phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-29 03:14:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: OpenAI Responses API (#1989)

Browse source 
# 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>
This commit is contained in:
Ben Browning 2025-04-28 17:06:00 -04:00 • committed by GitHub
parent 79851d93aa
commit 8dfce2f596
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 1766 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

56
tests/verifications/openai_api/test_chat_completion.py
View file

@ -7,7 +7,6 @@
import base64
import copy
import json
import re
from pathlib import Path
from typing import Any
@ -16,7 +15,9 @@ from openai import APIError
from pydantic import BaseModel
from tests.verifications.openai_api.fixtures.fixtures import (
_load_all_verification_configs,
case_id_generator,
get_base_test_name,
should_skip_test,
)
from tests.verifications.openai_api.fixtures.load import load_test_cases
@ -25,57 +26,6 @@ chat_completion_test_cases = load_test_cases("chat_completion")
THIS_DIR = Path(__file__).parent
def case_id_generator(case):
"""Generate a test ID from the case's 'case_id' field, or use a default."""
case_id = case.get("case_id")
if isinstance(case_id, (str, int)):
return re.sub(r"\\W|^(?=\\d)", "_", str(case_id))
return None
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
def should_skip_test(verification_config, provider, model, test_name_base):
"""Check if a test should be skipped based on config exclusions."""
provider_config = verification_config.get("providers", {}).get(provider)
if not provider_config:
return False # No config for provider, don't skip
exclusions = provider_config.get("test_exclusions", {}).get(model, [])
return test_name_base in exclusions
# Helper to get the base test name from the request object
def get_base_test_name(request):
return request.node.originalname
@pytest.fixture
def multi_image_data():
files = [