fix: rename llama_stack_api dir (#4155)

# What does this PR do?

the directory structure was src/llama-stack-api/llama_stack_api

instead it should just be src/llama_stack_api to match the other
packages.

update the structure and pyproject/linting config

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

src/llama_stack/providers/remote/datasetio/huggingface/huggingface.py

@@ -6,10 +6,9 @@
 from typing import Any
 from urllib.parse import parse_qs, urlparse
 
-from llama_stack_api import Dataset, DatasetIO, DatasetsProtocolPrivate, PaginatedResponse
-
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.pagination import paginate_records
+from llama_stack_api import Dataset, DatasetIO, DatasetsProtocolPrivate, PaginatedResponse
 
 from .config import HuggingfaceDatasetIOConfig
 

src/llama_stack/providers/remote/datasetio/nvidia/datasetio.py

@@ -7,6 +7,7 @@
 from typing import Any
 
 import aiohttp
+
 from llama_stack_api import URL, Dataset, PaginatedResponse, ParamType
 
 from .config import NvidiaDatasetIOConfig

src/llama_stack/providers/remote/eval/nvidia/eval.py

@@ -6,6 +6,8 @@
 from typing import Any
 
 import requests
+
+from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 from llama_stack_api import (
     Agents,
     Benchmark,
@@ -22,8 +24,6 @@ from llama_stack_api import (
     ScoringResult,
 )
 
-from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
-
 from .config import NVIDIAEvalConfig
 
 DEFAULT_NAMESPACE = "nvidia"

src/llama_stack/providers/remote/files/openai/files.py

@@ -8,6 +8,12 @@ from datetime import UTC, datetime
 from typing import Annotated, Any
 
 from fastapi import Depends, File, Form, Response, UploadFile
+
+from llama_stack.core.datatypes import AccessRule
+from llama_stack.providers.utils.files.form_data import parse_expires_after
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 from llama_stack_api import (
     ExpiresAfter,
     Files,
@@ -18,12 +24,6 @@ from llama_stack_api import (
     Order,
     ResourceNotFoundError,
 )
-
-from llama_stack.core.datatypes import AccessRule
-from llama_stack.providers.utils.files.form_data import parse_expires_after
-from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
-from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
-from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 from openai import OpenAI
 
 from .config import OpenAIFilesImplConfig

src/llama_stack/providers/remote/files/s3/files.py

@@ -17,6 +17,12 @@ from fastapi import Depends, File, Form, Response, UploadFile
 if TYPE_CHECKING:
     from mypy_boto3_s3.client import S3Client
 
+from llama_stack.core.datatypes import AccessRule
+from llama_stack.core.id_generation import generate_object_id
+from llama_stack.providers.utils.files.form_data import parse_expires_after
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 from llama_stack_api import (
     ExpiresAfter,
     Files,
@@ -28,13 +34,6 @@ from llama_stack_api import (
     ResourceNotFoundError,
 )
 
-from llama_stack.core.datatypes import AccessRule
-from llama_stack.core.id_generation import generate_object_id
-from llama_stack.providers.utils.files.form_data import parse_expires_after
-from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
-from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
-from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
-
 from .config import S3FilesImplConfig
 
 # TODO: provider data for S3 credentials

src/llama_stack/providers/remote/inference/anthropic/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class AnthropicProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/azure/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, HttpUrl, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class AzureProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/bedrock/bedrock.py

@@ -6,6 +6,11 @@
 
 from collections.abc import AsyncIterator, Iterable
 
+from openai import AuthenticationError
+
+from llama_stack.core.telemetry.tracing import get_current_span
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
@@ -15,11 +20,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
-from openai import AuthenticationError
-
-from llama_stack.core.telemetry.tracing import get_current_span
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import BedrockConfig
 

src/llama_stack/providers/remote/inference/cerebras/cerebras.py

@@ -6,13 +6,12 @@
 
 from urllib.parse import urljoin
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import CerebrasImplConfig
 
 

src/llama_stack/providers/remote/inference/cerebras/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 DEFAULT_BASE_URL = "https://api.cerebras.ai"
 

src/llama_stack/providers/remote/inference/databricks/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class DatabricksProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/databricks/databricks.py

@@ -7,10 +7,10 @@
 from collections.abc import Iterable
 
 from databricks.sdk import WorkspaceClient
-from llama_stack_api import OpenAICompletion, OpenAICompletionRequestWithExtraBody
 
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import OpenAICompletion, OpenAICompletionRequestWithExtraBody
 
 from .config import DatabricksImplConfig
 

src/llama_stack/providers/remote/inference/fireworks/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/gemini/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class GeminiProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/gemini/gemini.py

@@ -6,6 +6,7 @@
 
 from typing import Any
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIEmbeddingData,
     OpenAIEmbeddingsRequestWithExtraBody,
@@ -13,8 +14,6 @@ from llama_stack_api import (
     OpenAIEmbeddingUsage,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import GeminiConfig
 
 

src/llama_stack/providers/remote/inference/groq/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class GroqProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/llama_openai_compat/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class LlamaProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -4,6 +4,9 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAICompletion,
     OpenAICompletionRequestWithExtraBody,
@@ -11,10 +14,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 logger = get_logger(name=__name__, category="inference::llama_openai_compat")
 
 

src/llama_stack/providers/remote/inference/nvidia/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class NVIDIAProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -8,6 +8,9 @@
 from collections.abc import Iterable
 
 import aiohttp
+
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     Model,
     ModelType,
@@ -17,9 +20,6 @@ from llama_stack_api import (
     RerankResponse,
 )
 
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from . import NVIDIAConfig
 from .utils import _is_nvidia_hosted
 

src/llama_stack/providers/remote/inference/oci/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class OCIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/oci/oci.py

@@ -10,11 +10,6 @@ from typing import Any
 
 import httpx
 import oci
-from llama_stack_api import (
-    ModelType,
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-)
 from oci.generative_ai.generative_ai_client import GenerativeAiClient
 from oci.generative_ai.models import ModelCollection
 from openai._base_client import DefaultAsyncHttpxClient
@@ -23,6 +18,11 @@ from llama_stack.log import get_logger
 from llama_stack.providers.remote.inference.oci.auth import OciInstancePrincipalAuth, OciUserPrincipalAuth
 from llama_stack.providers.remote.inference.oci.config import OCIConfig
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    ModelType,
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 
 logger = get_logger(name=__name__, category="inference::oci")
 

src/llama_stack/providers/remote/inference/ollama/ollama.py

@@ -7,17 +7,17 @@
 
 import asyncio
 
+from ollama import AsyncClient as AsyncOllamaClient
+
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     HealthResponse,
     HealthStatus,
     Model,
     UnsupportedModelError,
 )
-from ollama import AsyncClient as AsyncOllamaClient
-
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 logger = get_logger(name=__name__, category="inference::ollama")
 

src/llama_stack/providers/remote/inference/openai/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class OpenAIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/passthrough/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/passthrough/passthrough.py

@@ -6,6 +6,9 @@
 
 from collections.abc import AsyncIterator
 
+from openai import AsyncOpenAI
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack_api import (
     Inference,
     Model,
@@ -17,9 +20,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
-from openai import AsyncOpenAI
-
-from llama_stack.core.request_headers import NeedsRequestProviderData
 
 from .config import PassthroughImplConfig
 

src/llama_stack/providers/remote/inference/runpod/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class RunpodProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/runpod/runpod.py

@@ -6,14 +6,13 @@
 
 from collections.abc import AsyncIterator
 
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAIChatCompletionRequestWithExtraBody,
 )
 
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
-
 from .config import RunpodImplConfig
 
 

src/llama_stack/providers/remote/inference/sambanova/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class SambaNovaProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/tgi/config.py

@@ -5,10 +5,10 @@
 # the root directory of this source tree.
 
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/tgi/tgi.py

@@ -8,14 +8,14 @@
 from collections.abc import Iterable
 
 from huggingface_hub import AsyncInferenceClient, HfApi
-from llama_stack_api import (
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-)
 from pydantic import SecretStr
 
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 

src/llama_stack/providers/remote/inference/together/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/together/together.py

@@ -8,18 +8,18 @@
 from collections.abc import Iterable
 from typing import Any, cast
 
-from llama_stack_api import (
-    Model,
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-    OpenAIEmbeddingUsage,
-)
 from together import AsyncTogether  # type: ignore[import-untyped]
 from together.constants import BASE_URL  # type: ignore[import-untyped]
 
 from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+from llama_stack_api import (
+    Model,
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+    OpenAIEmbeddingUsage,
+)
 
 from .config import TogetherImplConfig
 

src/llama_stack/providers/remote/inference/vertexai/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class VertexAIProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/vllm/config.py

@@ -6,10 +6,10 @@
 
 from pathlib import Path
 
-from llama_stack_api import json_schema_type
 from pydantic import Field, SecretStr, field_validator
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/inference/vllm/vllm.py

@@ -7,6 +7,10 @@ from collections.abc import AsyncIterator
 from urllib.parse import urljoin
 
 import httpx
+from pydantic import ConfigDict
+
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from llama_stack_api import (
     HealthResponse,
     HealthStatus,
@@ -15,10 +19,6 @@ from llama_stack_api import (
     OpenAIChatCompletionRequestWithExtraBody,
     ToolChoice,
 )
-from pydantic import ConfigDict
-
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import VLLMInferenceAdapterConfig
 

src/llama_stack/providers/remote/inference/watsonx/config.py

@@ -7,10 +7,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack_api import json_schema_type
 
 
 class WatsonXProviderDataValidator(BaseModel):

src/llama_stack/providers/remote/inference/watsonx/watsonx.py

@@ -9,6 +9,12 @@ from typing import Any
 
 import litellm
 import requests
+
+from llama_stack.core.telemetry.tracing import get_current_span
+from llama_stack.log import get_logger
+from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
+from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
+from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
 from llama_stack_api import (
     Model,
     ModelType,
@@ -22,12 +28,6 @@ from llama_stack_api import (
     OpenAIEmbeddingsResponse,
 )
 
-from llama_stack.core.telemetry.tracing import get_current_span
-from llama_stack.log import get_logger
-from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
-from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
-from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
-
 logger = get_logger(name=__name__, category="providers::remote::watsonx")
 
 
@@ -238,9 +238,8 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
         )
 
         # Convert response to OpenAI format
-        from llama_stack_api import OpenAIEmbeddingUsage
-
         from llama_stack.providers.utils.inference.litellm_openai_mixin import b64_encode_openai_embeddings_response
+        from llama_stack_api import OpenAIEmbeddingUsage
 
         data = b64_encode_openai_embeddings_response(response.data, params.encoding_format)
 

src/llama_stack/providers/remote/post_training/nvidia/post_training.py

@@ -8,6 +8,11 @@ from datetime import datetime
 from typing import Any, Literal
 
 import aiohttp
+from pydantic import BaseModel, ConfigDict
+
+from llama_stack.providers.remote.post_training.nvidia.config import NvidiaPostTrainingConfig
+from llama_stack.providers.remote.post_training.nvidia.utils import warn_unsupported_params
+from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 from llama_stack_api import (
     AlgorithmConfig,
     DPOAlignmentConfig,
@@ -17,11 +22,6 @@ from llama_stack_api import (
     PostTrainingJobStatusResponse,
     TrainingConfig,
 )
-from pydantic import BaseModel, ConfigDict
-
-from llama_stack.providers.remote.post_training.nvidia.config import NvidiaPostTrainingConfig
-from llama_stack.providers.remote.post_training.nvidia.utils import warn_unsupported_params
-from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
 
 from .models import _MODEL_ENTRIES
 

src/llama_stack/providers/remote/post_training/nvidia/utils.py

@@ -7,11 +7,11 @@
 import warnings
 from typing import Any
 
-from llama_stack_api import TrainingConfig
 from pydantic import BaseModel
 
 from llama_stack.log import get_logger
 from llama_stack.providers.remote.post_training.nvidia.config import SFTLoRADefaultConfig
+from llama_stack_api import TrainingConfig
 
 from .config import NvidiaPostTrainingConfig
 

src/llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -7,6 +7,8 @@
 import json
 from typing import Any
 
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 from llama_stack_api import (
     OpenAIMessageParam,
     RunShieldResponse,
@@ -17,9 +19,6 @@ from llama_stack_api import (
     ViolationLevel,
 )
 
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.bedrock.client import create_bedrock_client
-
 from .config import BedrockSafetyConfig
 
 logger = get_logger(name=__name__, category="safety::bedrock")

src/llama_stack/providers/remote/safety/bedrock/config.py

@@ -5,9 +5,8 @@
 # the root directory of this source tree.
 
 
-from llama_stack_api import json_schema_type
-
 from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/safety/nvidia/config.py

@@ -6,9 +6,10 @@
 import os
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
+from llama_stack_api import json_schema_type
+
 
 @json_schema_type
 class NVIDIASafetyConfig(BaseModel):

src/llama_stack/providers/remote/safety/nvidia/nvidia.py

@@ -7,6 +7,8 @@
 from typing import Any
 
 import requests
+
+from llama_stack.log import get_logger
 from llama_stack_api import (
     ModerationObject,
     OpenAIMessageParam,
@@ -18,8 +20,6 @@ from llama_stack_api import (
     ViolationLevel,
 )
 
-from llama_stack.log import get_logger
-
 from .config import NVIDIASafetyConfig
 
 logger = get_logger(name=__name__, category="safety::nvidia")

src/llama_stack/providers/remote/safety/sambanova/config.py

@@ -6,9 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field, SecretStr
 
+from llama_stack_api import json_schema_type
+
 
 class SambaNovaProviderDataValidator(BaseModel):
     sambanova_api_key: str | None = Field(

src/llama_stack/providers/remote/safety/sambanova/sambanova.py

@@ -8,6 +8,9 @@ from typing import Any
 
 import litellm
 import requests
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
+from llama_stack.log import get_logger
 from llama_stack_api import (
     OpenAIMessageParam,
     RunShieldResponse,
@@ -18,9 +21,6 @@ from llama_stack_api import (
     ViolationLevel,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-from llama_stack.log import get_logger
-
 from .config import SambaNovaSafetyConfig
 
 logger = get_logger(name=__name__, category="safety::sambanova")

src/llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py

@@ -8,6 +8,8 @@ import json
 from typing import Any
 
 import httpx
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
@@ -18,8 +20,6 @@ from llama_stack_api import (
     ToolRuntime,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-
 from .config import BingSearchToolConfig
 
 

src/llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py

@@ -7,6 +7,9 @@
 from typing import Any
 
 import httpx
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
+from llama_stack.models.llama.datatypes import BuiltinTool
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
@@ -17,9 +20,6 @@ from llama_stack_api import (
     ToolRuntime,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-from llama_stack.models.llama.datatypes import BuiltinTool
-
 from .config import BraveSearchToolConfig
 
 

src/llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py

@@ -7,6 +7,9 @@
 from typing import Any
 from urllib.parse import urlparse
 
+from llama_stack.core.request_headers import NeedsRequestProviderData
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools
 from llama_stack_api import (
     URL,
     Api,
@@ -17,10 +20,6 @@ from llama_stack_api import (
     ToolRuntime,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools
-
 from .config import MCPProviderConfig
 
 logger = get_logger(__name__, category="tools")

src/llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py

@@ -8,6 +8,8 @@ import json
 from typing import Any
 
 import httpx
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
@@ -18,8 +20,6 @@ from llama_stack_api import (
     ToolRuntime,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-
 from .config import TavilySearchToolConfig
 
 

src/llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py

@@ -8,6 +8,8 @@ import json
 from typing import Any
 
 import httpx
+
+from llama_stack.core.request_headers import NeedsRequestProviderData
 from llama_stack_api import (
     URL,
     ListToolDefsResponse,
@@ -18,8 +20,6 @@ from llama_stack_api import (
     ToolRuntime,
 )
 
-from llama_stack.core.request_headers import NeedsRequestProviderData
-
 from .config import WolframAlphaToolConfig
 
 

src/llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -9,6 +9,14 @@ from typing import Any
 from urllib.parse import urlparse
 
 import chromadb
+from numpy.typing import NDArray
+
+from llama_stack.log import get_logger
+from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig
+from llama_stack.providers.utils.kvstore import kvstore_impl
+from llama_stack.providers.utils.kvstore.api import KVStore
+from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
+from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex
 from llama_stack_api import (
     Chunk,
     Files,
@@ -19,14 +27,6 @@ from llama_stack_api import (
     VectorStore,
     VectorStoresProtocolPrivate,
 )
-from numpy.typing import NDArray
-
-from llama_stack.log import get_logger
-from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig
-from llama_stack.providers.utils.kvstore import kvstore_impl
-from llama_stack.providers.utils.kvstore.api import KVStore
-from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
-from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex
 
 from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig
 

src/llama_stack/providers/remote/vector_io/chroma/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.core.storage.datatypes import KVStoreReference
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/vector_io/milvus/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, ConfigDict, Field
 
 from llama_stack.core.storage.datatypes import KVStoreReference
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -8,17 +8,6 @@ import asyncio
 import os
 from typing import Any
 
-from llama_stack_api import (
-    Chunk,
-    Files,
-    Inference,
-    InterleavedContent,
-    QueryChunksResponse,
-    VectorIO,
-    VectorStore,
-    VectorStoreNotFoundError,
-    VectorStoresProtocolPrivate,
-)
 from numpy.typing import NDArray
 from pymilvus import AnnSearchRequest, DataType, Function, FunctionType, MilvusClient, RRFRanker, WeightedRanker
 
@@ -34,6 +23,17 @@ from llama_stack.providers.utils.memory.vector_store import (
     VectorStoreWithIndex,
 )
 from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collection_name
+from llama_stack_api import (
+    Chunk,
+    Files,
+    Inference,
+    InterleavedContent,
+    QueryChunksResponse,
+    VectorIO,
+    VectorStore,
+    VectorStoreNotFoundError,
+    VectorStoresProtocolPrivate,
+)
 
 from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig
 

src/llama_stack/providers/remote/vector_io/pgvector/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.core.storage.datatypes import KVStoreReference
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -8,17 +8,6 @@ import heapq
 from typing import Any
 
 import psycopg2
-from llama_stack_api import (
-    Chunk,
-    Files,
-    Inference,
-    InterleavedContent,
-    QueryChunksResponse,
-    VectorIO,
-    VectorStore,
-    VectorStoreNotFoundError,
-    VectorStoresProtocolPrivate,
-)
 from numpy.typing import NDArray
 from psycopg2 import sql
 from psycopg2.extras import Json, execute_values
@@ -31,6 +20,17 @@ from llama_stack.providers.utils.kvstore.api import KVStore
 from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
 from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex
 from llama_stack.providers.utils.vector_io.vector_utils import WeightedInMemoryAggregator, sanitize_collection_name
+from llama_stack_api import (
+    Chunk,
+    Files,
+    Inference,
+    InterleavedContent,
+    QueryChunksResponse,
+    VectorIO,
+    VectorStore,
+    VectorStoreNotFoundError,
+    VectorStoresProtocolPrivate,
+)
 
 from .config import PGVectorVectorIOConfig
 

src/llama_stack/providers/remote/vector_io/qdrant/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel
 
 from llama_stack.core.storage.datatypes import KVStoreReference
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -9,6 +9,15 @@ import hashlib
 import uuid
 from typing import Any
 
+from numpy.typing import NDArray
+from qdrant_client import AsyncQdrantClient, models
+from qdrant_client.models import PointStruct
+
+from llama_stack.log import get_logger
+from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
+from llama_stack.providers.utils.kvstore import kvstore_impl
+from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
+from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex
 from llama_stack_api import (
     Chunk,
     Files,
@@ -22,15 +31,6 @@ from llama_stack_api import (
     VectorStoreNotFoundError,
     VectorStoresProtocolPrivate,
 )
-from numpy.typing import NDArray
-from qdrant_client import AsyncQdrantClient, models
-from qdrant_client.models import PointStruct
-
-from llama_stack.log import get_logger
-from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
-from llama_stack.providers.utils.kvstore import kvstore_impl
-from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
-from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex
 
 from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
 

src/llama_stack/providers/remote/vector_io/weaviate/config.py

@@ -6,10 +6,10 @@
 
 from typing import Any
 
-from llama_stack_api import json_schema_type
 from pydantic import BaseModel, Field
 
 from llama_stack.core.storage.datatypes import KVStoreReference
+from llama_stack_api import json_schema_type
 
 
 @json_schema_type

src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -8,17 +8,6 @@ from typing import Any
 
 import weaviate
 import weaviate.classes as wvc
-from llama_stack_api import (
-    Chunk,
-    Files,
-    Inference,
-    InterleavedContent,
-    QueryChunksResponse,
-    VectorIO,
-    VectorStore,
-    VectorStoreNotFoundError,
-    VectorStoresProtocolPrivate,
-)
 from numpy.typing import NDArray
 from weaviate.classes.init import Auth
 from weaviate.classes.query import Filter, HybridFusion
@@ -35,6 +24,17 @@ from llama_stack.providers.utils.memory.vector_store import (
     VectorStoreWithIndex,
 )
 from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collection_name
+from llama_stack_api import (
+    Chunk,
+    Files,
+    Inference,
+    InterleavedContent,
+    QueryChunksResponse,
+    VectorIO,
+    VectorStore,
+    VectorStoreNotFoundError,
+    VectorStoresProtocolPrivate,
+)
 
 from .config import WeaviateVectorIOConfig