mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
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.
101 lines
3.2 KiB
Python
101 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.
|
|
|
|
from typing import Any, Dict, List, Literal, Optional, Protocol, Union
|
|
|
|
from llama_models.llama3.api.datatypes import BaseModel, Field
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from typing_extensions import Annotated
|
|
|
|
from llama_stack.apis.agents import AgentConfig
|
|
from llama_stack.apis.common.job_types import Job, JobStatus
|
|
from llama_stack.apis.inference import SamplingParams, SystemMessage
|
|
from llama_stack.apis.scoring import ScoringResult
|
|
from llama_stack.apis.scoring_functions import ScoringFnParams
|
|
|
|
|
|
@json_schema_type
|
|
class ModelCandidate(BaseModel):
|
|
type: Literal["model"] = "model"
|
|
model: str
|
|
sampling_params: SamplingParams
|
|
system_message: Optional[SystemMessage] = None
|
|
|
|
|
|
@json_schema_type
|
|
class AgentCandidate(BaseModel):
|
|
type: Literal["agent"] = "agent"
|
|
config: AgentConfig
|
|
|
|
|
|
EvalCandidate = Annotated[
|
|
Union[ModelCandidate, AgentCandidate], Field(discriminator="type")
|
|
]
|
|
|
|
|
|
@json_schema_type
|
|
class BenchmarkEvalTaskConfig(BaseModel):
|
|
type: Literal["benchmark"] = "benchmark"
|
|
eval_candidate: EvalCandidate
|
|
num_examples: Optional[int] = Field(
|
|
description="Number of examples to evaluate (useful for testing), if not provided, all examples in the dataset will be evaluated",
|
|
default=None,
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class AppEvalTaskConfig(BaseModel):
|
|
type: Literal["app"] = "app"
|
|
eval_candidate: EvalCandidate
|
|
scoring_params: Dict[str, ScoringFnParams] = Field(
|
|
description="Map between scoring function id and parameters for each scoring function you want to run",
|
|
default_factory=dict,
|
|
)
|
|
num_examples: Optional[int] = Field(
|
|
description="Number of examples to evaluate (useful for testing), if not provided, all examples in the dataset will be evaluated",
|
|
default=None,
|
|
)
|
|
# we could optinally add any specific dataset config here
|
|
|
|
|
|
EvalTaskConfig = Annotated[
|
|
Union[BenchmarkEvalTaskConfig, AppEvalTaskConfig], Field(discriminator="type")
|
|
]
|
|
|
|
|
|
@json_schema_type
|
|
class EvaluateResponse(BaseModel):
|
|
generations: List[Dict[str, Any]]
|
|
# each key in the dict is a scoring function name
|
|
scores: Dict[str, ScoringResult]
|
|
|
|
|
|
class Eval(Protocol):
|
|
@webmethod(route="/eval/run-eval", method="POST")
|
|
async def run_eval(
|
|
self,
|
|
task_id: str,
|
|
task_config: EvalTaskConfig,
|
|
) -> Job: ...
|
|
|
|
@webmethod(route="/eval/evaluate-rows", method="POST")
|
|
async def evaluate_rows(
|
|
self,
|
|
task_id: str,
|
|
input_rows: List[Dict[str, Any]],
|
|
scoring_functions: List[str],
|
|
task_config: EvalTaskConfig,
|
|
) -> EvaluateResponse: ...
|
|
|
|
@webmethod(route="/eval/job/status", method="GET")
|
|
async def job_status(self, task_id: str, job_id: str) -> Optional[JobStatus]: ...
|
|
|
|
@webmethod(route="/eval/job/cancel", method="POST")
|
|
async def job_cancel(self, task_id: str, job_id: str) -> None: ...
|
|
|
|
@webmethod(route="/eval/job/result", method="GET")
|
|
async def job_result(self, task_id: str, job_id: str) -> EvaluateResponse: ...
|