forked from phoenix-oss/llama-stack-mirror
[remove import *] clean up import *'s (#689)
# 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.
This commit is contained in:
Xi Yan
GitHub
parent
70db039ff4
commit
3c72c034e6
99 changed files with 907 additions and 359 deletions
|
|
@ -6,21 +6,22 @@
|
|||
|
||||
import logging
|
||||
from enum import Enum
|
||||
from typing import List
|
||||
|
||||
from pathlib import Path
|
||||
from typing import Dict, List
|
||||
|
||||
import pkg_resources
|
||||
from pydantic import BaseModel
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.utils.exec import run_with_pty
|
||||
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
from pathlib import Path
|
||||
from llama_stack.distribution.datatypes import BuildConfig, Provider
|
||||
|
||||
from llama_stack.distribution.distribution import get_provider_registry
|
||||
|
||||
from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
|
||||
|
||||
from llama_stack.distribution.utils.exec import run_with_pty
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
|
|
|||
|
|
@ -6,10 +6,14 @@
|
|||
import logging
|
||||
import textwrap
|
||||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
from typing import Any, Dict
|
||||
|
||||
from llama_stack.distribution.datatypes import (
|
||||
DistributionSpec,
|
||||
LLAMA_STACK_RUN_CONFIG_VERSION,
|
||||
Provider,
|
||||
StackRunConfig,
|
||||
)
|
||||
from llama_stack.distribution.distribution import (
|
||||
builtin_automatically_routed_apis,
|
||||
get_provider_registry,
|
||||
|
|
@ -17,10 +21,7 @@ from llama_stack.distribution.distribution import (
|
|||
from llama_stack.distribution.utils.dynamic import instantiate_class_type
|
||||
from llama_stack.distribution.utils.prompt_for_config import prompt_for_config
|
||||
|
||||
|
||||
from llama_stack.apis.models import * # noqa: F403
|
||||
from llama_stack.apis.shields import * # noqa: F403
|
||||
from llama_stack.apis.memory_banks import * # noqa: F403
|
||||
from llama_stack.providers.datatypes import Api, ProviderSpec
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
|
|||
|
|
@ -4,24 +4,24 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import Dict, List, Optional, Union
|
||||
from typing import Annotated, Any, Dict, List, Optional, Union
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.datasetio import DatasetIO
|
||||
from llama_stack.apis.datasets import * # noqa: F403
|
||||
from llama_stack.apis.datasets import Dataset, DatasetInput
|
||||
from llama_stack.apis.eval import Eval
|
||||
from llama_stack.apis.eval_tasks import EvalTaskInput
|
||||
from llama_stack.apis.eval_tasks import EvalTask, EvalTaskInput
|
||||
from llama_stack.apis.inference import Inference
|
||||
from llama_stack.apis.memory import Memory
|
||||
from llama_stack.apis.memory_banks import * # noqa: F403
|
||||
from llama_stack.apis.models import * # noqa: F403
|
||||
from llama_stack.apis.memory_banks import MemoryBank, MemoryBankInput
|
||||
from llama_stack.apis.models import Model, ModelInput
|
||||
from llama_stack.apis.safety import Safety
|
||||
from llama_stack.apis.scoring import Scoring
|
||||
from llama_stack.apis.scoring_functions import * # noqa: F403
|
||||
from llama_stack.apis.shields import * # noqa: F403
|
||||
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnInput
|
||||
from llama_stack.apis.shields import Shield, ShieldInput
|
||||
from llama_stack.apis.tools import Tool, ToolGroup, ToolRuntime
|
||||
from llama_stack.providers.datatypes import * # noqa: F403
|
||||
from llama_stack.providers.datatypes import Api, ProviderSpec
|
||||
from llama_stack.providers.utils.kvstore.config import KVStoreConfig
|
||||
|
||||
LLAMA_STACK_BUILD_CONFIG_VERSION = "2"
|
||||
|
|
|
|||
|
|
@ -5,12 +5,12 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
from typing import Dict, List
|
||||
from llama_stack.apis.inspect import * # noqa: F403
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from llama_stack.apis.inspect import HealthInfo, Inspect, ProviderInfo, RouteInfo
|
||||
from llama_stack.distribution.datatypes import StackRunConfig
|
||||
from llama_stack.distribution.server.endpoints import get_all_api_endpoints
|
||||
from llama_stack.providers.datatypes import * # noqa: F403
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
|
||||
|
||||
class DistributionInspectConfig(BaseModel):
|
||||
|
|
|
|||
|
|
@ -6,14 +6,10 @@
|
|||
import importlib
|
||||
import inspect
|
||||
|
||||
from typing import Any, Dict, List, Set
|
||||
|
||||
|
||||
from llama_stack.providers.datatypes import * # noqa: F403
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
|
||||
import logging
|
||||
|
||||
from typing import Any, Dict, List, Set
|
||||
|
||||
from llama_stack.apis.agents import Agents
|
||||
from llama_stack.apis.datasetio import DatasetIO
|
||||
from llama_stack.apis.datasets import Datasets
|
||||
|
|
@ -32,10 +28,32 @@ from llama_stack.apis.shields import Shields
|
|||
from llama_stack.apis.telemetry import Telemetry
|
||||
from llama_stack.apis.tools import ToolGroups, ToolRuntime
|
||||
from llama_stack.distribution.client import get_client_impl
|
||||
|
||||
from llama_stack.distribution.datatypes import (
|
||||
AutoRoutedProviderSpec,
|
||||
Provider,
|
||||
RoutingTableProviderSpec,
|
||||
StackRunConfig,
|
||||
)
|
||||
from llama_stack.distribution.distribution import builtin_automatically_routed_apis
|
||||
from llama_stack.distribution.store import DistributionRegistry
|
||||
from llama_stack.distribution.utils.dynamic import instantiate_class_type
|
||||
|
||||
from llama_stack.providers.datatypes import (
|
||||
Api,
|
||||
DatasetsProtocolPrivate,
|
||||
EvalTasksProtocolPrivate,
|
||||
InlineProviderSpec,
|
||||
MemoryBanksProtocolPrivate,
|
||||
ModelsProtocolPrivate,
|
||||
ProviderSpec,
|
||||
RemoteProviderConfig,
|
||||
RemoteProviderSpec,
|
||||
ScoringFunctionsProtocolPrivate,
|
||||
ShieldsProtocolPrivate,
|
||||
ToolsProtocolPrivate,
|
||||
)
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -4,10 +4,12 @@
|
|||
# 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
|
||||
from typing import Any, Dict
|
||||
|
||||
from llama_stack.distribution.datatypes import RoutedProtocol
|
||||
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
from llama_stack.distribution.store import DistributionRegistry
|
||||
from llama_stack.providers.datatypes import Api, RoutingTable
|
||||
|
||||
from .routing_tables import (
|
||||
DatasetsRoutingTable,
|
||||
|
|
|
|||
|
|
@ -6,16 +6,40 @@
|
|||
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional
|
||||
|
||||
from llama_stack.apis.datasetio import * # noqa: F403
|
||||
from llama_stack.apis.datasetio.datasetio import DatasetIO
|
||||
from llama_stack.apis.eval import * # noqa: F403
|
||||
from llama_stack.apis.inference import * # noqa: F403
|
||||
from llama_stack.apis.memory import * # noqa: F403
|
||||
from llama_stack.apis.common.content_types import InterleavedContent
|
||||
from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult
|
||||
from llama_stack.apis.eval import (
|
||||
AppEvalTaskConfig,
|
||||
Eval,
|
||||
EvalTaskConfig,
|
||||
EvaluateResponse,
|
||||
Job,
|
||||
JobStatus,
|
||||
)
|
||||
from llama_stack.apis.inference import (
|
||||
EmbeddingsResponse,
|
||||
Inference,
|
||||
LogProbConfig,
|
||||
Message,
|
||||
ResponseFormat,
|
||||
SamplingParams,
|
||||
ToolChoice,
|
||||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.memory import Memory, MemoryBankDocument, QueryDocumentsResponse
|
||||
from llama_stack.apis.memory_banks.memory_banks import BankParams
|
||||
from llama_stack.apis.safety import * # noqa: F403
|
||||
from llama_stack.apis.scoring import * # noqa: F403
|
||||
from llama_stack.apis.tools import * # noqa: F403
|
||||
from llama_stack.distribution.datatypes import RoutingTable
|
||||
from llama_stack.apis.models import ModelType
|
||||
from llama_stack.apis.safety import RunShieldResponse, Safety
|
||||
from llama_stack.apis.scoring import (
|
||||
ScoreBatchResponse,
|
||||
ScoreResponse,
|
||||
Scoring,
|
||||
ScoringFnParams,
|
||||
)
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.apis.tools import Tool, ToolGroupDef, ToolRuntime
|
||||
from llama_stack.providers.datatypes import RoutingTable
|
||||
|
||||
|
||||
class MemoryRouter(Memory):
|
||||
|
|
@ -330,7 +354,6 @@ class EvalRouter(Eval):
|
|||
task_config=task_config,
|
||||
)
|
||||
|
||||
@webmethod(route="/eval/evaluate_rows", method="POST")
|
||||
async def evaluate_rows(
|
||||
self,
|
||||
task_id: str,
|
||||
|
|
|
|||
|
|
@ -6,19 +6,42 @@
|
|||
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from llama_models.llama3.api.datatypes import * # noqa: F403
|
||||
from pydantic import parse_obj_as
|
||||
|
||||
from llama_stack.apis.common.content_types import URL
|
||||
from llama_stack.apis.common.type_system import ParamType
|
||||
from llama_stack.apis.datasets import * # noqa: F403
|
||||
from llama_stack.apis.eval_tasks import * # noqa: F403
|
||||
from llama_stack.apis.memory_banks import * # noqa: F403
|
||||
from llama_stack.apis.models import * # noqa: F403
|
||||
from llama_stack.apis.shields import * # noqa: F403
|
||||
from llama_stack.apis.tools import * # noqa: F403
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
from llama_stack.apis.datasets import Dataset, Datasets
|
||||
from llama_stack.apis.eval_tasks import EvalTask, EvalTasks
|
||||
from llama_stack.apis.memory_banks import (
|
||||
BankParams,
|
||||
MemoryBank,
|
||||
MemoryBanks,
|
||||
MemoryBankType,
|
||||
)
|
||||
from llama_stack.apis.models import Model, Models, ModelType
|
||||
from llama_stack.apis.resource import ResourceType
|
||||
from llama_stack.apis.scoring_functions import (
|
||||
ScoringFn,
|
||||
ScoringFnParams,
|
||||
ScoringFunctions,
|
||||
)
|
||||
from llama_stack.apis.shields import Shield, Shields
|
||||
from llama_stack.apis.tools import (
|
||||
MCPToolGroupDef,
|
||||
Tool,
|
||||
ToolGroup,
|
||||
ToolGroupDef,
|
||||
ToolGroups,
|
||||
UserDefinedToolGroupDef,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import (
|
||||
RoutableObject,
|
||||
RoutableObjectWithProvider,
|
||||
RoutedProtocol,
|
||||
)
|
||||
|
||||
from llama_stack.distribution.store import DistributionRegistry
|
||||
from llama_stack.providers.datatypes import Api, RoutingTable
|
||||
|
||||
|
||||
def get_impl_api(p: Any) -> Api:
|
||||
|
|
|
|||
|
|
@ -28,14 +28,9 @@ from pydantic import BaseModel, ValidationError
|
|||
from termcolor import cprint
|
||||
from typing_extensions import Annotated
|
||||
|
||||
from llama_stack.distribution.distribution import builtin_automatically_routed_apis
|
||||
from llama_stack.distribution.datatypes import StackRunConfig
|
||||
|
||||
from llama_stack.providers.utils.telemetry.tracing import (
|
||||
end_trace,
|
||||
setup_logger,
|
||||
start_trace,
|
||||
)
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
from llama_stack.distribution.distribution import builtin_automatically_routed_apis
|
||||
from llama_stack.distribution.request_headers import set_request_provider_data
|
||||
from llama_stack.distribution.resolver import InvalidProviderError
|
||||
from llama_stack.distribution.stack import (
|
||||
|
|
@ -43,11 +38,19 @@ from llama_stack.distribution.stack import (
|
|||
replace_env_vars,
|
||||
validate_env_pair,
|
||||
)
|
||||
|
||||
from llama_stack.providers.datatypes import Api
|
||||
from llama_stack.providers.inline.telemetry.meta_reference.config import TelemetryConfig
|
||||
from llama_stack.providers.inline.telemetry.meta_reference.telemetry import (
|
||||
TelemetryAdapter,
|
||||
)
|
||||
|
||||
from llama_stack.providers.utils.telemetry.tracing import (
|
||||
end_trace,
|
||||
setup_logger,
|
||||
start_trace,
|
||||
)
|
||||
|
||||
from .endpoints import get_all_api_endpoints
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -8,32 +8,31 @@ import logging
|
|||
import os
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import pkg_resources
|
||||
import yaml
|
||||
|
||||
from termcolor import colored
|
||||
|
||||
from llama_models.llama3.api.datatypes import * # noqa: F403
|
||||
from llama_stack.apis.agents import * # noqa: F403
|
||||
from llama_stack.apis.datasets import * # noqa: F403
|
||||
from llama_stack.apis.datasetio import * # noqa: F403
|
||||
from llama_stack.apis.scoring import * # noqa: F403
|
||||
from llama_stack.apis.scoring_functions import * # noqa: F403
|
||||
from llama_stack.apis.eval import * # noqa: F403
|
||||
from llama_stack.apis.inference import * # noqa: F403
|
||||
from llama_stack.apis.batch_inference import * # noqa: F403
|
||||
from llama_stack.apis.memory import * # noqa: F403
|
||||
from llama_stack.apis.telemetry import * # noqa: F403
|
||||
from llama_stack.apis.post_training import * # noqa: F403
|
||||
from llama_stack.apis.synthetic_data_generation import * # noqa: F403
|
||||
from llama_stack.apis.safety import * # noqa: F403
|
||||
from llama_stack.apis.models import * # noqa: F403
|
||||
from llama_stack.apis.memory_banks import * # noqa: F403
|
||||
from llama_stack.apis.shields import * # noqa: F403
|
||||
from llama_stack.apis.inspect import * # noqa: F403
|
||||
from llama_stack.apis.eval_tasks import * # noqa: F403
|
||||
from llama_stack.apis.agents import Agents
|
||||
from llama_stack.apis.batch_inference import BatchInference
|
||||
from llama_stack.apis.datasetio import DatasetIO
|
||||
from llama_stack.apis.datasets import Datasets
|
||||
from llama_stack.apis.eval import Eval
|
||||
from llama_stack.apis.eval_tasks import EvalTasks
|
||||
from llama_stack.apis.inference import Inference
|
||||
from llama_stack.apis.inspect import Inspect
|
||||
from llama_stack.apis.memory import Memory
|
||||
from llama_stack.apis.memory_banks import MemoryBanks
|
||||
from llama_stack.apis.models import Models
|
||||
from llama_stack.apis.post_training import PostTraining
|
||||
from llama_stack.apis.safety import Safety
|
||||
from llama_stack.apis.scoring import Scoring
|
||||
from llama_stack.apis.scoring_functions import ScoringFunctions
|
||||
from llama_stack.apis.shields import Shields
|
||||
from llama_stack.apis.synthetic_data_generation import SyntheticDataGeneration
|
||||
from llama_stack.apis.telemetry import Telemetry
|
||||
|
||||
from llama_stack.distribution.datatypes import StackRunConfig
|
||||
from llama_stack.distribution.distribution import get_provider_registry
|
||||
|
|
|
|||
|
|
@ -13,11 +13,8 @@ import pydantic
|
|||
from llama_stack.distribution.datatypes import KVStoreConfig, RoutableObjectWithProvider
|
||||
from llama_stack.distribution.utils.config_dirs import DISTRIBS_BASE_DIR
|
||||
|
||||
from llama_stack.providers.utils.kvstore import (
|
||||
KVStore,
|
||||
kvstore_impl,
|
||||
SqliteKVStoreConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
|
||||
|
||||
class DistributionRegistry(Protocol):
|
||||
|
|
|
|||
|
|
@ -8,11 +8,14 @@ import os
|
|||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
from llama_stack.distribution.store import * # noqa F403
|
||||
from llama_stack.apis.inference import Model
|
||||
from llama_stack.apis.memory_banks import VectorMemoryBank
|
||||
|
||||
from llama_stack.distribution.store.registry import (
|
||||
CachedDiskDistributionRegistry,
|
||||
DiskDistributionRegistry,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl, SqliteKVStoreConfig
|
||||
from llama_stack.distribution.datatypes import * # noqa F403
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue