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/vector_io/qdrant/__init__.py

@@ -4,14 +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 Dict
-
 from llama_stack.providers.datatypes import Api, ProviderSpec
 
 from .config import QdrantVectorIOConfig
 
 
-async def get_adapter_impl(config: QdrantVectorIOConfig, deps: Dict[Api, ProviderSpec]):
+async def get_adapter_impl(config: QdrantVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .qdrant import QdrantVectorIOAdapter
 
     impl = QdrantVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/remote/vector_io/qdrant/config.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, Optional
+from typing import Any
 
 from pydantic import BaseModel
 
@@ -13,19 +13,19 @@ from llama_stack.schema_utils import json_schema_type
 
 @json_schema_type
 class QdrantVectorIOConfig(BaseModel):
-    location: Optional[str] = None
-    url: Optional[str] = None
-    port: Optional[int] = 6333
+    location: str | None = None
+    url: str | None = None
+    port: int | None = 6333
     grpc_port: int = 6334
     prefer_grpc: bool = False
-    https: Optional[bool] = None
-    api_key: Optional[str] = None
-    prefix: Optional[str] = None
-    timeout: Optional[int] = None
-    host: Optional[str] = None
+    https: bool | None = None
+    api_key: str | None = None
+    prefix: str | None = None
+    timeout: int | None = None
+    host: str | None = None
 
     @classmethod
-    def sample_run_config(cls, **kwargs: Any) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
         return {
             "api_key": "${env.QDRANT_API_KEY}",
         }

llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -6,7 +6,7 @@
 
 import logging
 import uuid
-from typing import Any, Dict, List, Optional, Union
+from typing import Any
 
 from numpy.typing import NDArray
 from qdrant_client import AsyncQdrantClient, models
@@ -44,7 +44,7 @@ class QdrantIndex(EmbeddingIndex):
         self.client = client
         self.collection_name = collection_name
 
-    async def add_chunks(self, chunks: List[Chunk], embeddings: NDArray):
+    async def add_chunks(self, chunks: list[Chunk], embeddings: NDArray):
         assert len(chunks) == len(embeddings), (
             f"Chunk length {len(chunks)} does not match embedding length {len(embeddings)}"
         )
@@ -101,7 +101,7 @@ class QdrantIndex(EmbeddingIndex):
 
 class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
     def __init__(
-        self, config: Union[RemoteQdrantVectorIOConfig, InlineQdrantVectorIOConfig], inference_api: Api.inference
+        self, config: RemoteQdrantVectorIOConfig | InlineQdrantVectorIOConfig, inference_api: Api.inference
     ) -> None:
         self.config = config
         self.client: AsyncQdrantClient = None
@@ -131,7 +131,7 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
             await self.cache[vector_db_id].index.delete()
             del self.cache[vector_db_id]
 
-    async def _get_and_cache_vector_db_index(self, vector_db_id: str) -> Optional[VectorDBWithIndex]:
+    async def _get_and_cache_vector_db_index(self, vector_db_id: str) -> VectorDBWithIndex | None:
         if vector_db_id in self.cache:
             return self.cache[vector_db_id]
 
@@ -150,8 +150,8 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
     async def insert_chunks(
         self,
         vector_db_id: str,
-        chunks: List[Chunk],
-        ttl_seconds: Optional[int] = None,
+        chunks: list[Chunk],
+        ttl_seconds: int | None = None,
     ) -> None:
         index = await self._get_and_cache_vector_db_index(vector_db_id)
         if not index:
@@ -163,7 +163,7 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         self,
         vector_db_id: str,
         query: InterleavedContent,
-        params: Optional[Dict[str, Any]] = None,
+        params: dict[str, Any] | None = None,
     ) -> QueryChunksResponse:
         index = await self._get_and_cache_vector_db_index(vector_db_id)
         if not index: