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/tgi/__init__.py

@@ -4,13 +4,11 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Union
-
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 
 
 async def get_adapter_impl(
-    config: Union[InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig],
+    config: InferenceAPIImplConfig | InferenceEndpointImplConfig | TGIImplConfig,
     _deps,
 ):
     from .tgi import InferenceAPIAdapter, InferenceEndpointAdapter, TGIAdapter

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

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Optional
 
 from pydantic import BaseModel, Field, SecretStr
 
@@ -29,7 +28,7 @@ class InferenceEndpointImplConfig(BaseModel):
     endpoint_name: str = Field(
         description="The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided.",
     )
-    api_token: Optional[SecretStr] = Field(
+    api_token: SecretStr | None = Field(
         default=None,
         description="Your Hugging Face user access token (will default to locally saved token if not provided)",
     )
@@ -52,7 +51,7 @@ class InferenceAPIImplConfig(BaseModel):
     huggingface_repo: str = Field(
         description="The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct')",
     )
-    api_token: Optional[SecretStr] = Field(
+    api_token: SecretStr | None = Field(
         default=None,
         description="Your Hugging Face user access token (will default to locally saved token if not provided)",
     )

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -6,7 +6,7 @@
 
 
 import logging
-from typing import AsyncGenerator, List, Optional
+from collections.abc import AsyncGenerator
 
 from huggingface_hub import AsyncInferenceClient, HfApi
 
@@ -105,10 +105,10 @@ class _HfAdapter(
         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()
@@ -134,7 +134,7 @@ class _HfAdapter(
 
     def _build_options(
         self,
-        sampling_params: Optional[SamplingParams] = None,
+        sampling_params: SamplingParams | None = None,
         fmt: ResponseFormat = None,
     ):
         options = get_sampling_options(sampling_params)
@@ -209,15 +209,15 @@ class _HfAdapter(
     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()
@@ -284,10 +284,10 @@ class _HfAdapter(
     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()