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/chroma/__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 ChromaVectorIOConfig
 
 
-async def get_adapter_impl(config: ChromaVectorIOConfig, deps: Dict[Api, ProviderSpec]):
+async def get_adapter_impl(config: ChromaVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .chroma import ChromaVectorIOAdapter
 
     impl = ChromaVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -6,7 +6,7 @@
 import asyncio
 import json
 import logging
-from typing import Any, Dict, List, Optional, Union
+from typing import Any
 from urllib.parse import urlparse
 
 import chromadb
@@ -27,7 +27,7 @@ from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig
 log = logging.getLogger(__name__)
 
 
-ChromaClientType = Union[chromadb.AsyncHttpClient, chromadb.PersistentClient]
+ChromaClientType = chromadb.AsyncHttpClient | chromadb.PersistentClient
 
 
 # this is a helper to allow us to use async and non-async chroma clients interchangeably
@@ -42,7 +42,7 @@ class ChromaIndex(EmbeddingIndex):
         self.client = client
         self.collection = collection
 
-    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)}"
         )
@@ -89,7 +89,7 @@ class ChromaIndex(EmbeddingIndex):
 class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
     def __init__(
         self,
-        config: Union[RemoteChromaVectorIOConfig, InlineChromaVectorIOConfig],
+        config: RemoteChromaVectorIOConfig | InlineChromaVectorIOConfig,
         inference_api: Api.inference,
     ) -> None:
         log.info(f"Initializing ChromaVectorIOAdapter with url: {config}")
@@ -137,8 +137,8 @@ class ChromaVectorIOAdapter(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)
 
@@ -148,7 +148,7 @@ class ChromaVectorIOAdapter(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)
 

llama_stack/providers/remote/vector_io/chroma/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
+from typing import Any
 
 from pydantic import BaseModel
 
@@ -13,5 +13,5 @@ class ChromaVectorIOConfig(BaseModel):
     url: str
 
     @classmethod
-    def sample_run_config(cls, url: str = "${env.CHROMADB_URL}", **kwargs: Any) -> Dict[str, Any]:
+    def sample_run_config(cls, url: str = "${env.CHROMADB_URL}", **kwargs: Any) -> dict[str, Any]:
         return {"url": url}

llama_stack/providers/remote/vector_io/milvus/__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 MilvusVectorIOConfig
 
 
-async def get_adapter_impl(config: MilvusVectorIOConfig, deps: Dict[Api, ProviderSpec]):
+async def get_adapter_impl(config: MilvusVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .milvus import MilvusVectorIOAdapter
 
     assert isinstance(config, MilvusVectorIOConfig), f"Unexpected config type: {type(config)}"

llama_stack/providers/remote/vector_io/milvus/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
 
@@ -14,9 +14,9 @@ from llama_stack.schema_utils import json_schema_type
 @json_schema_type
 class MilvusVectorIOConfig(BaseModel):
     uri: str
-    token: Optional[str] = None
+    token: str | None = None
     consistency_level: str = "Strong"
 
     @classmethod
-    def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> Dict[str, Any]:
+    def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
         return {"uri": "${env.MILVUS_ENDPOINT}", "token": "${env.MILVUS_TOKEN}"}

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -9,7 +9,7 @@ import hashlib
 import logging
 import os
 import uuid
-from typing import Any, Dict, List, Optional, Union
+from typing import Any
 
 from numpy.typing import NDArray
 from pymilvus import MilvusClient
@@ -39,7 +39,7 @@ class MilvusIndex(EmbeddingIndex):
         if await asyncio.to_thread(self.client.has_collection, self.collection_name):
             await asyncio.to_thread(self.client.drop_collection, collection_name=self.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)}"
         )
@@ -89,7 +89,7 @@ class MilvusIndex(EmbeddingIndex):
 
 class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
     def __init__(
-        self, config: Union[RemoteMilvusVectorIOConfig, InlineMilvusVectorIOConfig], inference_api: Api.inference
+        self, config: RemoteMilvusVectorIOConfig | InlineMilvusVectorIOConfig, inference_api: Api.inference
     ) -> None:
         self.config = config
         self.cache = {}
@@ -124,7 +124,7 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
 
         self.cache[vector_db.identifier] = index
 
-    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]
 
@@ -148,8 +148,8 @@ class MilvusVectorIOAdapter(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:
@@ -161,7 +161,7 @@ class MilvusVectorIOAdapter(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:
@@ -172,7 +172,7 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
 
 def generate_chunk_id(document_id: str, chunk_text: str) -> str:
     """Generate a unique chunk ID using a hash of document ID and chunk text."""
-    hash_input = f"{document_id}:{chunk_text}".encode("utf-8")
+    hash_input = f"{document_id}:{chunk_text}".encode()
     return str(uuid.UUID(hashlib.md5(hash_input).hexdigest()))
 
 

llama_stack/providers/remote/vector_io/pgvector/__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 PGVectorVectorIOConfig
 
 
-async def get_adapter_impl(config: PGVectorVectorIOConfig, deps: Dict[Api, ProviderSpec]):
+async def get_adapter_impl(config: PGVectorVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .pgvector import PGVectorVectorIOAdapter
 
     impl = PGVectorVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/remote/vector_io/pgvector/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
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -28,5 +28,5 @@ class PGVectorVectorIOConfig(BaseModel):
         user: str = "${env.PGVECTOR_USER}",
         password: str = "${env.PGVECTOR_PASSWORD}",
         **kwargs: Any,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         return {"host": host, "port": port, "db": db, "user": user, "password": password}

llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
 import psycopg2
 from numpy.typing import NDArray
@@ -33,7 +33,7 @@ def check_extension_version(cur):
     return result[0] if result else None
 
 
-def upsert_models(conn, keys_models: List[Tuple[str, BaseModel]]):
+def upsert_models(conn, keys_models: list[tuple[str, BaseModel]]):
     with conn.cursor(cursor_factory=psycopg2.extras.DictCursor) as cur:
         query = sql.SQL(
             """
@@ -74,7 +74,7 @@ class PGVectorIndex(EmbeddingIndex):
             """
             )
 
-    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)}"
         )
@@ -180,8 +180,8 @@ class PGVectorVectorIOAdapter(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)
         await index.insert_chunks(chunks)
@@ -190,7 +190,7 @@ class PGVectorVectorIOAdapter(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)
         return await index.query_chunks(query, params)

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:

llama_stack/providers/remote/vector_io/weaviate/__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 WeaviateRequestProviderData, WeaviateVectorIOConfig  # noqa: F401
+from .config import WeaviateVectorIOConfig
 
 
-async def get_adapter_impl(config: WeaviateVectorIOConfig, deps: Dict[Api, ProviderSpec]):
+async def get_adapter_impl(config: WeaviateVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .weaviate import WeaviateVectorIOAdapter
 
     impl = WeaviateVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/remote/vector_io/weaviate/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
+from typing import Any
 
 from pydantic import BaseModel
 
@@ -16,5 +16,5 @@ class WeaviateRequestProviderData(BaseModel):
 
 class WeaviateVectorIOConfig(BaseModel):
     @classmethod
-    def sample_run_config(cls, **kwargs: Any) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
         return {}

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 import json
 import logging
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 import weaviate
 import weaviate.classes as wvc
@@ -33,7 +33,7 @@ class WeaviateIndex(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)}"
         )
@@ -80,7 +80,7 @@ class WeaviateIndex(EmbeddingIndex):
 
         return QueryChunksResponse(chunks=chunks, scores=scores)
 
-    async def delete(self, chunk_ids: List[str]) -> None:
+    async def delete(self, chunk_ids: list[str]) -> None:
         collection = self.client.collections.get(self.collection_name)
         collection.data.delete_many(where=Filter.by_property("id").contains_any(chunk_ids))
 
@@ -144,7 +144,7 @@ class WeaviateVectorIOAdapter(
             self.inference_api,
         )
 
-    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]
 
@@ -167,8 +167,8 @@ class WeaviateVectorIOAdapter(
     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:
@@ -180,7 +180,7 @@ class WeaviateVectorIOAdapter(
         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: