diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index bca91081f..a7ece3b25 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -29,10 +29,12 @@ repos: - repo: https://github.com/astral-sh/ruff-pre-commit rev: v0.9.4 hooks: + # Run the linter with import sorting. - id: ruff args: [ --fix, - --exit-non-zero-on-fix + --exit-non-zero-on-fix, + --select, I, ] - id: ruff-format diff --git a/llama_stack/apis/agents/agents.py b/llama_stack/apis/agents/agents.py index e2901448b..106d34584 100644 --- a/llama_stack/apis/agents/agents.py +++ b/llama_stack/apis/agents/agents.py @@ -15,14 +15,14 @@ from typing import ( Literal, Optional, Protocol, - runtime_checkable, Union, + runtime_checkable, ) from llama_models.schema_utils import json_schema_type, register_schema, webmethod from pydantic import BaseModel, ConfigDict, Field -from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, URL +from llama_stack.apis.common.content_types import URL, ContentDelta, InterleavedContent from llama_stack.apis.inference import ( CompletionMessage, ResponseFormat, diff --git a/llama_stack/apis/agents/event_logger.py b/llama_stack/apis/agents/event_logger.py index 021cb6e1a..835ce4cee 100644 --- a/llama_stack/apis/agents/event_logger.py +++ b/llama_stack/apis/agents/event_logger.py @@ -13,7 +13,6 @@ from termcolor import cprint from llama_stack.apis.agents import AgentTurnResponseEventType, StepType from llama_stack.apis.common.content_types import ToolCallParseStatus from llama_stack.apis.inference import ToolResponseMessage - from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) diff --git a/llama_stack/apis/common/content_types.py b/llama_stack/apis/common/content_types.py index 8e56f59b1..e648f9a19 100644 --- a/llama_stack/apis/common/content_types.py +++ b/llama_stack/apis/common/content_types.py @@ -8,7 +8,6 @@ from enum import Enum from typing import Annotated, List, Literal, Optional, Union from llama_models.llama3.api.datatypes import ToolCall - from llama_models.schema_utils import json_schema_type, register_schema from pydantic import BaseModel, Field, model_validator diff --git a/llama_stack/apis/common/deployment_types.py b/llama_stack/apis/common/deployment_types.py index 24de0cc91..16a5c8ad6 100644 --- a/llama_stack/apis/common/deployment_types.py +++ b/llama_stack/apis/common/deployment_types.py @@ -8,7 +8,6 @@ from enum import Enum from typing import Any, Dict, Optional from llama_models.schema_utils import json_schema_type - from pydantic import BaseModel from llama_stack.apis.common.content_types import URL diff --git a/llama_stack/apis/scoring_functions/scoring_functions.py b/llama_stack/apis/scoring_functions/scoring_functions.py index 3fa40ffbf..fece50fbd 100644 --- a/llama_stack/apis/scoring_functions/scoring_functions.py +++ b/llama_stack/apis/scoring_functions/scoring_functions.py @@ -12,8 +12,8 @@ from typing import ( Literal, Optional, Protocol, - runtime_checkable, Union, + runtime_checkable, ) from llama_models.schema_utils import json_schema_type, register_schema, webmethod diff --git a/llama_stack/apis/synthetic_data_generation/synthetic_data_generation.py b/llama_stack/apis/synthetic_data_generation/synthetic_data_generation.py index 13b209912..a61fb0cf2 100644 --- a/llama_stack/apis/synthetic_data_generation/synthetic_data_generation.py +++ b/llama_stack/apis/synthetic_data_generation/synthetic_data_generation.py @@ -5,11 +5,9 @@ # the root directory of this source tree. from enum import Enum - from typing import Any, Dict, List, Optional, Protocol, Union from llama_models.schema_utils import json_schema_type, webmethod - from pydantic import BaseModel from llama_stack.apis.inference import Message diff --git a/llama_stack/apis/tools/__init__.py b/llama_stack/apis/tools/__init__.py index 8cd798ebf..be8846ba2 100644 --- a/llama_stack/apis/tools/__init__.py +++ b/llama_stack/apis/tools/__init__.py @@ -4,5 +4,5 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from .tools import * # noqa: F401 F403 from .rag_tool import * # noqa: F401 F403 +from .tools import * # noqa: F401 F403 diff --git a/llama_stack/apis/tools/rag_tool.py b/llama_stack/apis/tools/rag_tool.py index 2e9bf9c51..2e6b43eb8 100644 --- a/llama_stack/apis/tools/rag_tool.py +++ b/llama_stack/apis/tools/rag_tool.py @@ -11,7 +11,7 @@ from llama_models.schema_utils import json_schema_type, register_schema, webmeth from pydantic import BaseModel, Field from typing_extensions import Annotated, Protocol, runtime_checkable -from llama_stack.apis.common.content_types import InterleavedContent, URL +from llama_stack.apis.common.content_types import URL, InterleavedContent from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol diff --git a/llama_stack/apis/tools/tools.py b/llama_stack/apis/tools/tools.py index a8e946b08..2a407ca00 100644 --- a/llama_stack/apis/tools/tools.py +++ b/llama_stack/apis/tools/tools.py @@ -11,7 +11,7 @@ from llama_models.schema_utils import json_schema_type, webmethod from pydantic import BaseModel, Field from typing_extensions import Protocol, runtime_checkable -from llama_stack.apis.common.content_types import InterleavedContent, URL +from llama_stack.apis.common.content_types import URL, InterleavedContent from llama_stack.apis.resource import Resource, ResourceType from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol diff --git a/llama_stack/cli/download.py b/llama_stack/cli/download.py index 379ac49ca..3ea534277 100644 --- a/llama_stack/cli/download.py +++ b/llama_stack/cli/download.py @@ -16,11 +16,9 @@ from pathlib import Path from typing import Dict, List, Optional import httpx - from llama_models.datatypes import Model from llama_models.sku_list import LlamaDownloadInfo from pydantic import BaseModel, ConfigDict - from rich.console import Console from rich.progress import ( BarColumn, diff --git a/llama_stack/cli/model/describe.py b/llama_stack/cli/model/describe.py index fc0190ca8..a25513633 100644 --- a/llama_stack/cli/model/describe.py +++ b/llama_stack/cli/model/describe.py @@ -8,7 +8,6 @@ import argparse import json from llama_models.sku_list import resolve_model - from termcolor import colored from llama_stack.cli.subcommand import Subcommand diff --git a/llama_stack/cli/model/model.py b/llama_stack/cli/model/model.py index 02e7f216f..3f8f55773 100644 --- a/llama_stack/cli/model/model.py +++ b/llama_stack/cli/model/model.py @@ -11,7 +11,6 @@ from llama_stack.cli.model.download import ModelDownload from llama_stack.cli.model.list import ModelList from llama_stack.cli.model.prompt_format import ModelPromptFormat from llama_stack.cli.model.verify_download import ModelVerifyDownload - from llama_stack.cli.subcommand import Subcommand diff --git a/llama_stack/cli/model/prompt_format.py b/llama_stack/cli/model/prompt_format.py index 388a63a42..2e1e1601e 100644 --- a/llama_stack/cli/model/prompt_format.py +++ b/llama_stack/cli/model/prompt_format.py @@ -8,7 +8,7 @@ import argparse import textwrap from io import StringIO -from llama_models.datatypes import CoreModelId, is_multimodal, model_family, ModelFamily +from llama_models.datatypes import CoreModelId, ModelFamily, is_multimodal, model_family from llama_stack.cli.subcommand import Subcommand diff --git a/llama_stack/cli/model/safety_models.py b/llama_stack/cli/model/safety_models.py index 424ec367b..2321c4615 100644 --- a/llama_stack/cli/model/safety_models.py +++ b/llama_stack/cli/model/safety_models.py @@ -9,7 +9,6 @@ from typing import Any, Dict, Optional from llama_models.datatypes import CheckpointQuantizationFormat from llama_models.llama3.api.datatypes import SamplingParams from llama_models.sku_list import LlamaDownloadInfo - from pydantic import BaseModel, ConfigDict, Field diff --git a/llama_stack/cli/stack/_build.py b/llama_stack/cli/stack/_build.py index 65d37e9da..76f03aa5c 100644 --- a/llama_stack/cli/stack/_build.py +++ b/llama_stack/cli/stack/_build.py @@ -21,12 +21,11 @@ from prompt_toolkit.validation import Validator from termcolor import cprint from llama_stack.cli.table import print_table - from llama_stack.distribution.build import ( + SERVER_DEPENDENCIES, + ImageType, build_image, get_provider_dependencies, - ImageType, - SERVER_DEPENDENCIES, ) from llama_stack.distribution.datatypes import ( BuildConfig, diff --git a/llama_stack/cli/tests/test_stack_config.py b/llama_stack/cli/tests/test_stack_config.py index e1b9b23c5..2b7b2b210 100644 --- a/llama_stack/cli/tests/test_stack_config.py +++ b/llama_stack/cli/tests/test_stack_config.py @@ -8,6 +8,7 @@ from datetime import datetime import pytest import yaml + from llama_stack.distribution.configure import ( LLAMA_STACK_RUN_CONFIG_VERSION, parse_and_maybe_upgrade_config, diff --git a/llama_stack/distribution/build.py b/llama_stack/distribution/build.py index b898312f4..9422c8457 100644 --- a/llama_stack/distribution/build.py +++ b/llama_stack/distribution/build.py @@ -8,7 +8,6 @@ import importlib.resources import logging import sys from enum import Enum - from pathlib import Path from typing import Dict, List @@ -16,11 +15,8 @@ from pydantic import BaseModel from termcolor import cprint 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_command, run_with_pty from llama_stack.providers.datatypes import Api diff --git a/llama_stack/distribution/client.py b/llama_stack/distribution/client.py index 8ed82f83e..b1d174ede 100644 --- a/llama_stack/distribution/client.py +++ b/llama_stack/distribution/client.py @@ -5,18 +5,16 @@ # the root directory of this source tree. import inspect - import json from collections.abc import AsyncIterator from enum import Enum -from typing import Any, get_args, get_origin, Type, Union +from typing import Any, Type, Union, get_args, get_origin import httpx from pydantic import BaseModel, parse_obj_as from termcolor import cprint from llama_stack.apis.version import LLAMA_STACK_API_VERSION - from llama_stack.providers.datatypes import RemoteProviderConfig _CLIENT_CLASSES = {} diff --git a/llama_stack/distribution/configure.py b/llama_stack/distribution/configure.py index 054f54864..825846a23 100644 --- a/llama_stack/distribution/configure.py +++ b/llama_stack/distribution/configure.py @@ -5,12 +5,11 @@ # the root directory of this source tree. import logging import textwrap - from typing import Any, Dict from llama_stack.distribution.datatypes import ( - DistributionSpec, LLAMA_STACK_RUN_CONFIG_VERSION, + DistributionSpec, Provider, StackRunConfig, ) @@ -20,7 +19,6 @@ 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.providers.datatypes import Api, ProviderSpec logger = logging.getLogger(__name__) diff --git a/llama_stack/distribution/library_client.py b/llama_stack/distribution/library_client.py index 2c0f73974..55a15e5e9 100644 --- a/llama_stack/distribution/library_client.py +++ b/llama_stack/distribution/library_client.py @@ -13,10 +13,21 @@ import re from concurrent.futures import ThreadPoolExecutor from enum import Enum from pathlib import Path -from typing import Any, get_args, get_origin, Optional, TypeVar +from typing import Any, Optional, TypeVar, get_args, get_origin import httpx import yaml +from llama_stack_client import ( + NOT_GIVEN, + APIResponse, + AsyncAPIResponse, + AsyncLlamaStackClient, + AsyncStream, + LlamaStackClient, +) +from pydantic import BaseModel, TypeAdapter +from rich.console import Console +from termcolor import cprint from llama_stack.distribution.build import print_pip_install_help from llama_stack.distribution.configure import parse_and_maybe_upgrade_config @@ -35,17 +46,6 @@ from llama_stack.providers.utils.telemetry.tracing import ( setup_logger, start_trace, ) -from llama_stack_client import ( - APIResponse, - AsyncAPIResponse, - AsyncLlamaStackClient, - AsyncStream, - LlamaStackClient, - NOT_GIVEN, -) -from pydantic import BaseModel, TypeAdapter -from rich.console import Console -from termcolor import cprint T = TypeVar("T") diff --git a/llama_stack/distribution/routers/__init__.py b/llama_stack/distribution/routers/__init__.py index 156cda385..18197ca7f 100644 --- a/llama_stack/distribution/routers/__init__.py +++ b/llama_stack/distribution/routers/__init__.py @@ -7,7 +7,6 @@ from typing import Any, Dict from llama_stack.distribution.datatypes import RoutedProtocol - from llama_stack.distribution.store import DistributionRegistry from llama_stack.providers.datatypes import Api, RoutingTable diff --git a/llama_stack/distribution/routers/routers.py b/llama_stack/distribution/routers/routers.py index 6cddcf73c..e716e44b0 100644 --- a/llama_stack/distribution/routers/routers.py +++ b/llama_stack/distribution/routers/routers.py @@ -6,7 +6,7 @@ from typing import Any, AsyncGenerator, Dict, List, Optional -from llama_stack.apis.common.content_types import InterleavedContent, URL +from llama_stack.apis.common.content_types import URL, InterleavedContent from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult from llama_stack.apis.eval import ( AppEvalTaskConfig, diff --git a/llama_stack/distribution/server/endpoints.py b/llama_stack/distribution/server/endpoints.py index 45f1a2831..812f59ffd 100644 --- a/llama_stack/distribution/server/endpoints.py +++ b/llama_stack/distribution/server/endpoints.py @@ -10,11 +10,8 @@ from typing import Dict, List from pydantic import BaseModel from llama_stack.apis.tools import RAGToolRuntime, SpecialToolGroup - from llama_stack.apis.version import LLAMA_STACK_API_VERSION - from llama_stack.distribution.resolver import api_protocol_map - from llama_stack.providers.datatypes import Api diff --git a/llama_stack/distribution/server/server.py b/llama_stack/distribution/server/server.py index bb735268b..0d234d506 100644 --- a/llama_stack/distribution/server/server.py +++ b/llama_stack/distribution/server/server.py @@ -7,9 +7,9 @@ import argparse import asyncio import functools -import logging import inspect import json +import logging import os import signal import sys @@ -21,7 +21,8 @@ from pathlib import Path from typing import Any, List, Union import yaml -from fastapi import Body, FastAPI, HTTPException, Path as FastapiPath, Request +from fastapi import Body, FastAPI, HTTPException, Request +from fastapi import Path as FastapiPath from fastapi.exceptions import RequestValidationError from fastapi.responses import JSONResponse, StreamingResponse from pydantic import BaseModel, ValidationError diff --git a/llama_stack/distribution/store/tests/test_registry.py b/llama_stack/distribution/store/tests/test_registry.py index 1671cd30b..1ddba7472 100644 --- a/llama_stack/distribution/store/tests/test_registry.py +++ b/llama_stack/distribution/store/tests/test_registry.py @@ -8,9 +8,9 @@ import os import pytest import pytest_asyncio + from llama_stack.apis.inference import Model from llama_stack.apis.vector_dbs import VectorDB - from llama_stack.distribution.store.registry import ( CachedDiskDistributionRegistry, DiskDistributionRegistry, diff --git a/llama_stack/distribution/ui/modules/api.py b/llama_stack/distribution/ui/modules/api.py index 5f07a27c7..40caccda0 100644 --- a/llama_stack/distribution/ui/modules/api.py +++ b/llama_stack/distribution/ui/modules/api.py @@ -5,7 +5,6 @@ # the root directory of this source tree. import os - from typing import Optional from llama_stack_client import LlamaStackClient diff --git a/llama_stack/distribution/ui/page/distribution/resources.py b/llama_stack/distribution/ui/page/distribution/resources.py index 38d494570..94b840bcb 100644 --- a/llama_stack/distribution/ui/page/distribution/resources.py +++ b/llama_stack/distribution/ui/page/distribution/resources.py @@ -10,7 +10,6 @@ from page.distribution.models import models from page.distribution.scoring_functions import scoring_functions from page.distribution.shields import shields from page.distribution.vector_dbs import vector_dbs - from streamlit_option_menu import option_menu diff --git a/llama_stack/distribution/ui/page/evaluations/app_eval.py b/llama_stack/distribution/ui/page/evaluations/app_eval.py index 9b684ab80..26bc28451 100644 --- a/llama_stack/distribution/ui/page/evaluations/app_eval.py +++ b/llama_stack/distribution/ui/page/evaluations/app_eval.py @@ -8,7 +8,6 @@ import json import pandas as pd import streamlit as st - from modules.api import llama_stack_api from modules.utils import process_dataset diff --git a/llama_stack/distribution/ui/page/evaluations/native_eval.py b/llama_stack/distribution/ui/page/evaluations/native_eval.py index c4a44990f..112d9cff0 100644 --- a/llama_stack/distribution/ui/page/evaluations/native_eval.py +++ b/llama_stack/distribution/ui/page/evaluations/native_eval.py @@ -7,9 +7,7 @@ import json import pandas as pd - import streamlit as st - from modules.api import llama_stack_api diff --git a/llama_stack/distribution/ui/page/playground/rag.py b/llama_stack/distribution/ui/page/playground/rag.py index 8b30987cf..d84418241 100644 --- a/llama_stack/distribution/ui/page/playground/rag.py +++ b/llama_stack/distribution/ui/page/playground/rag.py @@ -9,7 +9,6 @@ from llama_stack_client.lib.agents.agent import Agent from llama_stack_client.lib.agents.event_logger import EventLogger from llama_stack_client.types.agent_create_params import AgentConfig from llama_stack_client.types.memory_insert_params import Document - from modules.api import llama_stack_api from modules.utils import data_url_from_file diff --git a/llama_stack/distribution/utils/config_dirs.py b/llama_stack/distribution/utils/config_dirs.py index eca59493f..e512c3576 100644 --- a/llama_stack/distribution/utils/config_dirs.py +++ b/llama_stack/distribution/utils/config_dirs.py @@ -7,7 +7,6 @@ import os from pathlib import Path - LLAMA_STACK_CONFIG_DIR = Path(os.getenv("LLAMA_STACK_CONFIG_DIR", os.path.expanduser("~/.llama/"))) DISTRIBS_BASE_DIR = LLAMA_STACK_CONFIG_DIR / "distributions" diff --git a/llama_stack/distribution/utils/prompt_for_config.py b/llama_stack/distribution/utils/prompt_for_config.py index 6a6223cc9..9b2b99022 100644 --- a/llama_stack/distribution/utils/prompt_for_config.py +++ b/llama_stack/distribution/utils/prompt_for_config.py @@ -8,13 +8,11 @@ import inspect import json import logging from enum import Enum - -from typing import Any, get_args, get_origin, List, Literal, Optional, Type, Union +from typing import Any, List, Literal, Optional, Type, Union, get_args, get_origin from pydantic import BaseModel from pydantic.fields import FieldInfo from pydantic_core import PydanticUndefinedType - from typing_extensions import Annotated log = logging.getLogger(__name__) diff --git a/llama_stack/providers/datatypes.py b/llama_stack/providers/datatypes.py index 8df91cce6..ccdaf76e7 100644 --- a/llama_stack/providers/datatypes.py +++ b/llama_stack/providers/datatypes.py @@ -11,7 +11,6 @@ from llama_models.schema_utils import json_schema_type from pydantic import BaseModel, Field from llama_stack.apis.datasets import Dataset - from llama_stack.apis.datatypes import Api from llama_stack.apis.eval_tasks import EvalTask from llama_stack.apis.models import Model diff --git a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py index 2f397f438..8ba7885cd 100644 --- a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py +++ b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py @@ -42,10 +42,10 @@ from llama_stack.apis.agents import ( Turn, ) from llama_stack.apis.common.content_types import ( + URL, TextContentItem, ToolCallDelta, ToolCallParseStatus, - URL, ) from llama_stack.apis.inference import ( ChatCompletionResponseEventType, diff --git a/llama_stack/providers/inline/agents/meta_reference/safety.py b/llama_stack/providers/inline/agents/meta_reference/safety.py index 69439522b..30ce52e3b 100644 --- a/llama_stack/providers/inline/agents/meta_reference/safety.py +++ b/llama_stack/providers/inline/agents/meta_reference/safety.py @@ -6,11 +6,9 @@ import asyncio import logging - from typing import List from llama_stack.apis.inference import Message - from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel log = logging.getLogger(__name__) diff --git a/llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py b/llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py index b62bc5fee..4e3951ad3 100644 --- a/llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py +++ b/llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py @@ -41,7 +41,6 @@ from llama_stack.apis.tools import ( ToolInvocationResult, ) from llama_stack.apis.vector_io import QueryChunksResponse - from llama_stack.providers.inline.agents.meta_reference.agent_instance import ( MEMORY_QUERY_TOOL, ) diff --git a/llama_stack/providers/inline/datasetio/localfs/datasetio.py b/llama_stack/providers/inline/datasetio/localfs/datasetio.py index 54afae839..491f03f72 100644 --- a/llama_stack/providers/inline/datasetio/localfs/datasetio.py +++ b/llama_stack/providers/inline/datasetio/localfs/datasetio.py @@ -15,14 +15,12 @@ import pandas from llama_stack.apis.common.content_types import URL from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult from llama_stack.apis.datasets import Dataset - from llama_stack.providers.datatypes import DatasetsProtocolPrivate from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url from llama_stack.providers.utils.kvstore import kvstore_impl from .config import LocalFSDatasetIOConfig - DATASETS_PREFIX = "localfs_datasets:" diff --git a/llama_stack/providers/inline/eval/meta_reference/eval.py b/llama_stack/providers/inline/eval/meta_reference/eval.py index 1db627007..1c44caf7f 100644 --- a/llama_stack/providers/inline/eval/meta_reference/eval.py +++ b/llama_stack/providers/inline/eval/meta_reference/eval.py @@ -15,7 +15,6 @@ from llama_stack.apis.inference import Inference, UserMessage from llama_stack.apis.scoring import Scoring from llama_stack.distribution.datatypes import Api from llama_stack.providers.datatypes import EvalTasksProtocolPrivate - from llama_stack.providers.inline.agents.meta_reference.agent_instance import ( MEMORY_QUERY_TOOL, ) @@ -28,7 +27,6 @@ from llama_stack.providers.utils.kvstore import kvstore_impl from .....apis.common.job_types import Job from .....apis.eval.eval import Eval, EvalTaskConfig, EvaluateResponse, JobStatus - from .config import MetaReferenceEvalConfig EVAL_TASKS_PREFIX = "eval_tasks:" diff --git a/llama_stack/providers/inline/inference/meta_reference/config.py b/llama_stack/providers/inline/inference/meta_reference/config.py index 57939abaa..9e5f7747e 100644 --- a/llama_stack/providers/inline/inference/meta_reference/config.py +++ b/llama_stack/providers/inline/inference/meta_reference/config.py @@ -9,7 +9,6 @@ from typing import Any, Dict, Optional from pydantic import BaseModel, field_validator from llama_stack.apis.inference import QuantizationConfig - from llama_stack.providers.utils.inference import supported_inference_models diff --git a/llama_stack/providers/inline/inference/meta_reference/generation.py b/llama_stack/providers/inline/inference/meta_reference/generation.py index 51c10b0a8..e60c3b1be 100644 --- a/llama_stack/providers/inline/inference/meta_reference/generation.py +++ b/llama_stack/providers/inline/inference/meta_reference/generation.py @@ -37,7 +37,6 @@ from llama_models.llama3.reference_impl.multimodal.model import ( CrossAttentionTransformer, ) from llama_models.sku_list import resolve_model - from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData from pydantic import BaseModel @@ -47,7 +46,6 @@ from llama_stack.apis.inference import ( ResponseFormat, ResponseFormatType, ) - from llama_stack.distribution.utils.model_utils import model_local_dir from llama_stack.providers.utils.inference.prompt_adapter import ( ChatCompletionRequestWithRawContent, diff --git a/llama_stack/providers/inline/inference/meta_reference/inference.py b/llama_stack/providers/inline/inference/meta_reference/inference.py index 3caf4e2a5..61f0ee3f4 100644 --- a/llama_stack/providers/inline/inference/meta_reference/inference.py +++ b/llama_stack/providers/inline/inference/meta_reference/inference.py @@ -46,8 +46,8 @@ from llama_stack.providers.utils.inference.embedding_mixin import ( SentenceTransformerEmbeddingMixin, ) from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.prompt_adapter import ( augment_content_with_response_format_prompt, diff --git a/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py b/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py index b8efddcbd..711a4632d 100644 --- a/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py +++ b/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py @@ -22,16 +22,13 @@ from typing import Callable, Generator, Literal, Optional, Union import torch import zmq - from fairscale.nn.model_parallel.initialize import ( get_model_parallel_group, get_model_parallel_rank, get_model_parallel_src_rank, ) - from pydantic import BaseModel, Field - -from torch.distributed.launcher.api import elastic_launch, LaunchConfig +from torch.distributed.launcher.api import LaunchConfig, elastic_launch from typing_extensions import Annotated from llama_stack.providers.utils.inference.prompt_adapter import ( diff --git a/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls.py b/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls.py index f5235d6c9..2b5e135b4 100644 --- a/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls.py +++ b/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_impls.py @@ -8,7 +8,6 @@ # This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement. import collections - import logging from typing import Optional, Type @@ -23,7 +22,7 @@ except ImportError: raise import torch -from torch import nn, Tensor +from torch import Tensor, nn class Fp8ScaledWeights: diff --git a/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_txest_disabled.py b/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_txest_disabled.py index 8f52d8c04..014a26f09 100644 --- a/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_txest_disabled.py +++ b/llama_stack/providers/inline/inference/meta_reference/quantization/fp8_txest_disabled.py @@ -10,9 +10,9 @@ import unittest import torch - -from fp8_impls import ffn_swiglu_fp8_dynamic, FfnQuantizeMode, quantize_fp8 -from hypothesis import given, settings, strategies as st +from fp8_impls import FfnQuantizeMode, ffn_swiglu_fp8_dynamic, quantize_fp8 +from hypothesis import given, settings +from hypothesis import strategies as st from torch import Tensor diff --git a/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py b/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py index 955527ff8..9be35ae70 100644 --- a/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py +++ b/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py @@ -12,18 +12,13 @@ import os from typing import Any, Dict, List, Optional import torch - from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region - from llama_models.datatypes import CheckpointQuantizationFormat - from llama_models.llama3.api.args import ModelArgs from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock from llama_models.sku_list import resolve_model - -from torch import nn, Tensor - +from torch import Tensor, nn from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear from llama_stack.apis.inference import QuantizationType diff --git a/llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py b/llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py index 4764d59b1..8bff70464 100644 --- a/llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py +++ b/llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py @@ -16,14 +16,12 @@ from pathlib import Path from typing import Optional import fire - import torch from fairscale.nn.model_parallel.initialize import ( get_model_parallel_rank, initialize_model_parallel, model_parallel_is_initialized, ) - from llama_models.llama3.api.args import ModelArgs from llama_models.llama3.api.tokenizer import Tokenizer from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock diff --git a/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py b/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py index d34befbd9..6a83836e6 100644 --- a/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py +++ b/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py @@ -15,9 +15,9 @@ from llama_stack.apis.inference import ( ResponseFormat, SamplingParams, ToolChoice, + ToolConfig, ToolDefinition, ToolPromptFormat, - ToolConfig, ) from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate from llama_stack.providers.utils.inference.embedding_mixin import ( diff --git a/llama_stack/providers/inline/inference/vllm/vllm.py b/llama_stack/providers/inline/inference/vllm/vllm.py index 77c95cc7e..e75a9aac3 100644 --- a/llama_stack/providers/inline/inference/vllm/vllm.py +++ b/llama_stack/providers/inline/inference/vllm/vllm.py @@ -37,9 +37,9 @@ from llama_stack.apis.inference import ( from llama_stack.apis.models import Model from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.openai_compat import ( - get_sampling_options, OpenAICompatCompletionChoice, OpenAICompatCompletionResponse, + get_sampling_options, process_chat_completion_response, process_chat_completion_stream_response, ) diff --git a/llama_stack/providers/inline/post_training/torchtune/common/utils.py b/llama_stack/providers/inline/post_training/torchtune/common/utils.py index 88011ead4..735af8c79 100644 --- a/llama_stack/providers/inline/post_training/torchtune/common/utils.py +++ b/llama_stack/providers/inline/post_training/torchtune/common/utils.py @@ -15,10 +15,8 @@ from typing import Any, Callable, Dict import torch from llama_models.datatypes import Model from llama_models.sku_list import resolve_model - from pydantic import BaseModel from torchtune.data._messages import InputOutputToMessages, ShareGPTToMessages - from torchtune.models.llama3 import llama3_tokenizer from torchtune.models.llama3._tokenizer import Llama3Tokenizer from torchtune.models.llama3_1 import lora_llama3_1_8b diff --git a/llama_stack/providers/inline/post_training/torchtune/datasets/sft.py b/llama_stack/providers/inline/post_training/torchtune/datasets/sft.py index 82e6645d2..b556b59a6 100644 --- a/llama_stack/providers/inline/post_training/torchtune/datasets/sft.py +++ b/llama_stack/providers/inline/post_training/torchtune/datasets/sft.py @@ -13,7 +13,6 @@ from typing import Any, Dict, List, Mapping import numpy as np - from torch.utils.data import Dataset from torchtune.data._common import CROSS_ENTROPY_IGNORE_IDX from torchtune.data._messages import validate_messages diff --git a/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py b/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py index dbb3f714a..ef379aff2 100644 --- a/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py +++ b/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py @@ -18,9 +18,9 @@ from llama_models.sku_list import resolve_model from torch import nn from torch.optim import Optimizer from torch.utils.data import DataLoader, DistributedSampler -from torchtune import modules, training, utils as torchtune_utils +from torchtune import modules, training +from torchtune import utils as torchtune_utils from torchtune.data import padded_collate_sft - from torchtune.modules.loss import CEWithChunkedOutputLoss from torchtune.modules.peft import ( get_adapter_params, @@ -44,14 +44,11 @@ from llama_stack.apis.post_training import ( OptimizerConfig, TrainingConfig, ) - from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR - from llama_stack.distribution.utils.model_utils import model_local_dir from llama_stack.providers.inline.post_training.common.validator import ( validate_input_dataset_schema, ) - from llama_stack.providers.inline.post_training.torchtune.common import utils from llama_stack.providers.inline.post_training.torchtune.common.checkpointer import ( TorchtuneCheckpointer, diff --git a/llama_stack/providers/inline/safety/code_scanner/code_scanner.py b/llama_stack/providers/inline/safety/code_scanner/code_scanner.py index 22af7ef23..606d11d2c 100644 --- a/llama_stack/providers/inline/safety/code_scanner/code_scanner.py +++ b/llama_stack/providers/inline/safety/code_scanner/code_scanner.py @@ -21,7 +21,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import ( from .config import CodeScannerConfig - log = logging.getLogger(__name__) ALLOWED_CODE_SCANNER_MODEL_IDS = [ diff --git a/llama_stack/providers/inline/safety/llama_guard/llama_guard.py b/llama_stack/providers/inline/safety/llama_guard/llama_guard.py index e5168fb00..32d6d5100 100644 --- a/llama_stack/providers/inline/safety/llama_guard/llama_guard.py +++ b/llama_stack/providers/inline/safety/llama_guard/llama_guard.py @@ -5,7 +5,6 @@ # the root directory of this source tree. import re - from string import Template from typing import Any, Dict, List, Optional @@ -25,10 +24,8 @@ from llama_stack.apis.safety import ( SafetyViolation, ViolationLevel, ) - from llama_stack.apis.shields import Shield from llama_stack.distribution.datatypes import Api - from llama_stack.providers.datatypes import ShieldsProtocolPrivate from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, @@ -36,7 +33,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import ( from .config import LlamaGuardConfig - CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?" SAFE_RESPONSE = "safe" diff --git a/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py b/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py index 76d34e549..fce3e3d14 100644 --- a/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py +++ b/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py @@ -8,7 +8,6 @@ import logging from typing import Any, Dict, List import torch - from transformers import AutoModelForSequenceClassification, AutoTokenizer from llama_stack.apis.inference import Message @@ -19,7 +18,6 @@ from llama_stack.apis.safety import ( ViolationLevel, ) from llama_stack.apis.shields import Shield - from llama_stack.distribution.utils.model_utils import model_local_dir from llama_stack.providers.datatypes import ShieldsProtocolPrivate from llama_stack.providers.utils.inference.prompt_adapter import ( diff --git a/llama_stack/providers/inline/scoring/basic/scoring.py b/llama_stack/providers/inline/scoring/basic/scoring.py index 24ce11872..13cd78243 100644 --- a/llama_stack/providers/inline/scoring/basic/scoring.py +++ b/llama_stack/providers/inline/scoring/basic/scoring.py @@ -14,13 +14,13 @@ from llama_stack.apis.scoring import ( ScoringResult, ) from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams - from llama_stack.distribution.datatypes import Api from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate from llama_stack.providers.utils.common.data_schema_validator import ( get_valid_schemas, validate_dataset_schema, ) + from .config import BasicScoringConfig from .scoring_fn.equality_scoring_fn import EqualityScoringFn from .scoring_fn.regex_parser_scoring_fn import RegexParserScoringFn diff --git a/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py b/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py index ad2037bdf..0bd6bdd48 100644 --- a/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py +++ b/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py @@ -7,7 +7,6 @@ from typing import Any, Dict, Optional from llama_stack.apis.scoring import ScoringResultRow - from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn diff --git a/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py b/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py index 7973eb939..9b24ff791 100644 --- a/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py +++ b/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py @@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import ( ScoringFn, ) - equality = ScoringFn( identifier="basic::equality", description="Returns 1.0 if the input is equal to the target, 0.0 otherwise.", diff --git a/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py b/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py index 0281e81b9..9cae66fa6 100644 --- a/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py +++ b/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py @@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import ( ScoringFn, ) - subset_of = ScoringFn( identifier="basic::subset_of", description="Returns 1.0 if the expected is included in generated, 0.0 otherwise.", diff --git a/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py b/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py index 4fcfdba76..0606a9581 100644 --- a/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py +++ b/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py @@ -4,7 +4,6 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. import re - from typing import Any, Dict, Optional from llama_stack.apis.scoring import ScoringResultRow diff --git a/llama_stack/providers/inline/scoring/braintrust/braintrust.py b/llama_stack/providers/inline/scoring/braintrust/braintrust.py index ff3207e32..be0f023f3 100644 --- a/llama_stack/providers/inline/scoring/braintrust/braintrust.py +++ b/llama_stack/providers/inline/scoring/braintrust/braintrust.py @@ -29,9 +29,7 @@ from llama_stack.apis.scoring import ( ScoringResultRow, ) from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams - from llama_stack.distribution.datatypes import Api - from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate from llama_stack.providers.utils.common.data_schema_validator import ( @@ -39,8 +37,8 @@ from llama_stack.providers.utils.common.data_schema_validator import ( validate_dataset_schema, validate_row_schema, ) - from llama_stack.providers.utils.scoring.aggregation_utils import aggregate_metrics + from .config import BraintrustScoringConfig from .scoring_fn.fn_defs.answer_correctness import answer_correctness_fn_def from .scoring_fn.fn_defs.answer_relevancy import answer_relevancy_fn_def diff --git a/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py b/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py index 1941417bb..4fe07f822 100644 --- a/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py +++ b/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py @@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import ( ScoringFn, ) - answer_correctness_fn_def = ScoringFn( identifier="braintrust::answer-correctness", description=( diff --git a/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py b/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py index 3c9fb88de..c621ecf7f 100644 --- a/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py +++ b/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py @@ -11,7 +11,6 @@ from llama_stack.apis.scoring_functions import ( ScoringFn, ) - factuality_fn_def = ScoringFn( identifier="braintrust::factuality", description=( diff --git a/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py b/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py index 333910c2c..dc562df1f 100644 --- a/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py +++ b/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py @@ -8,7 +8,6 @@ from typing import Any, Dict, List, Optional from llama_stack.apis.datasetio import DatasetIO from llama_stack.apis.datasets import Datasets from llama_stack.apis.inference.inference import Inference - from llama_stack.apis.scoring import ( ScoreBatchResponse, ScoreResponse, @@ -26,7 +25,6 @@ from llama_stack.providers.utils.common.data_schema_validator import ( from .config import LlmAsJudgeScoringConfig from .scoring_fn.llm_as_judge_scoring_fn import LlmAsJudgeScoringFn - LLM_JUDGE_FNS = [LlmAsJudgeScoringFn] diff --git a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py index 0b18bac01..205e0bbf3 100644 --- a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py +++ b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py @@ -7,7 +7,6 @@ from llama_stack.apis.common.type_system import NumberType from llama_stack.apis.scoring_functions import LLMAsJudgeScoringFnParams, ScoringFn - llm_as_judge_base = ScoringFn( identifier="llm-as-judge::base", description="Llm As Judge Scoring Function", diff --git a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py index 0cf5a042a..457151c04 100644 --- a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py +++ b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py @@ -4,18 +4,14 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. import re - from typing import Any, Dict, Optional from llama_stack.apis.inference.inference import Inference - from llama_stack.apis.scoring import ScoringResultRow from llama_stack.apis.scoring_functions import ScoringFnParams - from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn from .fn_defs.llm_as_judge_405b_simpleqa import llm_as_judge_405b_simpleqa - from .fn_defs.llm_as_judge_base import llm_as_judge_base diff --git a/llama_stack/providers/inline/telemetry/sample/sample.py b/llama_stack/providers/inline/telemetry/sample/sample.py index f07a185ef..a4147a1b2 100644 --- a/llama_stack/providers/inline/telemetry/sample/sample.py +++ b/llama_stack/providers/inline/telemetry/sample/sample.py @@ -5,6 +5,7 @@ # the root directory of this source tree. from llama_stack.apis.telemetry import Telemetry + from .config import SampleConfig diff --git a/llama_stack/providers/inline/tool_runtime/code_interpreter/code_env_prefix.py b/llama_stack/providers/inline/tool_runtime/code_interpreter/code_env_prefix.py index 10f64ec94..f28ae248c 100644 --- a/llama_stack/providers/inline/tool_runtime/code_interpreter/code_env_prefix.py +++ b/llama_stack/providers/inline/tool_runtime/code_interpreter/code_env_prefix.py @@ -82,7 +82,11 @@ import sys as _sys # them with linters - they're used in code_execution.py from contextlib import ( # noqa contextmanager as _contextmanager, +) +from contextlib import ( redirect_stderr as _redirect_stderr, +) +from contextlib import ( redirect_stdout as _redirect_stdout, ) from multiprocessing.connection import Connection as _Connection diff --git a/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py b/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py index e77ec76af..be18430e4 100644 --- a/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py +++ b/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py @@ -9,7 +9,6 @@ from jinja2 import Template from llama_stack.apis.common.content_types import InterleavedContent from llama_stack.apis.inference import UserMessage - from llama_stack.apis.tools.rag_tool import ( DefaultRAGQueryGeneratorConfig, LLMRAGQueryGeneratorConfig, diff --git a/llama_stack/providers/inline/tool_runtime/rag/memory.py b/llama_stack/providers/inline/tool_runtime/rag/memory.py index 7b0fff348..5695d4037 100644 --- a/llama_stack/providers/inline/tool_runtime/rag/memory.py +++ b/llama_stack/providers/inline/tool_runtime/rag/memory.py @@ -11,9 +11,9 @@ import string from typing import Any, Dict, List, Optional from llama_stack.apis.common.content_types import ( + URL, InterleavedContent, TextContentItem, - URL, ) from llama_stack.apis.inference import Inference from llama_stack.apis.tools import ( diff --git a/llama_stack/providers/inline/vector_io/faiss/__init__.py b/llama_stack/providers/inline/vector_io/faiss/__init__.py index 15b7259ad..8c075a0f8 100644 --- a/llama_stack/providers/inline/vector_io/faiss/__init__.py +++ b/llama_stack/providers/inline/vector_io/faiss/__init__.py @@ -7,6 +7,7 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec + from .config import FaissImplConfig diff --git a/llama_stack/providers/inline/vector_io/faiss/faiss.py b/llama_stack/providers/inline/vector_io/faiss/faiss.py index 563d37bb1..565afdcf6 100644 --- a/llama_stack/providers/inline/vector_io/faiss/faiss.py +++ b/llama_stack/providers/inline/vector_io/faiss/faiss.py @@ -8,11 +8,9 @@ import base64 import io import json import logging - from typing import Any, Dict, List, Optional import faiss - import numpy as np from numpy.typing import NDArray diff --git a/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py b/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py index 488a57660..5a2f07012 100644 --- a/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py +++ b/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py @@ -5,7 +5,9 @@ # the root directory of this source tree. from typing import Dict + from llama_stack.providers.datatypes import Api, ProviderSpec + from .config import SQLiteVectorIOConfig diff --git a/llama_stack/providers/inline/vector_io/sqlite_vec/config.py b/llama_stack/providers/inline/vector_io/sqlite_vec/config.py index 60fe3ca2a..5a830ff27 100644 --- a/llama_stack/providers/inline/vector_io/sqlite_vec/config.py +++ b/llama_stack/providers/inline/vector_io/sqlite_vec/config.py @@ -5,9 +5,10 @@ # the root directory of this source tree. # config.py -from pydantic import BaseModel from typing import Any, Dict +from pydantic import BaseModel + from llama_stack.providers.utils.kvstore.config import ( KVStoreConfig, SqliteKVStoreConfig, diff --git a/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py b/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py index 019d260f8..fcd7cd8f9 100644 --- a/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py +++ b/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py @@ -4,13 +4,14 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -import sqlite3 -import sqlite_vec -import struct import logging +import sqlite3 +import struct +from typing import Any, Dict, List, Optional + import numpy as np +import sqlite_vec from numpy.typing import NDArray -from typing import List, Optional, Dict, Any from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO diff --git a/llama_stack/providers/remote/agents/sample/sample.py b/llama_stack/providers/remote/agents/sample/sample.py index f8b312f1e..02e889496 100644 --- a/llama_stack/providers/remote/agents/sample/sample.py +++ b/llama_stack/providers/remote/agents/sample/sample.py @@ -5,6 +5,7 @@ # the root directory of this source tree. from llama_stack.apis.agents import Agents + from .config import SampleConfig diff --git a/llama_stack/providers/remote/datasetio/huggingface/huggingface.py b/llama_stack/providers/remote/datasetio/huggingface/huggingface.py index cf17820dd..cd4e7f1f1 100644 --- a/llama_stack/providers/remote/datasetio/huggingface/huggingface.py +++ b/llama_stack/providers/remote/datasetio/huggingface/huggingface.py @@ -9,7 +9,6 @@ import datasets as hf_datasets from llama_stack.apis.datasetio import DatasetIO, PaginatedRowsResult from llama_stack.apis.datasets import Dataset - from llama_stack.providers.datatypes import DatasetsProtocolPrivate from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url from llama_stack.providers.utils.kvstore import kvstore_impl diff --git a/llama_stack/providers/remote/inference/bedrock/bedrock.py b/llama_stack/providers/remote/inference/bedrock/bedrock.py index 54a674d7e..917ac7a25 100644 --- a/llama_stack/providers/remote/inference/bedrock/bedrock.py +++ b/llama_stack/providers/remote/inference/bedrock/bedrock.py @@ -31,13 +31,13 @@ from llama_stack.apis.inference import ( from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig from llama_stack.providers.utils.bedrock.client import create_bedrock_client from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( - get_sampling_strategy_options, OpenAICompatCompletionChoice, OpenAICompatCompletionResponse, + get_sampling_strategy_options, process_chat_completion_response, process_chat_completion_stream_response, ) diff --git a/llama_stack/providers/remote/inference/cerebras/cerebras.py b/llama_stack/providers/remote/inference/cerebras/cerebras.py index 47f208129..2158fc5b4 100644 --- a/llama_stack/providers/remote/inference/cerebras/cerebras.py +++ b/llama_stack/providers/remote/inference/cerebras/cerebras.py @@ -29,8 +29,8 @@ from llama_stack.apis.inference import ( ToolPromptFormat, ) from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( get_sampling_options, diff --git a/llama_stack/providers/remote/inference/databricks/databricks.py b/llama_stack/providers/remote/inference/databricks/databricks.py index ee3c6e99b..d56be1465 100644 --- a/llama_stack/providers/remote/inference/databricks/databricks.py +++ b/llama_stack/providers/remote/inference/databricks/databricks.py @@ -26,8 +26,8 @@ from llama_stack.apis.inference import ( ToolPromptFormat, ) from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( get_sampling_options, diff --git a/llama_stack/providers/remote/inference/fireworks/fireworks.py b/llama_stack/providers/remote/inference/fireworks/fireworks.py index d978cb02e..7e8f85313 100644 --- a/llama_stack/providers/remote/inference/fireworks/fireworks.py +++ b/llama_stack/providers/remote/inference/fireworks/fireworks.py @@ -31,8 +31,8 @@ from llama_stack.apis.inference import ( ) from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( convert_message_to_openai_dict, diff --git a/llama_stack/providers/remote/inference/groq/groq.py b/llama_stack/providers/remote/inference/groq/groq.py index 9b3c1abbf..59ec8b0d2 100644 --- a/llama_stack/providers/remote/inference/groq/groq.py +++ b/llama_stack/providers/remote/inference/groq/groq.py @@ -31,9 +31,9 @@ from llama_stack.apis.inference import ( from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.providers.remote.inference.groq.config import GroqConfig from llama_stack.providers.utils.inference.model_registry import ( + ModelRegistryHelper, build_model_alias, build_model_alias_with_just_provider_model_id, - ModelRegistryHelper, ) from .groq_utils import ( diff --git a/llama_stack/providers/remote/inference/groq/groq_utils.py b/llama_stack/providers/remote/inference/groq/groq_utils.py index d00e5c5a9..2445c1b39 100644 --- a/llama_stack/providers/remote/inference/groq/groq_utils.py +++ b/llama_stack/providers/remote/inference/groq/groq_utils.py @@ -24,10 +24,8 @@ from groq.types.chat.chat_completion_user_message_param import ( ) from groq.types.chat.completion_create_params import CompletionCreateParams from groq.types.shared.function_definition import FunctionDefinition - from llama_models.llama3.api.datatypes import ToolParamDefinition - from llama_stack.apis.common.content_types import ( TextDelta, ToolCallDelta, @@ -47,9 +45,9 @@ from llama_stack.apis.inference import ( ToolPromptFormat, ) from llama_stack.providers.utils.inference.openai_compat import ( - get_sampling_strategy_options, - convert_tool_call, UnparseableToolCall, + convert_tool_call, + get_sampling_strategy_options, ) diff --git a/llama_stack/providers/remote/inference/nvidia/nvidia.py b/llama_stack/providers/remote/inference/nvidia/nvidia.py index b9b43006c..82343513f 100644 --- a/llama_stack/providers/remote/inference/nvidia/nvidia.py +++ b/llama_stack/providers/remote/inference/nvidia/nvidia.py @@ -29,8 +29,8 @@ from llama_stack.apis.inference import ( ToolConfig, ) from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.prompt_adapter import content_has_media diff --git a/llama_stack/providers/remote/inference/nvidia/openai_utils.py b/llama_stack/providers/remote/inference/nvidia/openai_utils.py index 0a62a2ab4..c757c562c 100644 --- a/llama_stack/providers/remote/inference/nvidia/openai_utils.py +++ b/llama_stack/providers/remote/inference/nvidia/openai_utils.py @@ -22,17 +22,35 @@ from llama_models.llama3.api.datatypes import ( from openai import AsyncStream from openai.types.chat import ( ChatCompletionAssistantMessageParam as OpenAIChatCompletionAssistantMessage, +) +from openai.types.chat import ( ChatCompletionChunk as OpenAIChatCompletionChunk, +) +from openai.types.chat import ( ChatCompletionContentPartImageParam as OpenAIChatCompletionContentPartImageParam, +) +from openai.types.chat import ( ChatCompletionContentPartParam as OpenAIChatCompletionContentPartParam, +) +from openai.types.chat import ( ChatCompletionMessageParam as OpenAIChatCompletionMessage, +) +from openai.types.chat import ( ChatCompletionMessageToolCallParam as OpenAIChatCompletionMessageToolCall, +) +from openai.types.chat import ( ChatCompletionSystemMessageParam as OpenAIChatCompletionSystemMessage, +) +from openai.types.chat import ( ChatCompletionToolMessageParam as OpenAIChatCompletionToolMessage, +) +from openai.types.chat import ( ChatCompletionUserMessageParam as OpenAIChatCompletionUserMessage, ) from openai.types.chat.chat_completion import ( Choice as OpenAIChoice, +) +from openai.types.chat.chat_completion import ( ChoiceLogprobs as OpenAIChoiceLogprobs, # same as chat_completion_chunk ChoiceLogprobs ) from openai.types.chat.chat_completion_content_part_image_param import ( @@ -69,7 +87,6 @@ from llama_stack.apis.inference import ( ToolResponseMessage, UserMessage, ) - from llama_stack.providers.utils.inference.prompt_adapter import ( convert_image_content_to_url, ) diff --git a/llama_stack/providers/remote/inference/ollama/config.py b/llama_stack/providers/remote/inference/ollama/config.py index f056b9ab6..a5a4d48ab 100644 --- a/llama_stack/providers/remote/inference/ollama/config.py +++ b/llama_stack/providers/remote/inference/ollama/config.py @@ -8,7 +8,6 @@ from typing import Any, Dict from pydantic import BaseModel - DEFAULT_OLLAMA_URL = "http://localhost:11434" diff --git a/llama_stack/providers/remote/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py index 05a5d2d7a..1c12d0d91 100644 --- a/llama_stack/providers/remote/inference/ollama/ollama.py +++ b/llama_stack/providers/remote/inference/ollama/ollama.py @@ -36,14 +36,14 @@ from llama_stack.apis.inference import ( from llama_stack.apis.models import Model, ModelType from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.model_registry import ( + ModelRegistryHelper, build_model_alias, build_model_alias_with_just_provider_model_id, - ModelRegistryHelper, ) from llama_stack.providers.utils.inference.openai_compat import ( - get_sampling_options, OpenAICompatCompletionChoice, OpenAICompatCompletionResponse, + get_sampling_options, process_chat_completion_response, process_chat_completion_stream_response, process_completion_response, diff --git a/llama_stack/providers/remote/inference/runpod/runpod.py b/llama_stack/providers/remote/inference/runpod/runpod.py index c7b20b9a1..a3c615418 100644 --- a/llama_stack/providers/remote/inference/runpod/runpod.py +++ b/llama_stack/providers/remote/inference/runpod/runpod.py @@ -8,14 +8,12 @@ from typing import AsyncGenerator from llama_models.llama3.api.chat_format import ChatFormat from llama_models.llama3.api.datatypes import Message from llama_models.llama3.api.tokenizer import Tokenizer - from openai import OpenAI from llama_stack.apis.inference import * # noqa: F403 # from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper - from llama_stack.providers.utils.inference.openai_compat import ( get_sampling_options, process_chat_completion_response, diff --git a/llama_stack/providers/remote/inference/sambanova/sambanova.py b/llama_stack/providers/remote/inference/sambanova/sambanova.py index 18a78e69c..3546ee977 100644 --- a/llama_stack/providers/remote/inference/sambanova/sambanova.py +++ b/llama_stack/providers/remote/inference/sambanova/sambanova.py @@ -24,8 +24,8 @@ from llama_stack.apis.common.content_types import ( ) from llama_stack.apis.inference import * # noqa: F403 from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( process_chat_completion_stream_response, diff --git a/llama_stack/providers/remote/inference/sample/sample.py b/llama_stack/providers/remote/inference/sample/sample.py index 51ce879eb..106381618 100644 --- a/llama_stack/providers/remote/inference/sample/sample.py +++ b/llama_stack/providers/remote/inference/sample/sample.py @@ -6,6 +6,7 @@ from llama_stack.apis.inference import Inference from llama_stack.apis.models import Model + from .config import SampleConfig diff --git a/llama_stack/providers/remote/inference/tgi/tgi.py b/llama_stack/providers/remote/inference/tgi/tgi.py index 97a6621fb..72eaa6c31 100644 --- a/llama_stack/providers/remote/inference/tgi/tgi.py +++ b/llama_stack/providers/remote/inference/tgi/tgi.py @@ -33,13 +33,13 @@ from llama_stack.apis.inference import ( from llama_stack.apis.models import Model from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( - get_sampling_options, OpenAICompatCompletionChoice, OpenAICompatCompletionResponse, + get_sampling_options, process_chat_completion_response, process_chat_completion_stream_response, process_completion_response, diff --git a/llama_stack/providers/remote/inference/together/together.py b/llama_stack/providers/remote/inference/together/together.py index a165b01d9..916e64ad4 100644 --- a/llama_stack/providers/remote/inference/together/together.py +++ b/llama_stack/providers/remote/inference/together/together.py @@ -30,8 +30,8 @@ from llama_stack.apis.inference import ( ) from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( convert_message_to_openai_dict, diff --git a/llama_stack/providers/remote/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py index 3574768b5..8f9cf68a8 100644 --- a/llama_stack/providers/remote/inference/vllm/vllm.py +++ b/llama_stack/providers/remote/inference/vllm/vllm.py @@ -13,10 +13,14 @@ from llama_models.llama3.api.tokenizer import Tokenizer from llama_models.sku_list import all_registered_models from openai import OpenAI -from llama_stack.apis.common.content_types import InterleavedContent, ToolCallDelta, ToolCallParseStatus, TextDelta +from llama_stack.apis.common.content_types import InterleavedContent, TextDelta, ToolCallDelta, ToolCallParseStatus from llama_stack.apis.inference import ( ChatCompletionRequest, ChatCompletionResponse, + ChatCompletionResponseEvent, + ChatCompletionResponseEventType, + ChatCompletionResponseStreamChunk, + CompletionMessage, CompletionRequest, CompletionResponse, CompletionResponseStreamChunk, @@ -31,26 +35,22 @@ from llama_stack.apis.inference import ( ToolConfig, ToolDefinition, ToolPromptFormat, - CompletionMessage, - ChatCompletionResponseEventType, - ChatCompletionResponseStreamChunk, - ChatCompletionResponseEvent, ) from llama_stack.apis.models import Model, ModelType from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.model_registry import ( - build_model_alias, ModelRegistryHelper, + build_model_alias, ) from llama_stack.providers.utils.inference.openai_compat import ( - convert_message_to_openai_dict, - get_sampling_options, - process_completion_response, - process_completion_stream_response, OpenAICompatCompletionResponse, UnparseableToolCall, + convert_message_to_openai_dict, convert_tool_call, + get_sampling_options, process_chat_completion_stream_response, + process_completion_response, + process_completion_stream_response, ) from llama_stack.providers.utils.inference.prompt_adapter import ( completion_request_to_prompt, diff --git a/llama_stack/providers/remote/safety/bedrock/bedrock.py b/llama_stack/providers/remote/safety/bedrock/bedrock.py index b9d9b9825..c8cd129f2 100644 --- a/llama_stack/providers/remote/safety/bedrock/bedrock.py +++ b/llama_stack/providers/remote/safety/bedrock/bedrock.py @@ -6,11 +6,9 @@ import json import logging - from typing import Any, Dict, List from llama_stack.apis.inference import Message - from llama_stack.apis.safety import ( RunShieldResponse, Safety, @@ -23,7 +21,6 @@ from llama_stack.providers.utils.bedrock.client import create_bedrock_client from .config import BedrockSafetyConfig - logger = logging.getLogger(__name__) diff --git a/llama_stack/providers/remote/safety/sample/sample.py b/llama_stack/providers/remote/safety/sample/sample.py index 180e6c3b5..7645c69e9 100644 --- a/llama_stack/providers/remote/safety/sample/sample.py +++ b/llama_stack/providers/remote/safety/sample/sample.py @@ -6,6 +6,7 @@ from llama_stack.apis.safety import Safety from llama_stack.apis.shields import Shield + from .config import SampleConfig diff --git a/llama_stack/providers/remote/tool_runtime/model_context_protocol/__init__.py b/llama_stack/providers/remote/tool_runtime/model_context_protocol/__init__.py index 3b05f5632..2ddf7b4fe 100644 --- a/llama_stack/providers/remote/tool_runtime/model_context_protocol/__init__.py +++ b/llama_stack/providers/remote/tool_runtime/model_context_protocol/__init__.py @@ -7,7 +7,6 @@ from pydantic import BaseModel from .config import ModelContextProtocolConfig - from .model_context_protocol import ModelContextProtocolToolRuntimeImpl diff --git a/llama_stack/providers/remote/vector_io/chroma/chroma.py b/llama_stack/providers/remote/vector_io/chroma/chroma.py index 3ebdd089b..47ef30b5a 100644 --- a/llama_stack/providers/remote/vector_io/chroma/chroma.py +++ b/llama_stack/providers/remote/vector_io/chroma/chroma.py @@ -21,6 +21,7 @@ from llama_stack.providers.utils.memory.vector_store import ( EmbeddingIndex, VectorDBWithIndex, ) + from .config import ChromaRemoteImplConfig log = logging.getLogger(__name__) diff --git a/llama_stack/providers/remote/vector_io/pgvector/pgvector.py b/llama_stack/providers/remote/vector_io/pgvector/pgvector.py index eb1c9aab1..693aacd76 100644 --- a/llama_stack/providers/remote/vector_io/pgvector/pgvector.py +++ b/llama_stack/providers/remote/vector_io/pgvector/pgvector.py @@ -10,15 +10,13 @@ from typing import Any, Dict, List, Optional, Tuple import psycopg2 from numpy.typing import NDArray from psycopg2 import sql -from psycopg2.extras import execute_values, Json - +from psycopg2.extras import Json, execute_values from pydantic import BaseModel, TypeAdapter from llama_stack.apis.inference import InterleavedContent from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate - from llama_stack.providers.utils.memory.vector_store import ( EmbeddingIndex, VectorDBWithIndex, diff --git a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py index e7ad136eb..b2eae3dad 100644 --- a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py +++ b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py @@ -20,6 +20,7 @@ from llama_stack.providers.utils.memory.vector_store import ( EmbeddingIndex, VectorDBWithIndex, ) + from .config import QdrantConfig log = logging.getLogger(__name__) diff --git a/llama_stack/providers/remote/vector_io/sample/sample.py b/llama_stack/providers/remote/vector_io/sample/sample.py index e311be39d..b0ba50315 100644 --- a/llama_stack/providers/remote/vector_io/sample/sample.py +++ b/llama_stack/providers/remote/vector_io/sample/sample.py @@ -6,6 +6,7 @@ from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import VectorIO + from .config import SampleConfig diff --git a/llama_stack/providers/remote/vector_io/weaviate/weaviate.py b/llama_stack/providers/remote/vector_io/weaviate/weaviate.py index c57b57609..c4d3c39ac 100644 --- a/llama_stack/providers/remote/vector_io/weaviate/weaviate.py +++ b/llama_stack/providers/remote/vector_io/weaviate/weaviate.py @@ -5,7 +5,6 @@ # the root directory of this source tree. import json import logging - from typing import Any, Dict, List, Optional import weaviate diff --git a/llama_stack/providers/tests/agents/conftest.py b/llama_stack/providers/tests/agents/conftest.py index 5759b77c5..3a6ce278a 100644 --- a/llama_stack/providers/tests/agents/conftest.py +++ b/llama_stack/providers/tests/agents/conftest.py @@ -13,7 +13,6 @@ from ..conftest import ( ) from ..inference.fixtures import INFERENCE_FIXTURES from ..safety.fixtures import SAFETY_FIXTURES, safety_model_from_shield - from ..tools.fixtures import TOOL_RUNTIME_FIXTURES from ..vector_io.fixtures import VECTOR_IO_FIXTURES from .fixtures import AGENTS_FIXTURES diff --git a/llama_stack/providers/tests/agents/test_agents.py b/llama_stack/providers/tests/agents/test_agents.py index 37d0c04b5..45b276cc3 100644 --- a/llama_stack/providers/tests/agents/test_agents.py +++ b/llama_stack/providers/tests/agents/test_agents.py @@ -23,7 +23,6 @@ from llama_stack.apis.agents import ( ToolExecutionStep, Turn, ) - from llama_stack.apis.inference import CompletionMessage, UserMessage from llama_stack.apis.safety import ViolationLevel from llama_stack.providers.datatypes import Api diff --git a/llama_stack/providers/tests/agents/test_persistence.py b/llama_stack/providers/tests/agents/test_persistence.py index a1d69c9ca..f02279e8d 100644 --- a/llama_stack/providers/tests/agents/test_persistence.py +++ b/llama_stack/providers/tests/agents/test_persistence.py @@ -13,7 +13,6 @@ from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig from .fixtures import pick_inference_model - from .utils import create_agent_session diff --git a/llama_stack/providers/tests/conftest.py b/llama_stack/providers/tests/conftest.py index cf88e8fe8..d3e715b7e 100644 --- a/llama_stack/providers/tests/conftest.py +++ b/llama_stack/providers/tests/conftest.py @@ -6,13 +6,11 @@ import os from collections import defaultdict - from pathlib import Path from typing import Any, Dict, List, Optional import pytest import yaml - from dotenv import load_dotenv from pydantic import BaseModel, Field from termcolor import colored diff --git a/llama_stack/providers/tests/datasetio/fixtures.py b/llama_stack/providers/tests/datasetio/fixtures.py index d288198ca..27aedb645 100644 --- a/llama_stack/providers/tests/datasetio/fixtures.py +++ b/llama_stack/providers/tests/datasetio/fixtures.py @@ -8,7 +8,6 @@ import pytest import pytest_asyncio from llama_stack.distribution.datatypes import Api, Provider - from llama_stack.providers.tests.resolver import construct_stack_for_test from ..conftest import ProviderFixture, remote_stack_fixture diff --git a/llama_stack/providers/tests/eval/conftest.py b/llama_stack/providers/tests/eval/conftest.py index 84eae2efa..c1da6ba42 100644 --- a/llama_stack/providers/tests/eval/conftest.py +++ b/llama_stack/providers/tests/eval/conftest.py @@ -7,16 +7,14 @@ import pytest from ..agents.fixtures import AGENTS_FIXTURES - from ..conftest import get_provider_fixture_overrides - from ..datasetio.fixtures import DATASETIO_FIXTURES from ..inference.fixtures import INFERENCE_FIXTURES from ..safety.fixtures import SAFETY_FIXTURES from ..scoring.fixtures import SCORING_FIXTURES from ..tools.fixtures import TOOL_RUNTIME_FIXTURES -from .fixtures import EVAL_FIXTURES from ..vector_io.fixtures import VECTOR_IO_FIXTURES +from .fixtures import EVAL_FIXTURES DEFAULT_PROVIDER_COMBINATIONS = [ pytest.param( diff --git a/llama_stack/providers/tests/eval/fixtures.py b/llama_stack/providers/tests/eval/fixtures.py index 009e65fb3..c6d15bbf5 100644 --- a/llama_stack/providers/tests/eval/fixtures.py +++ b/llama_stack/providers/tests/eval/fixtures.py @@ -8,8 +8,8 @@ import pytest import pytest_asyncio from llama_stack.distribution.datatypes import Api, ModelInput, Provider - from llama_stack.providers.tests.resolver import construct_stack_for_test + from ..conftest import ProviderFixture, remote_stack_fixture diff --git a/llama_stack/providers/tests/eval/test_eval.py b/llama_stack/providers/tests/eval/test_eval.py index 40835bf53..ec3d08728 100644 --- a/llama_stack/providers/tests/eval/test_eval.py +++ b/llama_stack/providers/tests/eval/test_eval.py @@ -9,7 +9,6 @@ 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.eval.eval import ( AppEvalTaskConfig, BenchmarkEvalTaskConfig, @@ -19,6 +18,7 @@ from llama_stack.apis.inference import SamplingParams from llama_stack.apis.scoring_functions import LLMAsJudgeScoringFnParams from llama_stack.distribution.datatypes import Api from llama_stack.providers.tests.datasetio.test_datasetio import register_dataset + from .constants import JUDGE_PROMPT # How to run this test: diff --git a/llama_stack/providers/tests/inference/fixtures.py b/llama_stack/providers/tests/inference/fixtures.py index b33a217bb..2a782befc 100644 --- a/llama_stack/providers/tests/inference/fixtures.py +++ b/llama_stack/providers/tests/inference/fixtures.py @@ -11,13 +11,11 @@ import pytest_asyncio from llama_stack.apis.models import ModelInput, ModelType from llama_stack.distribution.datatypes import Api, Provider - from llama_stack.providers.inline.inference.meta_reference import ( MetaReferenceInferenceConfig, ) from llama_stack.providers.inline.inference.vllm import VLLMConfig from llama_stack.providers.remote.inference.bedrock import BedrockConfig - from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig from llama_stack.providers.remote.inference.groq import GroqConfig diff --git a/llama_stack/providers/tests/inference/groq/test_groq_utils.py b/llama_stack/providers/tests/inference/groq/test_groq_utils.py index a28dd308e..3eba991c1 100644 --- a/llama_stack/providers/tests/inference/groq/test_groq_utils.py +++ b/llama_stack/providers/tests/inference/groq/test_groq_utils.py @@ -10,11 +10,13 @@ import pytest from groq.types.chat.chat_completion import ChatCompletion, Choice from groq.types.chat.chat_completion_chunk import ( ChatCompletionChunk, - Choice as StreamChoice, ChoiceDelta, ChoiceDeltaToolCall, ChoiceDeltaToolCallFunction, ) +from groq.types.chat.chat_completion_chunk import ( + Choice as StreamChoice, +) from groq.types.chat.chat_completion_message import ChatCompletionMessage from groq.types.chat.chat_completion_message_tool_call import ( ChatCompletionMessageToolCall, @@ -23,6 +25,7 @@ from groq.types.chat.chat_completion_message_tool_call import ( from groq.types.shared.function_definition import FunctionDefinition from llama_models.datatypes import GreedySamplingStrategy, TopPSamplingStrategy from llama_models.llama3.api.datatypes import ToolParamDefinition + from llama_stack.apis.common.content_types import ToolCallParseStatus from llama_stack.apis.inference import ( ChatCompletionRequest, diff --git a/llama_stack/providers/tests/inference/groq/test_init.py b/llama_stack/providers/tests/inference/groq/test_init.py index d23af5934..4cdd3bfd5 100644 --- a/llama_stack/providers/tests/inference/groq/test_init.py +++ b/llama_stack/providers/tests/inference/groq/test_init.py @@ -5,11 +5,11 @@ # the root directory of this source tree. import pytest + from llama_stack.apis.inference import Inference from llama_stack.providers.remote.inference.groq import get_adapter_impl from llama_stack.providers.remote.inference.groq.config import GroqConfig from llama_stack.providers.remote.inference.groq.groq import GroqInferenceAdapter - from llama_stack.providers.remote.inference.ollama import OllamaImplConfig diff --git a/llama_stack/providers/tests/inference/test_model_registration.py b/llama_stack/providers/tests/inference/test_model_registration.py index 664564d22..7c41b07ef 100644 --- a/llama_stack/providers/tests/inference/test_model_registration.py +++ b/llama_stack/providers/tests/inference/test_model_registration.py @@ -8,7 +8,6 @@ from unittest.mock import AsyncMock, patch import pytest - # How to run this test: # # torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="Llama3.1-8B-Instruct" diff --git a/llama_stack/providers/tests/inference/test_text_inference.py b/llama_stack/providers/tests/inference/test_text_inference.py index 6a7259123..14ed2fc4b 100644 --- a/llama_stack/providers/tests/inference/test_text_inference.py +++ b/llama_stack/providers/tests/inference/test_text_inference.py @@ -6,7 +6,6 @@ import pytest - from llama_models.llama3.api.datatypes import ( SamplingParams, StopReason, @@ -15,7 +14,6 @@ from llama_models.llama3.api.datatypes import ( ToolParamDefinition, ToolPromptFormat, ) - from pydantic import BaseModel, ValidationError from llama_stack.apis.common.content_types import ToolCallParseStatus @@ -35,7 +33,6 @@ from llama_stack.apis.models import ListModelsResponse, Model from .utils import group_chunks - # How to run this test: # # pytest -v -s llama_stack/providers/tests/inference/test_text_inference.py diff --git a/llama_stack/providers/tests/post_training/conftest.py b/llama_stack/providers/tests/post_training/conftest.py index 3cd60e53a..b6d95444b 100644 --- a/llama_stack/providers/tests/post_training/conftest.py +++ b/llama_stack/providers/tests/post_training/conftest.py @@ -7,9 +7,7 @@ import pytest from ..conftest import get_provider_fixture_overrides - from ..datasetio.fixtures import DATASETIO_FIXTURES - from .fixtures import POST_TRAINING_FIXTURES DEFAULT_PROVIDER_COMBINATIONS = [ diff --git a/llama_stack/providers/tests/post_training/fixtures.py b/llama_stack/providers/tests/post_training/fixtures.py index fd8a9e4f6..7c3ff3ddb 100644 --- a/llama_stack/providers/tests/post_training/fixtures.py +++ b/llama_stack/providers/tests/post_training/fixtures.py @@ -8,13 +8,10 @@ import pytest import pytest_asyncio from llama_stack.apis.common.content_types import URL - from llama_stack.apis.common.type_system import StringType from llama_stack.apis.datasets import DatasetInput from llama_stack.apis.models import ModelInput - from llama_stack.distribution.datatypes import Api, Provider - from llama_stack.providers.tests.resolver import construct_stack_for_test from ..conftest import ProviderFixture diff --git a/llama_stack/providers/tests/report.py b/llama_stack/providers/tests/report.py index b7a238908..3901dc2e3 100644 --- a/llama_stack/providers/tests/report.py +++ b/llama_stack/providers/tests/report.py @@ -12,10 +12,8 @@ import pytest from llama_models.datatypes import CoreModelId from llama_models.sku_list import all_registered_models from pytest import ExitCode - from pytest_html.basereport import _process_outcome - INFERENCE_APIS = ["chat_completion"] FUNCTIONALITIES = ["streaming", "structured_output", "tool_calling"] SUPPORTED_MODELS = { diff --git a/llama_stack/providers/tests/safety/conftest.py b/llama_stack/providers/tests/safety/conftest.py index 10a8517fc..3e46f0d50 100644 --- a/llama_stack/providers/tests/safety/conftest.py +++ b/llama_stack/providers/tests/safety/conftest.py @@ -7,11 +7,9 @@ import pytest from ..conftest import get_provider_fixture_overrides - from ..inference.fixtures import INFERENCE_FIXTURES from .fixtures import SAFETY_FIXTURES - DEFAULT_PROVIDER_COMBINATIONS = [ pytest.param( { diff --git a/llama_stack/providers/tests/safety/fixtures.py b/llama_stack/providers/tests/safety/fixtures.py index 32883bfab..a0c00ee7c 100644 --- a/llama_stack/providers/tests/safety/fixtures.py +++ b/llama_stack/providers/tests/safety/fixtures.py @@ -8,14 +8,11 @@ import pytest import pytest_asyncio from llama_stack.apis.models import ModelInput - from llama_stack.apis.shields import ShieldInput - from llama_stack.distribution.datatypes import Api, Provider from llama_stack.providers.inline.safety.llama_guard import LlamaGuardConfig from llama_stack.providers.inline.safety.prompt_guard import PromptGuardConfig from llama_stack.providers.remote.safety.bedrock import BedrockSafetyConfig - from llama_stack.providers.tests.resolver import construct_stack_for_test from ..conftest import ProviderFixture, remote_stack_fixture diff --git a/llama_stack/providers/tests/scoring/conftest.py b/llama_stack/providers/tests/scoring/conftest.py index 450f65695..9278d3c2d 100644 --- a/llama_stack/providers/tests/scoring/conftest.py +++ b/llama_stack/providers/tests/scoring/conftest.py @@ -7,7 +7,6 @@ import pytest from ..conftest import get_provider_fixture_overrides - from ..datasetio.fixtures import DATASETIO_FIXTURES from ..inference.fixtures import INFERENCE_FIXTURES from .fixtures import SCORING_FIXTURES diff --git a/llama_stack/providers/tests/scoring/fixtures.py b/llama_stack/providers/tests/scoring/fixtures.py index 2cf32b1e2..09f31cbc2 100644 --- a/llama_stack/providers/tests/scoring/fixtures.py +++ b/llama_stack/providers/tests/scoring/fixtures.py @@ -8,10 +8,10 @@ import pytest import pytest_asyncio from llama_stack.apis.models import ModelInput - from llama_stack.distribution.datatypes import Api, Provider from llama_stack.providers.inline.scoring.braintrust import BraintrustScoringConfig 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 diff --git a/llama_stack/providers/tests/vector_io/conftest.py b/llama_stack/providers/tests/vector_io/conftest.py index 3a02ac712..3da64ff2e 100644 --- a/llama_stack/providers/tests/vector_io/conftest.py +++ b/llama_stack/providers/tests/vector_io/conftest.py @@ -11,11 +11,9 @@ from ..conftest import ( get_provider_fixture_overrides_from_test_config, get_test_config_for_api, ) - from ..inference.fixtures import INFERENCE_FIXTURES from .fixtures import VECTOR_IO_FIXTURES - DEFAULT_PROVIDER_COMBINATIONS = [ pytest.param( { diff --git a/llama_stack/providers/tests/vector_io/fixtures.py b/llama_stack/providers/tests/vector_io/fixtures.py index 54a76141f..60d174d9e 100644 --- a/llama_stack/providers/tests/vector_io/fixtures.py +++ b/llama_stack/providers/tests/vector_io/fixtures.py @@ -12,7 +12,6 @@ import pytest_asyncio from llama_stack.apis.models import ModelInput, ModelType from llama_stack.distribution.datatypes import Api, Provider - from llama_stack.providers.inline.vector_io.chroma import ChromaInlineImplConfig from llama_stack.providers.inline.vector_io.faiss import FaissImplConfig from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConfig diff --git a/llama_stack/providers/tests/vector_io/test_vector_io.py b/llama_stack/providers/tests/vector_io/test_vector_io.py index 81b080f63..77bc24a21 100644 --- a/llama_stack/providers/tests/vector_io/test_vector_io.py +++ b/llama_stack/providers/tests/vector_io/test_vector_io.py @@ -9,10 +9,8 @@ import uuid import pytest from llama_stack.apis.tools import RAGDocument - from llama_stack.apis.vector_dbs import ListVectorDBsResponse, VectorDB from llama_stack.apis.vector_io import QueryChunksResponse - from llama_stack.providers.utils.memory.vector_store import make_overlapped_chunks # How to run this test: diff --git a/llama_stack/providers/tests/vector_io/test_vector_store.py b/llama_stack/providers/tests/vector_io/test_vector_store.py index 2a41a8982..e0d340657 100644 --- a/llama_stack/providers/tests/vector_io/test_vector_store.py +++ b/llama_stack/providers/tests/vector_io/test_vector_store.py @@ -12,8 +12,7 @@ from pathlib import Path import pytest from llama_stack.apis.tools import RAGDocument - -from llama_stack.providers.utils.memory.vector_store import content_from_doc, URL +from llama_stack.providers.utils.memory.vector_store import URL, content_from_doc DUMMY_PDF_PATH = Path(os.path.abspath(__file__)).parent / "fixtures" / "dummy.pdf" diff --git a/llama_stack/providers/utils/common/data_schema_validator.py b/llama_stack/providers/utils/common/data_schema_validator.py index 8b5618950..3d14c4148 100644 --- a/llama_stack/providers/utils/common/data_schema_validator.py +++ b/llama_stack/providers/utils/common/data_schema_validator.py @@ -12,7 +12,6 @@ from llama_stack.apis.common.type_system import ( CompletionInputType, StringType, ) - from llama_stack.distribution.datatypes import Api diff --git a/llama_stack/providers/utils/datasetio/url_utils.py b/llama_stack/providers/utils/datasetio/url_utils.py index da1e84d4d..f54cb55eb 100644 --- a/llama_stack/providers/utils/datasetio/url_utils.py +++ b/llama_stack/providers/utils/datasetio/url_utils.py @@ -11,7 +11,6 @@ from urllib.parse import unquote import pandas from llama_stack.apis.common.content_types import URL - from llama_stack.providers.utils.memory.vector_store import parse_data_url diff --git a/llama_stack/providers/utils/inference/model_registry.py b/llama_stack/providers/utils/inference/model_registry.py index dea951395..9345da949 100644 --- a/llama_stack/providers/utils/inference/model_registry.py +++ b/llama_stack/providers/utils/inference/model_registry.py @@ -11,7 +11,6 @@ from llama_models.sku_list import all_registered_models from llama_stack.apis.models.models import ModelType from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate - from llama_stack.providers.utils.inference import ( ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR, ) diff --git a/llama_stack/providers/utils/inference/openai_compat.py b/llama_stack/providers/utils/inference/openai_compat.py index 7480ff2c7..00e291e8f 100644 --- a/llama_stack/providers/utils/inference/openai_compat.py +++ b/llama_stack/providers/utils/inference/openai_compat.py @@ -13,7 +13,6 @@ from llama_models.datatypes import ( TopKSamplingStrategy, TopPSamplingStrategy, ) - from llama_models.llama3.api.chat_format import ChatFormat from llama_models.llama3.api.datatypes import StopReason, ToolCall from openai.types.chat import ChatCompletionMessageToolCall @@ -26,7 +25,6 @@ from llama_stack.apis.common.content_types import ( ToolCallDelta, ToolCallParseStatus, ) - from llama_stack.apis.inference import ( ChatCompletionRequest, ChatCompletionResponse, @@ -39,7 +37,6 @@ from llama_stack.apis.inference import ( Message, TokenLogProbs, ) - from llama_stack.providers.utils.inference.prompt_adapter import ( convert_image_content_to_url, ) diff --git a/llama_stack/providers/utils/inference/prompt_adapter.py b/llama_stack/providers/utils/inference/prompt_adapter.py index 57875e64b..15149e059 100644 --- a/llama_stack/providers/utils/inference/prompt_adapter.py +++ b/llama_stack/providers/utils/inference/prompt_adapter.py @@ -13,7 +13,7 @@ import re from typing import List, Optional, Tuple, Union import httpx -from llama_models.datatypes import is_multimodal, ModelFamily +from llama_models.datatypes import ModelFamily, is_multimodal from llama_models.llama3.api.chat_format import ChatFormat from llama_models.llama3.api.datatypes import ( RawContent, @@ -47,9 +47,9 @@ from llama_stack.apis.inference import ( ResponseFormat, ResponseFormatType, SystemMessage, + SystemMessageBehavior, ToolChoice, UserMessage, - SystemMessageBehavior, ) from llama_stack.providers.utils.inference import supported_inference_models diff --git a/llama_stack/providers/utils/kvstore/sqlite/sqlite.py b/llama_stack/providers/utils/kvstore/sqlite/sqlite.py index e7a33503b..bc0488aac 100644 --- a/llama_stack/providers/utils/kvstore/sqlite/sqlite.py +++ b/llama_stack/providers/utils/kvstore/sqlite/sqlite.py @@ -5,7 +5,6 @@ # the root directory of this source tree. import os - from datetime import datetime from typing import List, Optional diff --git a/llama_stack/providers/utils/memory/vector_store.py b/llama_stack/providers/utils/memory/vector_store.py index 310db18b0..1ac1cf8d5 100644 --- a/llama_stack/providers/utils/memory/vector_store.py +++ b/llama_stack/providers/utils/memory/vector_store.py @@ -15,13 +15,14 @@ from urllib.parse import unquote import chardet import httpx import numpy as np - from llama_models.llama3.api.tokenizer import Tokenizer +from numpy.typing import NDArray +from pypdf import PdfReader from llama_stack.apis.common.content_types import ( + URL, InterleavedContent, TextContentItem, - URL, ) from llama_stack.apis.tools import RAGDocument from llama_stack.apis.vector_dbs import VectorDB @@ -30,9 +31,6 @@ from llama_stack.providers.datatypes import Api from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) -from numpy.typing import NDArray - -from pypdf import PdfReader log = logging.getLogger(__name__) diff --git a/llama_stack/scripts/distro_codegen.py b/llama_stack/scripts/distro_codegen.py index c73c15d41..825a039ef 100644 --- a/llama_stack/scripts/distro_codegen.py +++ b/llama_stack/scripts/distro_codegen.py @@ -16,11 +16,10 @@ from typing import Iterator from rich.progress import Progress, SpinnerColumn, TextColumn from llama_stack.distribution.build import ( - get_provider_dependencies, SERVER_DEPENDENCIES, + get_provider_dependencies, ) - REPO_ROOT = Path(__file__).parent.parent.parent diff --git a/llama_stack/templates/dell/dell.py b/llama_stack/templates/dell/dell.py index 5781da7f4..116fbd285 100644 --- a/llama_stack/templates/dell/dell.py +++ b/llama_stack/templates/dell/dell.py @@ -15,7 +15,6 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) - from llama_stack.templates.template import DistributionTemplate, RunConfigSettings diff --git a/llama_stack/templates/sambanova/sambanova.py b/llama_stack/templates/sambanova/sambanova.py index 70b54b010..6d7477c8e 100644 --- a/llama_stack/templates/sambanova/sambanova.py +++ b/llama_stack/templates/sambanova/sambanova.py @@ -16,7 +16,6 @@ from llama_stack.distribution.datatypes import ( ) from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig from llama_stack.providers.remote.inference.sambanova.sambanova import MODEL_ALIASES - from llama_stack.templates.template import DistributionTemplate, RunConfigSettings diff --git a/llama_stack/templates/template.py b/llama_stack/templates/template.py index 04a09741c..cb5b07be3 100644 --- a/llama_stack/templates/template.py +++ b/llama_stack/templates/template.py @@ -9,6 +9,7 @@ from typing import Dict, List, Literal, Optional, Tuple import jinja2 import yaml +from pydantic import BaseModel, Field from llama_stack.apis.models.models import ModelType from llama_stack.distribution.datatypes import ( @@ -24,7 +25,6 @@ from llama_stack.distribution.datatypes import ( from llama_stack.distribution.distribution import get_provider_registry from llama_stack.distribution.utils.dynamic import instantiate_class_type from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig -from pydantic import BaseModel, Field class RunConfigSettings(BaseModel): diff --git a/tests/client-sdk/agents/test_agents.py b/tests/client-sdk/agents/test_agents.py index d14a7003f..f42341f72 100644 --- a/tests/client-sdk/agents/test_agents.py +++ b/tests/client-sdk/agents/test_agents.py @@ -13,12 +13,14 @@ from llama_stack_client.lib.agents.agent import Agent from llama_stack_client.lib.agents.client_tool import ClientTool from llama_stack_client.lib.agents.event_logger import EventLogger from llama_stack_client.types import ToolResponseMessage -from llama_stack_client.types.shared_params.agent_config import AgentConfig, ToolConfig from llama_stack_client.types.agents.turn_create_params import Document as AgentDocument from llama_stack_client.types.memory_insert_params import Document from llama_stack_client.types.shared.completion_message import CompletionMessage +from llama_stack_client.types.shared_params.agent_config import AgentConfig, ToolConfig from llama_stack_client.types.tool_def_param import Parameter -from llama_stack.apis.agents.agents import AgentConfig as Server__AgentConfig, ToolChoice + +from llama_stack.apis.agents.agents import AgentConfig as Server__AgentConfig +from llama_stack.apis.agents.agents import ToolChoice class TestClientTool(ClientTool): diff --git a/tests/client-sdk/conftest.py b/tests/client-sdk/conftest.py index 8c44242fe..b397f7ab3 100644 --- a/tests/client-sdk/conftest.py +++ b/tests/client-sdk/conftest.py @@ -6,11 +6,11 @@ import os import pytest +from llama_stack_client import LlamaStackClient +from report import Report from llama_stack import LlamaStackAsLibraryClient from llama_stack.providers.tests.env import get_env_or_fail -from llama_stack_client import LlamaStackClient -from report import Report def pytest_configure(config): diff --git a/tests/client-sdk/report.py b/tests/client-sdk/report.py index 5e8203ecb..543562541 100644 --- a/tests/client-sdk/report.py +++ b/tests/client-sdk/report.py @@ -22,15 +22,13 @@ from llama_models.sku_list import ( llama3_instruct_models, safety_models, ) +from metadata import API_MAPS +from pytest import CollectReport +from termcolor import cprint from llama_stack.providers.datatypes import Api from llama_stack.providers.tests.env import get_env_or_fail -from metadata import API_MAPS - -from pytest import CollectReport -from termcolor import cprint - def featured_models(): models = [ diff --git a/tests/client-sdk/tool_runtime/test_rag_tool.py b/tests/client-sdk/tool_runtime/test_rag_tool.py index f776bd0a9..40940f1ef 100644 --- a/tests/client-sdk/tool_runtime/test_rag_tool.py +++ b/tests/client-sdk/tool_runtime/test_rag_tool.py @@ -7,7 +7,6 @@ import random import pytest - from llama_stack_client.types import Document