forked from phoenix-oss/llama-stack-mirror
3c72c034e6
# 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.
121 lines
4.1 KiB
Python
121 lines
4.1 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 base64
|
|
import mimetypes
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from llama_stack.apis.common.content_types import URL
|
|
from llama_stack.apis.common.type_system import ChatCompletionInputType, StringType
|
|
from llama_stack.apis.datasets import Datasets
|
|
|
|
# How to run this test:
|
|
#
|
|
# pytest llama_stack/providers/tests/datasetio/test_datasetio.py
|
|
# -m "meta_reference"
|
|
# -v -s --tb=short --disable-warnings
|
|
|
|
|
|
def data_url_from_file(file_path: str) -> str:
|
|
if not os.path.exists(file_path):
|
|
raise FileNotFoundError(f"File not found: {file_path}")
|
|
|
|
with open(file_path, "rb") as file:
|
|
file_content = file.read()
|
|
|
|
base64_content = base64.b64encode(file_content).decode("utf-8")
|
|
mime_type, _ = mimetypes.guess_type(file_path)
|
|
|
|
data_url = f"data:{mime_type};base64,{base64_content}"
|
|
|
|
return data_url
|
|
|
|
|
|
async def register_dataset(
|
|
datasets_impl: Datasets, for_generation=False, dataset_id="test_dataset"
|
|
):
|
|
test_file = Path(os.path.abspath(__file__)).parent / "test_dataset.csv"
|
|
test_url = data_url_from_file(str(test_file))
|
|
|
|
if for_generation:
|
|
dataset_schema = {
|
|
"expected_answer": StringType(),
|
|
"input_query": StringType(),
|
|
"chat_completion_input": ChatCompletionInputType(),
|
|
}
|
|
else:
|
|
dataset_schema = {
|
|
"expected_answer": StringType(),
|
|
"input_query": StringType(),
|
|
"generated_answer": StringType(),
|
|
}
|
|
|
|
await datasets_impl.register_dataset(
|
|
dataset_id=dataset_id,
|
|
dataset_schema=dataset_schema,
|
|
url=URL(uri=test_url),
|
|
)
|
|
|
|
|
|
class TestDatasetIO:
|
|
@pytest.mark.asyncio
|
|
async def test_datasets_list(self, datasetio_stack):
|
|
# NOTE: this needs you to ensure that you are starting from a clean state
|
|
# but so far we don't have an unregister API unfortunately, so be careful
|
|
_, datasets_impl = datasetio_stack
|
|
response = await datasets_impl.list_datasets()
|
|
assert isinstance(response, list)
|
|
assert len(response) == 0
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_register_dataset(self, datasetio_stack):
|
|
_, datasets_impl = datasetio_stack
|
|
await register_dataset(datasets_impl)
|
|
response = await datasets_impl.list_datasets()
|
|
assert isinstance(response, list)
|
|
assert len(response) == 1
|
|
assert response[0].identifier == "test_dataset"
|
|
|
|
with pytest.raises(Exception) as exc_info:
|
|
# unregister a dataset that does not exist
|
|
await datasets_impl.unregister_dataset("test_dataset2")
|
|
|
|
await datasets_impl.unregister_dataset("test_dataset")
|
|
response = await datasets_impl.list_datasets()
|
|
assert isinstance(response, list)
|
|
assert len(response) == 0
|
|
|
|
with pytest.raises(Exception) as exc_info:
|
|
await datasets_impl.unregister_dataset("test_dataset")
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_rows_paginated(self, datasetio_stack):
|
|
datasetio_impl, datasets_impl = datasetio_stack
|
|
await register_dataset(datasets_impl)
|
|
response = await datasetio_impl.get_rows_paginated(
|
|
dataset_id="test_dataset",
|
|
rows_in_page=3,
|
|
)
|
|
assert isinstance(response.rows, list)
|
|
assert len(response.rows) == 3
|
|
assert response.next_page_token == "3"
|
|
|
|
provider = datasetio_impl.routing_table.get_provider_impl("test_dataset")
|
|
if provider.__provider_spec__.provider_type == "remote":
|
|
pytest.skip("remote provider doesn't support get_rows_paginated")
|
|
|
|
# iterate over all rows
|
|
response = await datasetio_impl.get_rows_paginated(
|
|
dataset_id="test_dataset",
|
|
rows_in_page=2,
|
|
page_token=response.next_page_token,
|
|
)
|
|
assert isinstance(response.rows, list)
|
|
assert len(response.rows) == 2
|
|
assert response.next_page_token == "5"
|