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/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)