai_client.completions.create(
response = llama_stack_client.completions.create(
model=text_model_id,
prompt=prompt,
stream=False,
Expand All @@ -144,11 +149,11 @@ def test_openai_completion_prompt_logprobs(openai_client, client_with_models, te
assert len(choice.prompt_logprobs) > 0


def test_openai_completion_guided_choice(openai_client, client_with_models, text_model_id):
def test_openai_completion_guided_choice(llama_stack_client, client_with_models, text_model_id):
skip_if_provider_isnt_vllm(client_with_models, text_model_id)

prompt = "I am feeling really sad today."
response = openai_client.completions.create(
response = llama_stack_client.completions.create(
model=text_model_id,
prompt=prompt,
stream=False,
Expand All @@ -161,20 +166,23 @@ def test_openai_completion_guided_choice(openai_client, client_with_models, text
assert choice.text in ["joy", "sadness"]


# Run the chat-completion tests with both the OpenAI client and the LlamaStack client


@pytest.mark.parametrize(
"test_case",
[
"inference:chat_completion:non_streaming_01",
"inference:chat_completion:non_streaming_02",
],
)
def test_openai_chat_completion_non_streaming(openai_client, client_with_models, text_model_id, test_case):
def test_openai_chat_completion_non_streaming(compat_client, client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
tc = TestCase(test_case)
question = tc["question"]
expected = tc["expected"]

response = openai_client.chat.completions.create(
response = compat_client.chat.completions.create(
model=text_model_id,
messages=[
{
Expand All @@ -196,13 +204,13 @@ def test_openai_chat_completion_non_streaming(openai_client, client_with_models,
"inference:chat_completion:streaming_02",
],
)
def test_openai_chat_completion_streaming(openai_client, client_with_models, text_model_id, test_case):
def test_openai_chat_completion_streaming(compat_client, client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
tc = TestCase(test_case)
question = tc["question"]
expected = tc["expected"]

response = openai_client.chat.completions.create(
response = compat_client.chat.completions.create(
model=text_model_id,
messages=[{"role": "user", "content": question}],
stream=True,
Expand Down