chore: enable pyupgrade fixes (#1806)

# What does this PR do?

The goal of this PR is code base modernization.

Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)

Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

llama_stack/providers/inline/inference/sentence_transformers/__init__.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 typing import Any, Dict
+from typing import Any
 
 from llama_stack.providers.inline.inference.sentence_transformers.config import (
     SentenceTransformersInferenceConfig,
@@ -13,7 +13,7 @@ from llama_stack.providers.inline.inference.sentence_transformers.config import
 
 async def get_provider_impl(
     config: SentenceTransformersInferenceConfig,
-    _deps: Dict[str, Any],
+    _deps: dict[str, Any],
 ):
     from .sentence_transformers import SentenceTransformersInferenceImpl
 

llama_stack/providers/inline/inference/sentence_transformers/config.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Any, Dict
+from typing import Any
 
 from pydantic import BaseModel
 
 
 class SentenceTransformersInferenceConfig(BaseModel):
     @classmethod
-    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
         return {}

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import AsyncGenerator, List, Optional, Union
+from collections.abc import AsyncGenerator
 
 from llama_stack.apis.inference import (
     CompletionResponse,
@@ -60,46 +60,46 @@ class SentenceTransformersInferenceImpl(
         self,
         model_id: str,
         content: str,
-        sampling_params: Optional[SamplingParams] = None,
-        response_format: Optional[ResponseFormat] = None,
-        stream: Optional[bool] = False,
-        logprobs: Optional[LogProbConfig] = None,
-    ) -> Union[CompletionResponse, AsyncGenerator]:
+        sampling_params: SamplingParams | None = None,
+        response_format: ResponseFormat | None = None,
+        stream: bool | None = False,
+        logprobs: LogProbConfig | None = None,
+    ) -> CompletionResponse | AsyncGenerator:
         raise ValueError("Sentence transformers don't support completion")
 
     async def chat_completion(
         self,
         model_id: str,
-        messages: List[Message],
-        sampling_params: Optional[SamplingParams] = None,
-        response_format: Optional[ResponseFormat] = None,
-        tools: Optional[List[ToolDefinition]] = None,
-        tool_choice: Optional[ToolChoice] = ToolChoice.auto,
-        tool_prompt_format: Optional[ToolPromptFormat] = None,
-        stream: Optional[bool] = False,
-        logprobs: Optional[LogProbConfig] = None,
-        tool_config: Optional[ToolConfig] = None,
+        messages: list[Message],
+        sampling_params: SamplingParams | None = None,
+        response_format: ResponseFormat | None = None,
+        tools: list[ToolDefinition] | None = None,
+        tool_choice: ToolChoice | None = ToolChoice.auto,
+        tool_prompt_format: ToolPromptFormat | None = None,
+        stream: bool | None = False,
+        logprobs: LogProbConfig | None = None,
+        tool_config: ToolConfig | None = None,
     ) -> AsyncGenerator:
         raise ValueError("Sentence transformers don't support chat completion")
 
     async def batch_completion(
         self,
         model_id: str,
-        content_batch: List[InterleavedContent],
-        sampling_params: Optional[SamplingParams] = None,
-        response_format: Optional[ResponseFormat] = None,
-        logprobs: Optional[LogProbConfig] = None,
+        content_batch: list[InterleavedContent],
+        sampling_params: SamplingParams | None = None,
+        response_format: ResponseFormat | None = None,
+        logprobs: LogProbConfig | None = None,
     ):
         raise NotImplementedError("Batch completion is not supported for Sentence Transformers")
 
     async def batch_chat_completion(
         self,
         model_id: str,
-        messages_batch: List[List[Message]],
-        sampling_params: Optional[SamplingParams] = None,
-        tools: Optional[List[ToolDefinition]] = None,
-        tool_config: Optional[ToolConfig] = None,
-        response_format: Optional[ResponseFormat] = None,
-        logprobs: Optional[LogProbConfig] = None,
+        messages_batch: list[list[Message]],
+        sampling_params: SamplingParams | None = None,
+        tools: list[ToolDefinition] | None = None,
+        tool_config: ToolConfig | None = None,
+        response_format: ResponseFormat | None = None,
+        logprobs: LogProbConfig | None = None,
     ):
         raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")