forked from phoenix-oss/llama-stack-mirror
50cc165077
# What does this PR do?
- braintrust scoring provider requires OPENAI_API_KEY env variable to be
set
- move this to be able to be set as request headers (e.g. like together
/ fireworks api keys)
- fixes pytest with agents dependency
## Test Plan
**E2E**
```
llama stack run
```
```yaml
scoring:
- provider_id: braintrust-0
provider_type: inline::braintrust
config: {}
```
**Client**
```python
self.client = LlamaStackClient(
base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:5000"),
provider_data={
"openai_api_key": os.environ.get("OPENAI_API_KEY", ""),
},
)
```
- run `llama-stack-client eval run_scoring`
**Unit Test**
```
pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py
```
```
pytest -v -s -m braintrust_scoring_together_inference scoring/test_scoring.py --env OPENAI_API_KEY=$OPENAI_API_KEY
```
<img width="745" alt="image"
src="https://github.com/user-attachments/assets/68f5cdda-f6c8-496d-8b4f-1b3dabeca9c2">
## 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.
94 lines
2.6 KiB
Python
94 lines
2.6 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
|
|
import pytest_asyncio
|
|
|
|
from llama_stack.apis.models import ModelInput
|
|
|
|
from llama_stack.distribution.datatypes import Api, Provider
|
|
from llama_stack.providers.inline.scoring.braintrust import BraintrustScoringConfig
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
from ..conftest import ProviderFixture, remote_stack_fixture
|
|
from ..env import get_env_or_fail
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_remote() -> ProviderFixture:
|
|
return remote_stack_fixture()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_basic() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="basic",
|
|
provider_type="inline::basic",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_braintrust() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="braintrust",
|
|
provider_type="inline::braintrust",
|
|
config=BraintrustScoringConfig(
|
|
openai_api_key=get_env_or_fail("OPENAI_API_KEY"),
|
|
).model_dump(),
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_llm_as_judge() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="llm-as-judge",
|
|
provider_type="inline::llm-as-judge",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
SCORING_FIXTURES = ["basic", "remote", "braintrust", "llm_as_judge"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def scoring_stack(request, inference_model):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in ["datasetio", "scoring", "inference"]:
|
|
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
|
|
providers[key] = fixture.providers
|
|
if fixture.provider_data:
|
|
provider_data.update(fixture.provider_data)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[Api.scoring, Api.datasetio, Api.inference],
|
|
providers,
|
|
provider_data,
|
|
models=[
|
|
ModelInput(model_id=model)
|
|
for model in [
|
|
inference_model,
|
|
"Llama3.1-405B-Instruct",
|
|
"Llama3.1-8B-Instruct",
|
|
]
|
|
],
|
|
)
|
|
|
|
return test_stack.impls
|