phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

Browse source 
With https://github.com/meta-llama/llama-stack-client-python/pull/226,
now we have llama-stack-client be able to used as a substitute for
OpenAI client (duck-typed) so you don't need to change downstream
library code.

<img width="1399" alt="image"
src="https://github.com/user-attachments/assets/abab6bfd-e6ff-4a7d-a965-fd93e3c105d7"
/>
This commit is contained in:
Ashwin Bharambe 2025-04-25 12:23:33 -07:00 • committed by GitHub
parent 0e4307de0f
commit 4fb583b407
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 20 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

32
tests/integration/inference/test_openai_completion.py
View file

@ -75,19 +75,24 @@ def openai_client(client_with_models):
return OpenAI(base_url=base_url, api_key="bar") 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( @pytest.mark.parametrize(
"test_case", "test_case",
[ [
"inference:completion:sanity", "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) skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
tc = TestCase(test_case) tc = TestCase(test_case)
# ollama needs more verbose prompting for some reason here... # ollama needs more verbose prompting for some reason here...
prompt = "Respond to this question and explain your answer. " + tc["content"] 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, model=text_model_id,
prompt=prompt, prompt=prompt,
stream=False, stream=False,
@ -103,13 +108,13 @@ def test_openai_completion_non_streaming(openai_client, client_with_models, text
"inference:completion:sanity", "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) skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
tc = TestCase(test_case) tc = TestCase(test_case)
# ollama needs more verbose prompting for some reason here... # ollama needs more verbose prompting for some reason here...
prompt = "Respond to this question and explain your answer. " + tc["content"] 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, model=text_model_id,
prompt=prompt, prompt=prompt,
stream=True, stream=True,
@ -127,11 +132,11 @@ def test_openai_completion_streaming(openai_client, client_with_models, text_mod
0, 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) skip_if_provider_isnt_vllm(client_with_models, text_model_id)
prompt = "Hello, world!" prompt = "Hello, world!"
response = openai_client.completions.create( response = llama_stack_client.completions.create(
model=text_model_id, model=text_model_id,
prompt=prompt, prompt=prompt,
stream=False, stream=False,
@ -144,11 +149,11 @@ def test_openai_completion_prompt_logprobs(openai_client, client_with_models, te
assert len(choice.prompt_logprobs) > 0 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) skip_if_provider_isnt_vllm(client_with_models, text_model_id)
prompt = "I am feeling really sad today." prompt = "I am feeling really sad today."
response = openai_client.completions.create( response = llama_stack_client.completions.create(
model=text_model_id, model=text_model_id,
prompt=prompt, prompt=prompt,
stream=False, stream=False,
@ -161,6 +166,9 @@ def test_openai_completion_guided_choice(openai_client, client_with_models, text
assert choice.text in ["joy", "sadness"] assert choice.text in ["joy", "sadness"]
# Run the chat-completion tests with both the OpenAI client and the LlamaStack client
@pytest.mark.parametrize( @pytest.mark.parametrize(
"test_case", "test_case",
[ [
@ -168,13 +176,13 @@ def test_openai_completion_guided_choice(openai_client, client_with_models, text
"inference:chat_completion:non_streaming_02", "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) skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
tc = TestCase(test_case) tc = TestCase(test_case)
question = tc["question"] question = tc["question"]
expected = tc["expected"] expected = tc["expected"]
response = openai_client.chat.completions.create( response = compat_client.chat.completions.create(
model=text_model_id, model=text_model_id,
messages=[ messages=[
{ {
@ -196,13 +204,13 @@ def test_openai_chat_completion_non_streaming(openai_client, client_with_models,
"inference:chat_completion:streaming_02", "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) skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
tc = TestCase(test_case) tc = TestCase(test_case)
question = tc["question"] question = tc["question"]
expected = tc["expected"] expected = tc["expected"]
response = openai_client.chat.completions.create( response = compat_client.chat.completions.create(
model=text_model_id, model=text_model_id,
messages=[{"role": "user", "content": question}], messages=[{"role": "user", "content": question}],
stream=True, stream=True,