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/vector_io/chroma/__init__.py

@@ -4,14 +4,14 @@
 # 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.datatypes import Api
 
 from .config import ChromaVectorIOConfig
 
 
-async def get_provider_impl(config: ChromaVectorIOConfig, deps: Dict[Api, Any]):
+async def get_provider_impl(config: ChromaVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.chroma.chroma import (
         ChromaVectorIOAdapter,
     )

llama_stack/providers/inline/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):
     db_path: str
 
     @classmethod
-    def sample_run_config(cls, db_path: str = "${env.CHROMADB_PATH}", **kwargs: Any) -> Dict[str, Any]:
+    def sample_run_config(cls, db_path: str = "${env.CHROMADB_PATH}", **kwargs: Any) -> dict[str, Any]:
         return {"db_path": db_path}

llama_stack/providers/inline/vector_io/faiss/__init__.py

@@ -4,14 +4,14 @@
 # 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.datatypes import Api
 
 from .config import FaissVectorIOConfig
 
 
-async def get_provider_impl(config: FaissVectorIOConfig, deps: Dict[Api, Any]):
+async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
     from .faiss import FaissVectorIOAdapter
 
     assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"

llama_stack/providers/inline/vector_io/faiss/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
 
@@ -20,7 +20,7 @@ class FaissVectorIOConfig(BaseModel):
     kvstore: KVStoreConfig
 
     @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 {
             "kvstore": SqliteKVStoreConfig.sample_run_config(
                 __distro_dir__=__distro_dir__,

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -9,7 +9,7 @@ import base64
 import io
 import json
 import logging
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 import faiss
 import numpy as np
@@ -84,7 +84,7 @@ class FaissIndex(EmbeddingIndex):
 
         await self.kvstore.delete(f"{FAISS_INDEX_PREFIX}{self.bank_id}")
 
-    async def add_chunks(self, chunks: List[Chunk], embeddings: NDArray):
+    async def add_chunks(self, chunks: list[Chunk], embeddings: NDArray):
         # Add dimension check
         embedding_dim = embeddings.shape[1] if len(embeddings.shape) > 1 else embeddings.shape[0]
         if embedding_dim != self.index.d:
@@ -159,7 +159,7 @@ class FaissVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
             inference_api=self.inference_api,
         )
 
-    async def list_vector_dbs(self) -> List[VectorDB]:
+    async def list_vector_dbs(self) -> list[VectorDB]:
         return [i.vector_db for i in self.cache.values()]
 
     async def unregister_vector_db(self, vector_db_id: str) -> None:
@@ -176,8 +176,8 @@ class FaissVectorIOAdapter(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 = self.cache.get(vector_db_id)
         if index is None:
@@ -189,7 +189,7 @@ class FaissVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         self,
         vector_db_id: str,
         query: InterleavedContent,
-        params: Optional[Dict[str, Any]] = None,
+        params: dict[str, Any] | None = None,
     ) -> QueryChunksResponse:
         index = self.cache.get(vector_db_id)
         if index is None:

llama_stack/providers/inline/vector_io/milvus/__init__.py

@@ -4,14 +4,14 @@
 # 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.datatypes import Api
 
 from .config import MilvusVectorIOConfig
 
 
-async def get_provider_impl(config: MilvusVectorIOConfig, deps: Dict[Api, Any]):
+async def get_provider_impl(config: MilvusVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusVectorIOAdapter
 
     impl = MilvusVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/inline/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
+from typing import Any
 
 from pydantic import BaseModel
 
@@ -16,5 +16,5 @@ class MilvusVectorIOConfig(BaseModel):
     db_path: str
 
     @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 {"db_path": "${env.MILVUS_DB_PATH}"}

llama_stack/providers/inline/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 llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
 
     impl = QdrantVectorIOAdapter(config, deps[Api.inference])

llama_stack/providers/inline/vector_io/qdrant/config.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 
-from typing import Any, Dict
+from typing import Any
 
 from pydantic import BaseModel
 
@@ -17,7 +17,7 @@ class QdrantVectorIOConfig(BaseModel):
     path: str
 
     @classmethod
-    def sample_run_config(cls, __distro_dir__: str) -> Dict[str, Any]:
+    def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
         return {
             "path": "${env.QDRANT_PATH:~/.llama/" + __distro_dir__ + "}/" + "qdrant.db",
         }

llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py

@@ -4,14 +4,14 @@
 # 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.datatypes import Api
 
 from .config import SQLiteVectorIOConfig
 
 
-async def get_provider_impl(config: SQLiteVectorIOConfig, deps: Dict[Api, Any]):
+async def get_provider_impl(config: SQLiteVectorIOConfig, deps: dict[Api, Any]):
     from .sqlite_vec import SQLiteVecVectorIOAdapter
 
     assert isinstance(config, SQLiteVectorIOConfig), f"Unexpected config type: {type(config)}"

llama_stack/providers/inline/vector_io/sqlite_vec/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
 
@@ -13,7 +13,7 @@ class SQLiteVectorIOConfig(BaseModel):
     db_path: str
 
     @classmethod
-    def sample_run_config(cls, __distro_dir__: str) -> Dict[str, Any]:
+    def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
         return {
             "db_path": "${env.SQLITE_STORE_DIR:" + __distro_dir__ + "}/" + "sqlite_vec.db",
         }

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -10,7 +10,7 @@ import logging
 import sqlite3
 import struct
 import uuid
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 import numpy as np
 import sqlite_vec
@@ -25,7 +25,7 @@ from llama_stack.providers.utils.memory.vector_store import EmbeddingIndex, Vect
 logger = logging.getLogger(__name__)
 
 
-def serialize_vector(vector: List[float]) -> bytes:
+def serialize_vector(vector: list[float]) -> bytes:
     """Serialize a list of floats into a compact binary representation."""
     return struct.pack(f"{len(vector)}f", *vector)
 
@@ -98,7 +98,7 @@ class SQLiteVecIndex(EmbeddingIndex):
 
         await asyncio.to_thread(_drop_tables)
 
-    async def add_chunks(self, chunks: List[Chunk], embeddings: NDArray, batch_size: int = 500):
+    async def add_chunks(self, chunks: list[Chunk], embeddings: NDArray, batch_size: int = 500):
         """
         Add new chunks along with their embeddings using batch inserts.
         For each chunk, we insert its JSON into the metadata table and then insert its
@@ -209,7 +209,7 @@ class SQLiteVecVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
     def __init__(self, config, inference_api: Inference) -> None:
         self.config = config
         self.inference_api = inference_api
-        self.cache: Dict[str, VectorDBWithIndex] = {}
+        self.cache: dict[str, VectorDBWithIndex] = {}
 
     async def initialize(self) -> None:
         def _setup_connection():
@@ -264,7 +264,7 @@ class SQLiteVecVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         index = await SQLiteVecIndex.create(vector_db.embedding_dimension, self.config.db_path, vector_db.identifier)
         self.cache[vector_db.identifier] = VectorDBWithIndex(vector_db, index, self.inference_api)
 
-    async def list_vector_dbs(self) -> List[VectorDB]:
+    async def list_vector_dbs(self) -> list[VectorDB]:
         return [v.vector_db for v in self.cache.values()]
 
     async def unregister_vector_db(self, vector_db_id: str) -> None:
@@ -286,7 +286,7 @@ class SQLiteVecVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
 
         await asyncio.to_thread(_delete_vector_db_from_registry)
 
-    async def insert_chunks(self, vector_db_id: str, chunks: List[Chunk], ttl_seconds: Optional[int] = None) -> None:
+    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
         if vector_db_id not in self.cache:
             raise ValueError(f"Vector DB {vector_db_id} not found. Found: {list(self.cache.keys())}")
         # The VectorDBWithIndex helper is expected to compute embeddings via the inference_api
@@ -294,7 +294,7 @@ class SQLiteVecVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         await self.cache[vector_db_id].insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: Any, params: Optional[Dict[str, Any]] = None
+        self, vector_db_id: str, query: Any, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
         if vector_db_id not in self.cache:
             raise ValueError(f"Vector DB {vector_db_id} not found")
@@ -303,5 +303,5 @@ class SQLiteVecVectorIOAdapter(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()))