feat: enable PyUpgrade Ruff Rule-Set (#633)

.ruff.toml

@@ -39,8 +39,8 @@ select = [
   "E722",
   # unused arguments
   "ARG",
-  # Enforce modern type-syntax
-  "UP006",
+  # pyupgrade
+  "UP",
 ]
 ignore = [
   # mutable defaults
@@ -55,10 +55,9 @@ unfixable = [
 ]
 ignore-init-module-imports = true
 
-[extend-per-file-ignores]
+[lint.extend-per-file-ignores]
 "instructor/distil.py" = ["ARG002"]
 "tests/test_distil.py" = ["ARG001"]
 "tests/test_patch.py" = ["ARG001"]
 "examples/task_planner/task_planner_topological_sort.py" = ["ARG002"]
 "examples/citation_with_extraction/main.py" = ["ARG001"]
-

examples/avail/run.py

@@ -1,5 +1,6 @@
 from pydantic import BaseModel, Field
-from typing import Iterable, Literal
+from typing import Literal
+from collections.abc import Iterable
 from datetime import datetime, timedelta
 
 from openai import OpenAI

examples/chain-of-density/finetune.py

@@ -44,7 +44,7 @@ def distil_summarization(text: str) -> GeneratedSummary:
     return GeneratedSummary(summary=summary_chain[-1])
 
 
-with open("test.csv", "r") as file:
+with open("test.csv") as file:
     reader = csv.reader(file)
     next(reader)  # Skip the header
     for article, _summary in reader:

examples/citation_with_extraction/main.py

@@ -1,5 +1,5 @@
 import json
-from typing import Iterable
+from collections.abc import Iterable
 from fastapi import FastAPI, Request, HTTPException
 from fastapi.params import Depends
 from instructor import OpenAISchema

examples/evals/streamlit.py

@@ -2,7 +2,7 @@
 from stats_dict import stats_dict
 
 # Sample data
-query_data = {i: line.strip() for i, line in enumerate(open("test.jsonl", "r"))}
+query_data = {i: line.strip() for i, line in enumerate(open("test.jsonl"))}
 
 # Initialize selected keys
 selected_keys = {}

examples/parallel/run.py

@@ -3,7 +3,8 @@
 import openai
 import instructor
 
-from typing import Iterable, Literal
+from typing import Literal
+from collections.abc import Iterable
 from pydantic import BaseModel
 
 

examples/patching/pcalls.py

@@ -1,4 +1,5 @@
-from typing import Iterable, Literal, Union
+from typing import Literal, Union
+from collections.abc import Iterable
 from pydantic import BaseModel
 from instructor import OpenAISchema
 

examples/stream_action_items/run.py

@@ -1,7 +1,8 @@
 import instructor
 
 from pydantic import BaseModel, Field
-from typing import Iterable, Optional
+from typing import Optional
+from collections.abc import Iterable
 from openai import OpenAI
 from rich.console import Console
 

examples/streaming_multitask/streaming_multitask.py

@@ -1,6 +1,6 @@
 import time
 
-from typing import Iterable
+from collections.abc import Iterable
 from openai import OpenAI
 from pydantic import BaseModel
 

examples/synethic-data/run.py

@@ -1,6 +1,6 @@
 import openai
 import instructor
-from typing import Iterable
+from collections.abc import Iterable
 from pydantic import BaseModel, ConfigDict
 
 client = instructor.from_openai(openai.OpenAI())

examples/task_planner/task_planner_topological_sort.py

@@ -11,7 +11,7 @@
 """
 
 import asyncio
-from typing import Generator
+from collections.abc import Generator
 
 from openai import OpenAI
 

examples/validators/allm_validator.py

@@ -1,5 +1,5 @@
 import asyncio
-from typing_extensions import Annotated
+from typing import Annotated
 from pydantic import BaseModel, BeforeValidator
 from instructor import llm_validator, patch
 from openai import AsyncOpenAI

examples/validators/annotator.py

@@ -1,4 +1,4 @@
-from typing_extensions import Annotated
+from typing import Annotated
 from pydantic import BaseModel, ValidationError
 from pydantic.functional_validators import AfterValidator
 

examples/validators/citations.py

@@ -1,4 +1,4 @@
-from typing_extensions import Annotated
+from typing import Annotated
 from pydantic import BaseModel, ValidationError, ValidationInfo, AfterValidator
 from openai import OpenAI
 import instructor

examples/validators/competitors.py

@@ -1,4 +1,4 @@
-from typing_extensions import Annotated
+from typing import Annotated
 from pydantic import BaseModel, ValidationError, AfterValidator
 from openai import OpenAI
 

examples/validators/llm_validator.py

@@ -3,7 +3,7 @@
 from openai import OpenAI
 from instructor import llm_validator
 from pydantic import BaseModel, ValidationError, BeforeValidator
-from typing_extensions import Annotated
+from typing import Annotated
 
 # Apply the patch to the OpenAI client
 client = instructor.from_openai(OpenAI())

examples/validators/moderation.py

@@ -2,7 +2,7 @@
 
 from instructor import openai_moderation
 
-from typing_extensions import Annotated
+from typing import Annotated
 from pydantic import BaseModel, AfterValidator
 from openai import OpenAI
 

examples/vision/image_to_ad_copy.py

@@ -191,7 +191,7 @@ def run(images: list[str]) -> tuple[list[Product], list[AdCopy]]:
         sys.exit(1)
 
     image_file = sys.argv[1]
-    with open(image_file, "r") as file:
+    with open(image_file) as file:
         logger.info(f"Reading images from file: {image_file}")
         try:
             image_list = file.read().splitlines()

examples/vision/slides.py

@@ -93,7 +93,7 @@ def process_and_identify_competitors():
     logger.info("Starting app...")
 
     try:
-        with open(IMAGE_FILE, "r") as file:
+        with open(IMAGE_FILE) as file:
             logger.info(f"Reading images from file: {IMAGE_FILE}")
             image_list = file.read().splitlines()
             logger.info(f"{len(image_list)} images read from file: {IMAGE_FILE}")

examples/youtube-clips/run.py

@@ -1,6 +1,6 @@
 from youtube_transcript_api import YouTubeTranscriptApi
 from pydantic import BaseModel, Field
-from typing import Generator, Iterable
+from collections.abc import Generator, Iterable
 import instructor
 import openai
 

instructor/cli/usage.py

@@ -1,9 +1,11 @@
-from typing import Any, Awaitable, List, Union
+from typing import Any, Union
+from collections.abc import Awaitable
 from datetime import datetime, timedelta
 import typer
 import os
 import aiohttp
 import asyncio
+from builtins import list as List
 from collections import defaultdict
 from rich.console import Console
 from rich.table import Table

instructor/client.py

@@ -7,15 +7,12 @@
 from openai.types.chat import ChatCompletionMessageParam
 from typing import (
     TypeVar,
-    Generator,
-    Iterable,
     Callable,
     overload,
     Union,
-    Awaitable,
-    AsyncGenerator,
     Any,
 )
+from collections.abc import Generator, Iterable, Awaitable, AsyncGenerator
 from typing_extensions import Self
 from pydantic import BaseModel
 from instructor.dsl.partial import Partial
@@ -59,7 +56,7 @@ def messages(self) -> Self:
 
     @overload
     def create(
-        self: "AsyncInstructor",
+        self: AsyncInstructor,
         response_model: type[T],
         messages: list[ChatCompletionMessageParam],
         max_retries: int = 3,
@@ -88,7 +85,7 @@ def create(
         validation_context: dict[str, Any] | None = None,
         strict: bool = True,
         **kwargs: Any,
-    ) -> Union[T, Awaitable[T]]:
+    ) -> T | Awaitable[T]:
         kwargs = self.handle_kwargs(kwargs)
 
         return self.create_fn(
@@ -102,7 +99,7 @@ def create(
 
     @overload
     def create_partial(
-        self: "AsyncInstructor",
+        self: AsyncInstructor,
         response_model: type[T],
         messages: list[ChatCompletionMessageParam],
         max_retries: int = 3,
@@ -130,7 +127,7 @@ def create_partial(
         validation_context: dict[str, Any] | None = None,
         strict: bool = True,
         **kwargs: Any,
-    ) -> Union[Generator[T, None, None], AsyncGenerator[T, None]]:
+    ) -> Generator[T, None, None] | AsyncGenerator[T, None]:
         assert self.provider != Provider.ANTHROPIC, "Anthropic doesn't support partial"
 
         kwargs["stream"] = True
@@ -149,7 +146,7 @@ def create_partial(
 
     @overload
     def create_iterable(
-        self: "AsyncInstructor",
+        self: AsyncInstructor,
         messages: list[ChatCompletionMessageParam],
         response_model: type[T],
         max_retries: int = 3,
@@ -177,7 +174,7 @@ def create_iterable(
         validation_context: dict[str, Any] | None = None,
         strict: bool = True,
         **kwargs: Any,
-    ) -> Union[Generator[T, None, None], AsyncGenerator[T, None]]:
+    ) -> Generator[T, None, None] | AsyncGenerator[T, None]:
         assert self.provider != Provider.ANTHROPIC, "Anthropic doesn't support iterable"
 
         kwargs["stream"] = True
@@ -195,7 +192,7 @@ def create_iterable(
 
     @overload
     def create_with_completion(
-        self: "AsyncInstructor",
+        self: AsyncInstructor,
         messages: list[ChatCompletionMessageParam],
         response_model: type[T],
         max_retries: int = 3,
@@ -223,7 +220,7 @@ def create_with_completion(
         validation_context: dict[str, Any] | None = None,
         strict: bool = True,
         **kwargs: Any,
-    ) -> Union[tuple[T, Any], Awaitable[tuple[T, Any]]]:
+    ) -> tuple[T, Any] | Awaitable[tuple[T, Any]]:
         kwargs = self.handle_kwargs(kwargs)
         model = self.create_fn(
             messages=messages,
@@ -368,7 +365,7 @@ def from_openai(
 
 
 def from_openai(
-    client: Union[openai.OpenAI, openai.AsyncOpenAI],
+    client: openai.OpenAI | openai.AsyncOpenAI,
     mode: instructor.Mode = instructor.Mode.TOOLS,
     **kwargs: Any,
 ) -> Instructor | AsyncInstructor:

instructor/client_cohere.py

@@ -7,7 +7,7 @@
     TypeVar,
     overload,
 )
-from typing import Any, Optional
+from typing import Any
 from typing_extensions import ParamSpec
 from pydantic import BaseModel
 from instructor.process_response import handle_response_model
@@ -58,8 +58,8 @@ def from_cohere(
 
     @wraps(client.chat)
     async def new_create_async(
-        response_model: Optional[type[T_Model]] = None,
-        validation_context: Optional[dict[str, Any]] = None,
+        response_model: type[T_Model] | None = None,
+        validation_context: dict[str, Any] | None = None,
         max_retries: int = 1,
         *args: T_ParamSpec.args,
         **kwargs: T_ParamSpec.kwargs,

instructor/distil.py

@@ -62,7 +62,7 @@ def get_signature_from_fn(fn: Callable[..., Any]) -> str:
     return f"{lines}\n{formatted_docstring}"
 
 
-@functools.lru_cache()
+@functools.lru_cache
 def format_function(func: Callable[..., Any]) -> str:
     """
     Format a function as a string with docstring and body.

instructor/dsl/citation.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, Field, model_validator, ValidationInfo
-from typing import Generator
+from collections.abc import Generator
 
 
 class CitationMixin(BaseModel):

instructor/dsl/iterable.py

@@ -1,4 +1,5 @@
-from typing import Any, AsyncGenerator, Generator, Iterable, Optional, cast, ClassVar
+from typing import Any, Optional, cast, ClassVar
+from collections.abc import AsyncGenerator, Generator, Iterable
 
 from pydantic import BaseModel, Field, create_model  # type: ignore - remove once Pydantic is updated
 

instructor/dsl/parallel.py

@@ -1,12 +1,12 @@
 from typing import (
     Any,
-    Generator,
     Optional,
     TypeVar,
     Union,
     get_args,
     get_origin,
 )
+from collections.abc import Generator
 from pydantic import BaseModel
 from instructor.function_calls import OpenAISchema, openai_schema
 from collections.abc import Iterable

instructor/dsl/partial.py

@@ -13,18 +13,16 @@
 from pydantic.fields import FieldInfo
 from typing import (
     Any,
-    AsyncGenerator,
-    Generator,
     Generic,
     get_args,
     get_origin,
-    Iterable,
     NoReturn,
     Optional,
     TypeVar,
 )
+from collections.abc import AsyncGenerator, Generator, Iterable
 from copy import deepcopy
-from functools import lru_cache
+from functools import cache
 
 from instructor.mode import Mode
 from instructor.utils import extract_json_from_stream, extract_json_from_stream_async
@@ -78,7 +76,7 @@ def _make_field_optional(
 
 class PartialBase(Generic[T_Model]):
     @classmethod
-    @lru_cache(maxsize=None)
+    @cache
     def get_partial_model(cls) -> type[T_Model]:
         """Return a partial model we can use to validate partial results."""
         assert issubclass(
@@ -207,7 +205,7 @@ def __new__(
         cls,
         *args: object,  # noqa :ARG003
         **kwargs: object,  # noqa :ARG003
-    ) -> "Partial[T_Model]":
+    ) -> Partial[T_Model]:
         """Cannot instantiate.
 
         Raises:
@@ -225,7 +223,7 @@ def __init_subclass__(
         Raises:
            TypeError: Subclassing not allowed.
         """
-        raise TypeError("Cannot subclass {}.Partial".format(cls.__module__))
+        raise TypeError(f"Cannot subclass {cls.__module__}.Partial")
 
     def __class_getitem__(
         cls,