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/remote/inference/cerebras/cerebras.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 AsyncGenerator, List, Optional, Union
+from collections.abc import AsyncGenerator
 
 from cerebras.cloud.sdk import AsyncCerebras
 
@@ -79,10 +79,10 @@ class CerebrasInferenceAdapter(
         self,
         model_id: str,
         content: InterleavedContent,
-        sampling_params: Optional[SamplingParams] = None,
-        response_format: Optional[ResponseFormat] = None,
-        stream: Optional[bool] = False,
-        logprobs: Optional[LogProbConfig] = None,
+        sampling_params: SamplingParams | None = None,
+        response_format: ResponseFormat | None = None,
+        stream: bool | None = False,
+        logprobs: LogProbConfig | None = None,
     ) -> AsyncGenerator:
         if sampling_params is None:
             sampling_params = SamplingParams()
@@ -120,15 +120,15 @@ class CerebrasInferenceAdapter(
     async def chat_completion(
         self,
         model_id: str,
-        messages: List[Message],
-        sampling_params: Optional[SamplingParams] = None,
-        tools: Optional[List[ToolDefinition]] = None,
-        tool_choice: Optional[ToolChoice] = ToolChoice.auto,
-        tool_prompt_format: Optional[ToolPromptFormat] = None,
-        response_format: Optional[ResponseFormat] = None,
-        stream: Optional[bool] = False,
-        logprobs: Optional[LogProbConfig] = None,
-        tool_config: Optional[ToolConfig] = None,
+        messages: list[Message],
+        sampling_params: SamplingParams | None = None,
+        tools: list[ToolDefinition] | None = None,
+        tool_choice: ToolChoice | None = ToolChoice.auto,
+        tool_prompt_format: ToolPromptFormat | None = None,
+        response_format: ResponseFormat | None = None,
+        stream: bool | None = False,
+        logprobs: LogProbConfig | None = None,
+        tool_config: ToolConfig | None = None,
     ) -> AsyncGenerator:
         if sampling_params is None:
             sampling_params = SamplingParams()
@@ -166,7 +166,7 @@ class CerebrasInferenceAdapter(
         async for chunk in process_chat_completion_stream_response(stream, request):
             yield chunk
 
-    async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
+    async def _get_params(self, request: ChatCompletionRequest | CompletionRequest) -> dict:
         if request.sampling_params and isinstance(request.sampling_params.strategy, TopKSamplingStrategy):
             raise ValueError("`top_k` not supported by Cerebras")
 
@@ -188,9 +188,9 @@ class CerebrasInferenceAdapter(
     async def embeddings(
         self,
         model_id: str,
-        contents: List[str] | List[InterleavedContentItem],
-        text_truncation: Optional[TextTruncation] = TextTruncation.none,
-        output_dimension: Optional[int] = None,
-        task_type: Optional[EmbeddingTaskType] = None,
+        contents: list[str] | list[InterleavedContentItem],
+        text_truncation: TextTruncation | None = TextTruncation.none,
+        output_dimension: int | None = None,
+        task_type: EmbeddingTaskType | None = None,
     ) -> EmbeddingsResponse:
         raise NotImplementedError()

llama_stack/providers/remote/inference/cerebras/config.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import os
-from typing import Any, Dict, Optional
+from typing import Any
 
 from pydantic import BaseModel, Field, SecretStr
 
@@ -20,13 +20,13 @@ class CerebrasImplConfig(BaseModel):
         default=os.environ.get("CEREBRAS_BASE_URL", DEFAULT_BASE_URL),
         description="Base URL for the Cerebras API",
     )
-    api_key: Optional[SecretStr] = Field(
+    api_key: SecretStr | None = Field(
         default=os.environ.get("CEREBRAS_API_KEY"),
         description="Cerebras API Key",
     )
 
     @classmethod
-    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
         return {
             "base_url": DEFAULT_BASE_URL,
             "api_key": "${env.CEREBRAS_API_KEY}",