phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Kill "remote" providers and fix testing with a remote stack properly (#435)

Browse source 
# What does this PR do?

This PR kills the notion of "pure passthrough" remote providers. You
cannot specify a single provider you must specify a whole distribution
(stack) as remote.

This PR also significantly fixes / upgrades testing infrastructure so
you can now test against a remotely hosted stack server by just doing

```bash
pytest -s -v -m remote  test_agents.py \
  --inference-model=Llama3.1-8B-Instruct --safety-shield=Llama-Guard-3-1B \
  --env REMOTE_STACK_URL=http://localhost:5001
```

Also fixed `test_agents_persistence.py` (which was broken) and killed
some deprecated testing functions.

## Test Plan

All the tests.
This commit is contained in:
Ashwin Bharambe 2024-11-12 21:51:29 -08:00 • committed by GitHub
parent 59a65e34d3
commit 12947ac19e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 406 additions and 519 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/tests/inference/fixtures.py
View file

@ -21,7 +21,7 @@ from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
from llama_stack.providers.remote.inference.together import TogetherImplConfig
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2
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
@ -182,15 +182,11 @@ INFERENCE_FIXTURES = [
async def inference_stack(request, inference_model):
fixture_name = request.param
inference_fixture = request.getfixturevalue(f"inference_{fixture_name}")
impls = await resolve_impls_for_test_v2(
test_stack = await construct_stack_for_test(
[Api.inference],
{"inference": inference_fixture.providers},
inference_fixture.provider_data,
models=[
ModelInput(
model_id=inference_model,
)
],
models=[ModelInput(model_id=inference_model)],
)
return (impls[Api.inference], impls[Api.models])
return test_stack.impls[Api.inference], test_stack.impls[Api.models]