mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
8dfce2f596
# What does this PR do? This provides an initial [OpenAI Responses API](https://platform.openai.com/docs/api-reference/responses) implementation. The API is not yet complete, and this is more a proof-of-concept to show how we can store responses in our key-value stores and use them to support the Responses API concepts like `previous_response_id`. ## Test Plan I've added a new `tests/integration/openai_responses/test_openai_responses.py` as part of a test-driven development for this new API. I'm only testing this locally with the remote-vllm provider for now, but it should work with any of our inference providers since the only API it requires out of the inference provider is the `openai_chat_completion` endpoint. ``` VLLM_URL="http://localhost:8000/v1" \ INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack build --template remote-vllm --image-type venv --run ``` ``` LLAMA_STACK_CONFIG="http://localhost:8321" \ python -m pytest -v \ tests/integration/openai_responses/test_openai_responses.py \ --text-model "meta-llama/Llama-3.2-3B-Instruct" ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
35 lines
1.5 KiB
Python
35 lines
1.5 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.
|
|
|
|
from tests.verifications.openai_api.fixtures.fixtures import _load_all_verification_configs
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
"""Dynamically parametrize tests based on the selected provider and config."""
|
|
if "model" in metafunc.fixturenames:
|
|
provider = metafunc.config.getoption("provider")
|
|
if not provider:
|
|
print("Warning: --provider not specified. Skipping model parametrization.")
|
|
metafunc.parametrize("model", [])
|
|
return
|
|
|
|
try:
|
|
config_data = _load_all_verification_configs()
|
|
except (FileNotFoundError, IOError) as e:
|
|
print(f"ERROR loading verification configs: {e}")
|
|
config_data = {"providers": {}}
|
|
|
|
provider_config = config_data.get("providers", {}).get(provider)
|
|
if provider_config:
|
|
models = provider_config.get("models", [])
|
|
if models:
|
|
metafunc.parametrize("model", models)
|
|
else:
|
|
print(f"Warning: No models found for provider '{provider}' in config.")
|
|
metafunc.parametrize("model", []) # Parametrize empty if no models found
|
|
else:
|
|
print(f"Warning: Provider '{provider}' not found in config. No models parametrized.")
|
|
metafunc.parametrize("model", []) # Parametrize empty if provider not found
|