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/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.inference import Inference
+from llama_stack.apis.inference import Inference, InterleavedContent
 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.inference.inference import Inference
+from llama_stack.apis.files import Files
+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 (
-    OpenAIChatCompletion,
-    OpenAIChatCompletionChunk,
-    OpenAICompletion,
-    OpenAIEmbeddingsResponse,
-    OpenAIEmbeddingUsage,
-    OpenAIMessageParam,
-    OpenAIResponseFormatParam,
-)
-from llama_stack.apis.models.models import Model
+from llama_stack.apis.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.files import OpenAIFileObject
+from llama_stack.apis.files import Files, 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)