forked from phoenix-oss/llama-stack-mirror
# What does this PR do? - as title, cleaning up `import *`'s - upgrade tests to make them more robust to bad model outputs - remove import *'s in llama_stack/apis/* (skip __init__ modules) <img width="465" alt="image" src="https://github.com/user-attachments/assets/d8339c13-3b40-4ba5-9c53-0d2329726ee2" /> - run `sh run_openapi_generator.sh`, no types gets affected ## Test Plan ### Providers Tests **agents** ``` pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8 ``` **inference** ```bash # meta-reference torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py # together pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.2-11B-Vision-Instruct" ./llama_stack/providers/tests/inference/test_vision_inference.py pytest ./llama_stack/providers/tests/inference/test_prompt_adapter.py ``` **safety** ``` pytest -v -s llama_stack/providers/tests/safety/test_safety.py -m together --safety-shield meta-llama/Llama-Guard-3-8B ``` **memory** ``` pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "sentence_transformers" --env EMBEDDING_DIMENSION=384 ``` **scoring** ``` pytest -v -s -m llm_as_judge_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py ``` **datasetio** ``` pytest -v -s -m localfs llama_stack/providers/tests/datasetio/test_datasetio.py pytest -v -s -m huggingface llama_stack/providers/tests/datasetio/test_datasetio.py ``` **eval** ``` pytest -v -s -m meta_reference_eval_together_inference llama_stack/providers/tests/eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py ``` ### Client-SDK Tests ``` LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v ./tests/client-sdk ``` ### llama-stack-apps ``` PORT=5000 LOCALHOST=localhost python -m examples.agents.hello $LOCALHOST $PORT python -m examples.agents.inflation $LOCALHOST $PORT python -m examples.agents.podcast_transcript $LOCALHOST $PORT python -m examples.agents.rag_as_attachments $LOCALHOST $PORT python -m examples.agents.rag_with_memory_bank $LOCALHOST $PORT python -m examples.safety.llama_guard_demo_mm $LOCALHOST $PORT python -m examples.agents.e2e_loop_with_custom_tools $LOCALHOST $PORT # Vision model python -m examples.interior_design_assistant.app python -m examples.agent_store.app $LOCALHOST $PORT ``` ### CLI ``` which llama llama model prompt-format -m Llama3.2-11B-Vision-Instruct llama model list llama stack list-apis llama stack list-providers inference llama stack build --template ollama --image-type conda ``` ### Distributions Tests **ollama** ``` llama stack build --template ollama --image-type conda ollama run llama3.2:1b-instruct-fp16 llama stack run ./llama_stack/templates/ollama/run.yaml --env INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct ``` **fireworks** ``` llama stack build --template fireworks --image-type conda llama stack run ./llama_stack/templates/fireworks/run.yaml ``` **together** ``` llama stack build --template together --image-type conda llama stack run ./llama_stack/templates/together/run.yaml ``` **tgi** ``` llama stack run ./llama_stack/templates/tgi/run.yaml --env TGI_URL=http://0.0.0.0:5009 --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct ``` ## Sources Please link relevant resources if necessary. ## 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.
101 lines
3.7 KiB
Python
101 lines
3.7 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 json
|
|
import tempfile
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.datasets import DatasetInput
|
|
from llama_stack.apis.eval_tasks import EvalTaskInput
|
|
from llama_stack.apis.memory_banks import MemoryBankInput
|
|
from llama_stack.apis.models import ModelInput
|
|
from llama_stack.apis.scoring_functions import ScoringFnInput
|
|
from llama_stack.apis.shields import ShieldInput
|
|
|
|
from llama_stack.distribution.build import print_pip_install_help
|
|
from llama_stack.distribution.configure import parse_and_maybe_upgrade_config
|
|
from llama_stack.distribution.datatypes import Provider, StackRunConfig
|
|
from llama_stack.distribution.distribution import get_provider_registry
|
|
from llama_stack.distribution.request_headers import set_request_provider_data
|
|
from llama_stack.distribution.resolver import resolve_remote_stack_impls
|
|
from llama_stack.distribution.stack import construct_stack
|
|
from llama_stack.providers.datatypes import Api, RemoteProviderConfig
|
|
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|
|
|
|
|
class TestStack(BaseModel):
|
|
impls: Dict[Api, Any]
|
|
run_config: StackRunConfig
|
|
|
|
|
|
async def construct_stack_for_test(
|
|
apis: List[Api],
|
|
providers: Dict[str, List[Provider]],
|
|
provider_data: Optional[Dict[str, Any]] = None,
|
|
models: Optional[List[ModelInput]] = None,
|
|
shields: Optional[List[ShieldInput]] = None,
|
|
memory_banks: Optional[List[MemoryBankInput]] = None,
|
|
datasets: Optional[List[DatasetInput]] = None,
|
|
scoring_fns: Optional[List[ScoringFnInput]] = None,
|
|
eval_tasks: Optional[List[EvalTaskInput]] = None,
|
|
) -> TestStack:
|
|
sqlite_file = tempfile.NamedTemporaryFile(delete=False, suffix=".db")
|
|
run_config = dict(
|
|
image_name="test-fixture",
|
|
apis=apis,
|
|
providers=providers,
|
|
metadata_store=SqliteKVStoreConfig(db_path=sqlite_file.name),
|
|
models=models or [],
|
|
shields=shields or [],
|
|
memory_banks=memory_banks or [],
|
|
datasets=datasets or [],
|
|
scoring_fns=scoring_fns or [],
|
|
eval_tasks=eval_tasks or [],
|
|
)
|
|
run_config = parse_and_maybe_upgrade_config(run_config)
|
|
try:
|
|
remote_config = remote_provider_config(run_config)
|
|
if not remote_config:
|
|
# TODO: add to provider registry by creating interesting mocks or fakes
|
|
impls = await construct_stack(run_config, get_provider_registry())
|
|
else:
|
|
# we don't register resources for a remote stack as part of the fixture setup
|
|
# because the stack is already "up". if a test needs to register resources, it
|
|
# can do so manually always.
|
|
|
|
impls = await resolve_remote_stack_impls(remote_config, run_config.apis)
|
|
|
|
test_stack = TestStack(impls=impls, run_config=run_config)
|
|
except ModuleNotFoundError as e:
|
|
print_pip_install_help(providers)
|
|
raise e
|
|
|
|
if provider_data:
|
|
set_request_provider_data(
|
|
{"X-LlamaStack-ProviderData": json.dumps(provider_data)}
|
|
)
|
|
|
|
return test_stack
|
|
|
|
|
|
def remote_provider_config(
|
|
run_config: StackRunConfig,
|
|
) -> Optional[RemoteProviderConfig]:
|
|
remote_config = None
|
|
has_non_remote = False
|
|
for api_providers in run_config.providers.values():
|
|
for provider in api_providers:
|
|
if provider.provider_type == "test::remote":
|
|
remote_config = RemoteProviderConfig(**provider.config)
|
|
else:
|
|
has_non_remote = True
|
|
|
|
if remote_config:
|
|
assert not has_non_remote, "Remote stack cannot have non-remote providers"
|
|
|
|
return remote_config
|