chore: remove nested imports (#2515)

# What does this PR do?

* Given that our API packages use "import *" in `__init.py__` we don't
need to do `from llama_stack.apis.models.models` but simply from
llama_stack.apis.models. The decision to use `import *` is debatable and
should probably be revisited at one point.

* Remove unneeded Ruff F401 rule
* Consolidate Ruff F403 rule in the pyprojectfrom
llama_stack.apis.models.models

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

llama_stack/apis/agents/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .agents import *  # noqa: F401 F403
+from .agents import *

llama_stack/apis/batch_inference/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .batch_inference import *  # noqa: F401 F403
+from .batch_inference import *

llama_stack/apis/benchmarks/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .benchmarks import *  # noqa: F401 F403
+from .benchmarks import *

llama_stack/apis/datasetio/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .datasetio import *  # noqa: F401 F403
+from .datasetio import *

llama_stack/apis/datasets/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .datasets import *  # noqa: F401 F403
+from .datasets import *

llama_stack/apis/eval/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .eval import *  # noqa: F401 F403
+from .eval import *

llama_stack/apis/files/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .files import *  # noqa: F401 F403
+from .files import *

llama_stack/apis/inference/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .inference import *  # noqa: F401 F403
+from .inference import *

llama_stack/apis/inference/inference.py

@@ -20,7 +20,7 @@ from typing_extensions import TypedDict
 from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, InterleavedContentItem
 from llama_stack.apis.common.responses import Order
 from llama_stack.apis.models import Model
-from llama_stack.apis.telemetry.telemetry import MetricResponseMixin
+from llama_stack.apis.telemetry import MetricResponseMixin
 from llama_stack.models.llama.datatypes import (
     BuiltinTool,
     StopReason,

llama_stack/apis/inspect/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .inspect import *  # noqa: F401 F403
+from .inspect import *

llama_stack/apis/models/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .models import *  # noqa: F401 F403
+from .models import *

llama_stack/apis/post_training/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .post_training import *  # noqa: F401 F403
+from .post_training import *

llama_stack/apis/providers/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .providers import *  # noqa: F401 F403
+from .providers import *

llama_stack/apis/safety/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .safety import *  # noqa: F401 F403
+from .safety import *

llama_stack/apis/scoring/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .scoring import *  # noqa: F401 F403
+from .scoring import *

llama_stack/apis/scoring_functions/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .scoring_functions import *  # noqa: F401 F403
+from .scoring_functions import *

llama_stack/apis/shields/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .shields import *  # noqa: F401 F403
+from .shields import *

llama_stack/apis/synthetic_data_generation/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .synthetic_data_generation import *  # noqa: F401 F403
+from .synthetic_data_generation import *

llama_stack/apis/telemetry/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .telemetry import *  # noqa: F401 F403
+from .telemetry import *

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 .rag_tool import *  # noqa: F401 F403
+from .rag_tool import *
-from .tools import *  # noqa: F401 F403
+from .tools import *

llama_stack/apis/vector_dbs/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .vector_dbs import *  # noqa: F401 F403
+from .vector_dbs import *

llama_stack/apis/vector_io/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .vector_io import *  # noqa: F401 F403
+from .vector_io import *

llama_stack/distribution/routers/inference.py

@@ -30,7 +30,13 @@ from llama_stack.apis.inference import (
     ListOpenAIChatCompletionResponse,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
     OpenAICompletionWithInputMessages,
+    OpenAIEmbeddingsResponse,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     Order,
     ResponseFormat,
     SamplingParams,
@@ -41,14 +47,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIEmbeddingsResponse,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.apis.telemetry import MetricEvent, MetricInResponse, Telemetry
 from llama_stack.log import get_logger

llama_stack/distribution/routers/vector_io.py

@@ -16,17 +16,15 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     SearchRankingOptions,
     VectorIO,
-    VectorStoreDeleteResponse,
-    VectorStoreListResponse,
-    VectorStoreObject,
-    VectorStoreSearchResponsePage,
-)
-from llama_stack.apis.vector_io.vector_io import (
     VectorStoreChunkingStrategy,
+    VectorStoreDeleteResponse,
     VectorStoreFileContentsResponse,
     VectorStoreFileDeleteResponse,
     VectorStoreFileObject,
     VectorStoreFileStatus,
+    VectorStoreListResponse,
+    VectorStoreObject,
+    VectorStoreSearchResponsePage,
 )
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import HealthResponse, HealthStatus, RoutingTable

llama_stack/distribution/ui/modules/api.py

@@ -25,7 +25,7 @@ class LlamaStackApi:
     def run_scoring(self, row, scoring_function_ids: list[str], scoring_params: dict | None):
         """Run scoring on a single row"""
         if not scoring_params:
-            scoring_params = {fn_id: None for fn_id in scoring_function_ids}
+            scoring_params = dict.fromkeys(scoring_function_ids)
         return self.client.scoring.score(input_rows=[row], scoring_functions=scoring_params)
 
 

llama_stack/log.py

@@ -33,7 +33,7 @@ CATEGORIES = [
 ]
 
 # Initialize category levels with default level
-_category_levels: dict[str, int] = {category: DEFAULT_LOG_LEVEL for category in CATEGORIES}
+_category_levels: dict[str, int] = dict.fromkeys(CATEGORIES, DEFAULT_LOG_LEVEL)
 
 
 def config_to_category_levels(category: str, level: str):

llama_stack/providers/inline/agents/meta_reference/openai_responses.py

@@ -45,7 +45,7 @@ from llama_stack.apis.agents.openai_responses import (
     WebSearchToolTypes,
 )
 from llama_stack.apis.common.content_types import TextContentItem
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     Inference,
     OpenAIAssistantMessageParam,
     OpenAIChatCompletion,
@@ -584,7 +584,7 @@ class OpenAIResponsesImpl:
         from llama_stack.apis.agents.openai_responses import (
             MCPListToolsTool,
         )
-        from llama_stack.apis.tools.tools import Tool
+        from llama_stack.apis.tools import Tool
 
         mcp_tool_to_server = {}
 

llama_stack/providers/inline/eval/meta_reference/eval.py

@@ -208,7 +208,7 @@ class MetaReferenceEvalImpl(
                 for scoring_fn_id in scoring_functions
             }
         else:
-            scoring_functions_dict = {scoring_fn_id: None for scoring_fn_id in scoring_functions}
+            scoring_functions_dict = dict.fromkeys(scoring_functions)
 
         score_response = await self.scoring_api.score(
             input_rows=score_input_rows, scoring_functions=scoring_functions_dict

llama_stack/providers/inline/scoring/llm_as_judge/scoring.py

@@ -7,7 +7,7 @@ from typing import Any
 
 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.inference import Inference
 from llama_stack.apis.scoring import (
     ScoreBatchResponse,
     ScoreResponse,

llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py

@@ -6,7 +6,7 @@
 import re
 from typing import Any
 
-from llama_stack.apis.inference.inference import Inference, UserMessage
+from llama_stack.apis.inference import Inference, UserMessage
 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

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -16,8 +16,7 @@ import numpy as np
 from numpy.typing import NDArray
 
 from llama_stack.apis.files import Files
-from llama_stack.apis.inference import InterleavedContent
+from llama_stack.apis.inference import Inference, InterleavedContent
-from llama_stack.apis.inference.inference import Inference
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -15,8 +15,8 @@ import numpy as np
 import sqlite_vec
 from numpy.typing import NDArray
 
-from llama_stack.apis.files.files import Files
+from llama_stack.apis.files import Files
-from llama_stack.apis.inference.inference import Inference
+from llama_stack.apis.inference import Inference
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
@@ -64,7 +64,7 @@ def _normalize_scores(scores: dict[str, float]) -> dict[str, float]:
     score_range = max_score - min_score
     if score_range > 0:
         return {doc_id: (score - min_score) / score_range for doc_id, score in scores.items()}
-    return {doc_id: 1.0 for doc_id in scores}
+    return dict.fromkeys(scores, 1.0)
 
 
 def _weighted_rerank(

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

@@ -66,7 +66,7 @@ class NvidiaDatasetIOAdapter:
         Returns:
             Dataset
         """
-        ## add warnings for unsupported params
+        # add warnings for unsupported params
         request_body = {
             "name": dataset_def.identifier,
             "namespace": self.config.dataset_namespace,

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

@@ -32,15 +32,6 @@ 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,
@@ -48,6 +39,13 @@ 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,
 )

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -23,6 +23,13 @@ from llama_stack.apis.inference import (
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
+    OpenAIEmbeddingsResponse,
+    OpenAIEmbeddingUsage,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -31,16 +38,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.models import Model
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIEmbeddingsResponse,
-    OpenAIEmbeddingUsage,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
-from llama_stack.apis.models.models import Model
 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/utils/inference/model_registry.py

@@ -8,7 +8,7 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
 from llama_stack.providers.utils.inference import (

llama_stack/providers/utils/inference/openai_compat.py

@@ -95,27 +95,25 @@ from llama_stack.apis.inference import (
     CompletionResponse,
     CompletionResponseStreamChunk,
     GreedySamplingStrategy,
-    Message,
-    SamplingParams,
-    SystemMessage,
-    TokenLogProbs,
-    ToolChoice,
-    ToolResponseMessage,
-    TopKSamplingStrategy,
-    TopPSamplingStrategy,
-    UserMessage,
-)
-from llama_stack.apis.inference.inference import (
     JsonSchemaResponseFormat,
+    Message,
     OpenAIChatCompletion,
     OpenAICompletion,
     OpenAICompletionChoice,
     OpenAIEmbeddingData,
     OpenAIMessageParam,
     OpenAIResponseFormatParam,
+    SamplingParams,
+    SystemMessage,
+    TokenLogProbs,
+    ToolChoice,
     ToolConfig,
+    ToolResponseMessage,
+    TopKSamplingStrategy,
+    TopPSamplingStrategy,
+    UserMessage,
 )
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     OpenAIChoice as OpenAIChatCompletionChoice,
 )
 from llama_stack.models.llama.datatypes import (

llama_stack/providers/utils/memory/openai_vector_store_mixin.py

@@ -12,8 +12,7 @@ import uuid
 from abc import ABC, abstractmethod
 from typing import Any
 
-from llama_stack.apis.files import Files
+from llama_stack.apis.files import Files, OpenAIFileObject
-from llama_stack.apis.files.files import OpenAIFileObject
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,

llama_stack/providers/utils/telemetry/tracing.py

@@ -180,7 +180,7 @@ async def start_trace(name: str, attributes: dict[str, Any] = None) -> TraceCont
 
     trace_id = generate_trace_id()
     context = TraceContext(BACKGROUND_LOGGER, trace_id)
-    attributes = {marker: True for marker in ROOT_SPAN_MARKERS} | (attributes or {})
+    attributes = dict.fromkeys(ROOT_SPAN_MARKERS, True) | (attributes or {})
     context.push_span(name, attributes)
 
     CURRENT_TRACE_CONTEXT.set(context)

llama_stack/templates/cerebras/cerebras.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,

llama_stack/templates/ci-tests/ci_tests.py

@@ -5,7 +5,7 @@
 # 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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/dell/dell.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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/fireworks/fireworks.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/groq/groq.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,

llama_stack/templates/hf-endpoint/hf_endpoint.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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/hf-serverless/hf_serverless.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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/llama_api/llama_api.py

@@ -5,7 +5,7 @@
 # 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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/ollama/ollama.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/open-benchmark/open_benchmark.py

@@ -6,7 +6,7 @@
 
 
 from llama_stack.apis.datasets import DatasetPurpose, URIDataSource
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     BenchmarkInput,
     DatasetInput,

llama_stack/templates/passthrough/passthrough.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/postgres-demo/postgres_demo.py

@@ -5,7 +5,7 @@
 # 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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/remote-vllm/vllm.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/sambanova/sambanova.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/starter/starter.py

@@ -5,7 +5,7 @@
 # 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.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/template.py

@@ -13,7 +13,7 @@ import yaml
 from pydantic import BaseModel, Field
 
 from llama_stack.apis.datasets import DatasetPurpose
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     Api,
     BenchmarkInput,

llama_stack/templates/tgi/tgi.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/together/together.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,

llama_stack/templates/vllm-gpu/vllm.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.distribution.datatypes import ModelInput, Provider
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,

llama_stack/templates/watsonx/watsonx.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.models import ModelType
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,

pyproject.toml

@@ -204,6 +204,9 @@ unfixable = [
     "RUF001",
     "PLE2515",
 ]
+"llama_stack/apis/**/__init__.py" = [
+    "F403",
+] # Using import * is acceptable (or at least tolerated) in an __init__.py of a package API
 
 [tool.mypy]
 mypy_path = ["llama_stack"]

tests/unit/distribution/routers/test_routing_tables.py

@@ -13,7 +13,7 @@ import pytest
 from llama_stack.apis.common.type_system import NumberType
 from llama_stack.apis.datasets.datasets import Dataset, DatasetPurpose, URIDataSource
 from llama_stack.apis.datatypes import Api
-from llama_stack.apis.models.models import Model, ModelType
+from llama_stack.apis.models import Model, ModelType
 from llama_stack.apis.shields.shields import Shield
 from llama_stack.apis.tools import ListToolDefsResponse, ToolDef, ToolGroup, ToolParameter
 from llama_stack.apis.vector_dbs.vector_dbs import VectorDB

tests/unit/providers/agents/meta_reference/fixtures/__init__.py

@@ -8,7 +8,7 @@ import os
 
 import yaml
 
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     OpenAIChatCompletion,
 )
 

tests/unit/providers/agents/meta_reference/test_openai_responses.py

@@ -29,7 +29,7 @@ from llama_stack.apis.agents.openai_responses import (
     OpenAIResponseTextFormat,
     WebSearchToolTypes,
 )
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     OpenAIAssistantMessageParam,
     OpenAIChatCompletionContentPartTextParam,
     OpenAIDeveloperMessageParam,

tests/unit/providers/nvidia/test_safety.py

@@ -11,7 +11,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from llama_stack.apis.inference.inference import CompletionMessage, UserMessage
+from llama_stack.apis.inference import CompletionMessage, UserMessage
 from llama_stack.apis.safety import RunShieldResponse, ViolationLevel
 from llama_stack.apis.shields import Shield
 from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig

tests/unit/providers/utils/inference/test_openai_compat.py

@@ -7,7 +7,7 @@
 import pytest
 
 from llama_stack.apis.common.content_types import TextContentItem
-from llama_stack.apis.inference.inference import (
+from llama_stack.apis.inference import (
     CompletionMessage,
     OpenAIAssistantMessageParam,
     OpenAIChatCompletionContentPartTextParam,

tests/unit/providers/utils/test_model_registry.py

@@ -35,7 +35,7 @@
 
 import pytest
 
-from llama_stack.apis.models.models import Model
+from llama_stack.apis.models import Model
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry