mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
78e2bfbe7a
# What does this PR do? **Why** - Clean up examples which we will not maintain; reduce the surface area to the minimal showcases **What** - Delete `client.py` in /apis/* - Move all scripts to unit tests - SDK sync in the future will just require running pytests **Side notes** - `bwrap` not available on Mac so code_interpreter will not work ## Test Plan ``` LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk ``` <img width="725" alt="image" src="https://github.com/user-attachments/assets/36bfe537-628d-43c3-8479-dcfcfe2e4035" /> ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
74 lines
2.2 KiB
Python
74 lines
2.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
from llama_stack_client.lib.inference.event_logger import EventLogger
|
|
|
|
|
|
def test_text_chat_completion(llama_stack_client):
|
|
# non-streaming
|
|
available_models = [
|
|
model.identifier
|
|
for model in llama_stack_client.models.list()
|
|
if model.identifier.startswith("meta-llama")
|
|
]
|
|
assert len(available_models) > 0
|
|
model_id = available_models[0]
|
|
response = llama_stack_client.inference.chat_completion(
|
|
model_id=model_id,
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "Hello, world!",
|
|
}
|
|
],
|
|
stream=False,
|
|
)
|
|
assert len(response.completion_message.content) > 0
|
|
|
|
# streaming
|
|
response = llama_stack_client.inference.chat_completion(
|
|
model_id=model_id,
|
|
messages=[{"role": "user", "content": "Hello, world!"}],
|
|
stream=True,
|
|
)
|
|
logs = [str(log.content) for log in EventLogger().log(response) if log is not None]
|
|
assert len(logs) > 0
|
|
assert "Assistant> " in logs[0]
|
|
|
|
|
|
def test_image_chat_completion(llama_stack_client):
|
|
available_models = [
|
|
model.identifier
|
|
for model in llama_stack_client.models.list()
|
|
if "vision" in model.identifier.lower()
|
|
]
|
|
if len(available_models) == 0:
|
|
pytest.skip("No vision models available")
|
|
|
|
model_id = available_models[0]
|
|
# non-streaming
|
|
message = {
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"image": {
|
|
"uri": "https://www.healthypawspetinsurance.com/Images/V3/DogAndPuppyInsurance/Dog_CTA_Desktop_HeroImage.jpg"
|
|
}
|
|
},
|
|
"Describe what is in this image.",
|
|
],
|
|
}
|
|
response = llama_stack_client.inference.chat_completion(
|
|
model_id=model_id,
|
|
messages=[message],
|
|
stream=False,
|
|
)
|
|
assert len(response.completion_message.content) > 0
|
|
assert (
|
|
"dog" in response.completion_message.content.lower()
|
|
or "puppy" in response.completion_message.content.lower()
|
|
)
|