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.
99 lines
3.1 KiB
Python
99 lines
3.1 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 ..agents.fixtures import AGENTS_FIXTURES
|
|
|
|
from ..conftest import get_provider_fixture_overrides
|
|
|
|
from ..datasetio.fixtures import DATASETIO_FIXTURES
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from ..memory.fixtures import MEMORY_FIXTURES
|
|
from ..safety.fixtures import SAFETY_FIXTURES
|
|
from ..scoring.fixtures import SCORING_FIXTURES
|
|
from .fixtures import EVAL_FIXTURES
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "localfs",
|
|
"inference": "fireworks",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
},
|
|
id="meta_reference_eval_fireworks_inference",
|
|
marks=pytest.mark.meta_reference_eval_fireworks_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "localfs",
|
|
"inference": "together",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
},
|
|
id="meta_reference_eval_together_inference",
|
|
marks=pytest.mark.meta_reference_eval_together_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "huggingface",
|
|
"inference": "together",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
},
|
|
id="meta_reference_eval_together_inference_huggingface_datasetio",
|
|
marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for fixture_name in [
|
|
"meta_reference_eval_fireworks_inference",
|
|
"meta_reference_eval_together_inference",
|
|
"meta_reference_eval_together_inference_huggingface_datasetio",
|
|
]:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{fixture_name}: marks tests as {fixture_name} specific",
|
|
)
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--inference-model",
|
|
action="store",
|
|
default="meta-llama/Llama-3.2-3B-Instruct",
|
|
help="Specify the inference model to use for testing",
|
|
)
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
if "eval_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"eval": EVAL_FIXTURES,
|
|
"scoring": SCORING_FIXTURES,
|
|
"datasetio": DATASETIO_FIXTURES,
|
|
"inference": INFERENCE_FIXTURES,
|
|
"agents": AGENTS_FIXTURES,
|
|
"safety": SAFETY_FIXTURES,
|
|
"memory": MEMORY_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("eval_stack", combinations, indirect=True)
|