forked from phoenix-oss/llama-stack-mirror
d9d271a684
# What does this PR do? This PR brings back the facility to not force registration of resources onto the user. This is not just annoying but actually not feasible sometimes. For example, you may have a Stack which boots up with private providers for inference for models A and B. There is no way for the user to actually know which model is being served by these providers now (to be able to register it.) How will this avoid the users needing to do registration? In a follow-up diff, I will make sure I update the sample run.yaml files so they list the models served by the distributions explicitly. So when users do `llama stack build --template <...>` and run it, their distributions come up with the right set of models they expect. For self-hosted distributions, it also allows us to have a place to explicit list the models that need to be served to make the "complete" stack (including safety, e.g.) ## Test Plan Started ollama locally with two lightweight models: Llama3.2-3B-Instruct and Llama-Guard-3-1B. Updated all the tests including agents. Here's the tests I ran so far: ```bash pytest -s -v -m "fireworks and llama_3b" test_text_inference.py::TestInference \ --env FIREWORKS_API_KEY=... pytest -s -v -m "ollama and llama_3b" test_text_inference.py::TestInference pytest -s -v -m ollama test_safety.py pytest -s -v -m faiss test_memory.py pytest -s -v -m ollama test_agents.py \ --inference-model=Llama3.2-3B-Instruct --safety-model=Llama-Guard-3-1B ``` Found a few bugs here and there pre-existing that these test runs fixed.
113 lines
3.2 KiB
Python
113 lines
3.2 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 ..conftest import get_provider_fixture_overrides
|
|
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from ..memory.fixtures import MEMORY_FIXTURES
|
|
from ..safety.fixtures import SAFETY_FIXTURES
|
|
from .fixtures import AGENTS_FIXTURES
|
|
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"inference": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
"agents": "meta_reference",
|
|
},
|
|
id="meta_reference",
|
|
marks=pytest.mark.meta_reference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
"agents": "meta_reference",
|
|
},
|
|
id="ollama",
|
|
marks=pytest.mark.ollama,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "together",
|
|
"safety": "llama_guard",
|
|
# make this work with Weaviate which is what the together distro supports
|
|
"memory": "faiss",
|
|
"agents": "meta_reference",
|
|
},
|
|
id="together",
|
|
marks=pytest.mark.together,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "remote",
|
|
"safety": "remote",
|
|
"memory": "remote",
|
|
"agents": "remote",
|
|
},
|
|
id="remote",
|
|
marks=pytest.mark.remote,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for mark in ["meta_reference", "ollama", "together", "remote"]:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{mark}: marks tests as {mark} specific",
|
|
)
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--inference-model",
|
|
action="store",
|
|
default="Llama3.1-8B-Instruct",
|
|
help="Specify the inference model to use for testing",
|
|
)
|
|
parser.addoption(
|
|
"--safety-model",
|
|
action="store",
|
|
default="Llama-Guard-3-8B",
|
|
help="Specify the safety model to use for testing",
|
|
)
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
safety_model = metafunc.config.getoption("--safety-model")
|
|
if "safety_model" in metafunc.fixturenames:
|
|
metafunc.parametrize(
|
|
"safety_model",
|
|
[pytest.param(safety_model, id="")],
|
|
indirect=True,
|
|
)
|
|
if "inference_model" in metafunc.fixturenames:
|
|
inference_model = metafunc.config.getoption("--inference-model")
|
|
models = list(set({inference_model, safety_model}))
|
|
|
|
metafunc.parametrize(
|
|
"inference_model",
|
|
[pytest.param(models, id="")],
|
|
indirect=True,
|
|
)
|
|
if "agents_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"inference": INFERENCE_FIXTURES,
|
|
"safety": SAFETY_FIXTURES,
|
|
"memory": MEMORY_FIXTURES,
|
|
"agents": AGENTS_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("agents_stack", combinations, indirect=True)
|