chore: remove nested imports

* Since our API packages use import * in __init__.py, we can import
  directly from llama_stack.apis.models instead of
  llama_stack.apis.models.models.  However, the choice to use import *
  is debatable and may need to be reconsidered in the future.

* Remove the unnecessary Ruff F401 suppression.

* Consolidate the Ruff F403 rule configuration in
pyproject.toml.

Signed-off-by: Sébastien Han <seb@redhat.com>

llama_stack/providers/remote/inference/anthropic/models.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,
 )

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

@@ -24,6 +24,12 @@ from llama_stack.apis.inference import (
     Inference,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
+    OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     ResponseFormatType,
     SamplingParams,
@@ -33,14 +39,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIEmbeddingsResponse,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.model_registry import (

llama_stack/providers/remote/inference/fireworks/models.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,
 )

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

@@ -9,7 +9,7 @@ from typing import Any
 
 from openai import AsyncOpenAI
 
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAIChoiceDelta,

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

@@ -29,20 +29,18 @@ from llama_stack.apis.inference import (
     Inference,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
     OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
     ToolChoice,
     ToolConfig,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.models.llama.datatypes import ToolDefinition, ToolPromptFormat
 from llama_stack.providers.utils.inference import (

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,

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

@@ -33,15 +33,6 @@ from llama_stack.apis.inference import (
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
-    ResponseFormat,
-    SamplingParams,
-    TextTruncation,
-    ToolChoice,
-    ToolConfig,
-    ToolDefinition,
-    ToolPromptFormat,
-)
-from llama_stack.apis.inference.inference import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAICompletion,
@@ -49,6 +40,13 @@ from llama_stack.apis.inference.inference import (
     OpenAIEmbeddingUsage,
     OpenAIMessageParam,
     OpenAIResponseFormatParam,
+    ResponseFormat,
+    SamplingParams,
+    TextTruncation,
+    ToolChoice,
+    ToolConfig,
+    ToolDefinition,
+    ToolPromptFormat,
 )
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.log import get_logger

llama_stack/providers/remote/inference/openai/models.py

@@ -6,7 +6,7 @@
 
 from dataclasses import dataclass
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,
 )

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

@@ -10,7 +10,7 @@ from typing import Any
 
 from openai import AsyncOpenAI
 
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
     OpenAICompletion,

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

@@ -19,7 +19,12 @@ from llama_stack.apis.inference import (
     Inference,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
     OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -28,13 +33,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.apis.models import Model
 from llama_stack.distribution.library_client import convert_pydantic_to_json_value, convert_to_pydantic
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper

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

@@ -8,7 +8,7 @@ from collections.abc import AsyncGenerator
 from openai import OpenAI
 
 from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.inference.inference import OpenAIEmbeddingsResponse
+from llama_stack.apis.inference import OpenAIEmbeddingsResponse
 
 # from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.utils.inference.model_registry import (
     ProviderModelEntry,

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

@@ -23,7 +23,12 @@ from llama_stack.apis.inference import (
     Inference,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
     OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     ResponseFormatType,
     SamplingParams,
@@ -33,13 +38,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper

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

@@ -38,9 +38,13 @@ from llama_stack.apis.inference import (
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAICompletion,
     OpenAIEmbeddingData,
     OpenAIEmbeddingsResponse,
     OpenAIEmbeddingUsage,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -49,12 +53,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAICompletion,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.models.llama.datatypes import BuiltinTool, StopReason, ToolCall
 from llama_stack.models.llama.sku_list import all_registered_models

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

@@ -18,10 +18,16 @@ from llama_stack.apis.inference import (
     CompletionRequest,
     EmbeddingsResponse,
     EmbeddingTaskType,
+    GreedySamplingStrategy,
     Inference,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
     OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -29,14 +35,6 @@ from llama_stack.apis.inference import (
     ToolConfig,
     ToolDefinition,
     ToolPromptFormat,
-)
-from llama_stack.apis.inference.inference import (
-    GreedySamplingStrategy,
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
     TopKSamplingStrategy,
     TopPSamplingStrategy,
 )