chore: Remove deprecated type aliases and run as pre-commit (#79)

docling_serve/app.py

@@ -5,7 +5,7 @@ import tempfile
 from contextlib import asynccontextmanager
 from io import BytesIO
 from pathlib import Path
-from typing import Annotated, Any, Dict, List, Optional, Union
+from typing import Annotated, Any, Optional, Union
 
 from fastapi import (
     BackgroundTasks,
@@ -205,8 +205,8 @@ def create_app():  # noqa: C901
     def process_url(
         background_tasks: BackgroundTasks, conversion_request: ConvertDocumentsRequest
     ):
-        sources: List[Union[str, DocumentStream]] = []
-        headers: Optional[Dict[str, Any]] = None
+        sources: list[Union[str, DocumentStream]] = []
+        headers: Optional[dict[str, Any]] = None
         if isinstance(conversion_request, ConvertDocumentFileSourcesRequest):
             for file_source in conversion_request.file_sources:
                 sources.append(file_source.to_document_stream())
@@ -242,7 +242,7 @@ def create_app():  # noqa: C901
     )
     async def process_file(
         background_tasks: BackgroundTasks,
-        files: List[UploadFile],
+        files: list[UploadFile],
         options: Annotated[
             ConvertDocumentsOptions, FormDepends(ConvertDocumentsOptions)
         ],

docling_serve/datamodel/convert.py

@@ -1,5 +1,5 @@
 # Define the input options for the API
-from typing import Annotated, List, Optional
+from typing import Annotated, Optional
 
 from pydantic import BaseModel, Field
 
@@ -10,7 +10,7 @@ from docling_core.types.doc import ImageRefMode
 
 class ConvertDocumentsOptions(BaseModel):
     from_formats: Annotated[
-        List[InputFormat],
+        list[InputFormat],
         Field(
             description=(
                 "Input format(s) to convert from. String or list of strings. "
@@ -22,7 +22,7 @@ class ConvertDocumentsOptions(BaseModel):
     ] = list(InputFormat)
 
     to_formats: Annotated[
-        List[OutputFormat],
+        list[OutputFormat],
         Field(
             description=(
                 "Output format(s) to convert to. String or list of strings. "
@@ -83,7 +83,7 @@ class ConvertDocumentsOptions(BaseModel):
     ] = OcrEngine.EASYOCR
 
     ocr_lang: Annotated[
-        Optional[List[str]],
+        Optional[list[str]],
         Field(
             description=(
                 "List of languages used by the OCR engine. "

docling_serve/datamodel/requests.py

@@ -1,6 +1,6 @@
 import base64
 from io import BytesIO
-from typing import Annotated, Any, Dict, List, Union
+from typing import Annotated, Any, Union
 
 from pydantic import BaseModel, Field
 
@@ -22,7 +22,7 @@ class HttpSource(BaseModel):
         ),
     ]
     headers: Annotated[
-        Dict[str, Any],
+        dict[str, Any],
         Field(
             description="Additional headers used to fetch the urls, "
             "e.g. authorization, agent, etc"
@@ -50,11 +50,11 @@ class FileSource(BaseModel):
 
 
 class ConvertDocumentHttpSourcesRequest(DocumentsConvertBase):
-    http_sources: List[HttpSource]
+    http_sources: list[HttpSource]
 
 
 class ConvertDocumentFileSourcesRequest(DocumentsConvertBase):
-    file_sources: List[FileSource]
+    file_sources: list[FileSource]
 
 
 ConvertDocumentsRequest = Union[

docling_serve/datamodel/responses.py

@@ -1,5 +1,5 @@
 import enum
-from typing import Dict, List, Optional
+from typing import Optional
 
 from pydantic import BaseModel
 
@@ -25,9 +25,9 @@ class DocumentResponse(BaseModel):
 class ConvertDocumentResponse(BaseModel):
     document: DocumentResponse
     status: ConversionStatus
-    errors: List[ErrorItem] = []
+    errors: list[ErrorItem] = []
     processing_time: float
-    timings: Dict[str, ProfilingItem] = {}
+    timings: dict[str, ProfilingItem] = {}
 
 
 class ConvertDocumentErrorResponse(BaseModel):

docling_serve/docling_conversion.py

@@ -1,8 +1,9 @@
 import hashlib
 import json
 import logging
+from collections.abc import Iterable, Iterator
 from pathlib import Path
-from typing import Any, Dict, Iterable, Iterator, Optional, Tuple, Type, Union
+from typing import Any, Optional, Union
 
 from fastapi import HTTPException
 
@@ -33,7 +34,7 @@ _log = logging.getLogger(__name__)
 
 
 # Document converters will be preloaded and stored in a dictionary
-converters: Dict[bytes, DocumentConverter] = {}
+converters: dict[bytes, DocumentConverter] = {}
 
 
 # Custom serializer for PdfFormatOption
@@ -69,7 +70,7 @@ def _serialize_pdf_format_option(pdf_format_option: PdfFormatOption) -> str:
 # Computes the PDF pipeline options and returns the PdfFormatOption and its hash
 def get_pdf_pipeline_opts(  # noqa: C901
     request: ConvertDocumentsOptions,
-) -> Tuple[PdfFormatOption, bytes]:
+) -> tuple[PdfFormatOption, bytes]:
     if request.ocr_engine == OcrEngine.EASYOCR:
         try:
             import easyocr  # noqa: F401
@@ -129,7 +130,7 @@ def get_pdf_pipeline_opts(  # noqa: C901
             pipeline_options.images_scale = request.images_scale
 
     if request.pdf_backend == PdfBackend.DLPARSE_V1:
-        backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+        backend: type[PdfDocumentBackend] = DoclingParseDocumentBackend
     elif request.pdf_backend == PdfBackend.DLPARSE_V2:
         backend = DoclingParseV2DocumentBackend
     elif request.pdf_backend == PdfBackend.PYPDFIUM2:
@@ -177,12 +178,12 @@ def get_pdf_pipeline_opts(  # noqa: C901
 def convert_documents(
     sources: Iterable[Union[Path, str, DocumentStream]],
     options: ConvertDocumentsOptions,
-    headers: Optional[Dict[str, Any]] = None,
+    headers: Optional[dict[str, Any]] = None,
 ):
     pdf_format_option, options_hash = get_pdf_pipeline_opts(options)
 
     if options_hash not in converters:
-        format_options: Dict[InputFormat, FormatOption] = {
+        format_options: dict[InputFormat, FormatOption] = {
             InputFormat.PDF: pdf_format_option,
             InputFormat.IMAGE: pdf_format_option,
         }

docling_serve/engines/async_local/orchestrator.py

@@ -1,7 +1,7 @@
 import asyncio
 import logging
 import uuid
-from typing import Dict, List, Optional, Set
+from typing import Optional
 
 from fastapi import WebSocket
 
@@ -30,9 +30,9 @@ class TaskNotFoundError(OrchestratorError):
 class AsyncLocalOrchestrator(BaseOrchestrator):
     def __init__(self):
         self.task_queue = asyncio.Queue()
-        self.tasks: Dict[str, Task] = {}
-        self.queue_list: List[str] = []
-        self.task_subscribers: Dict[str, Set[WebSocket]] = {}
+        self.tasks: dict[str, Task] = {}
+        self.queue_list: list[str] = []
+        self.task_subscribers: dict[str, set[WebSocket]] = {}
 
     async def enqueue(self, request: ConvertDocumentsRequest) -> Task:
         task_id = str(uuid.uuid4())

docling_serve/engines/async_local/worker.py

@@ -1,7 +1,7 @@
 import asyncio
 import logging
 import time
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from fastapi import BackgroundTasks
 
@@ -50,8 +50,8 @@ class AsyncLocalWorker:
                 # Define a callback function to send progress updates to the client.
                 # TODO: send partial updates, e.g. when a document in the batch is done
                 def run_conversion():
-                    sources: List[Union[str, DocumentStream]] = []
-                    headers: Optional[Dict[str, Any]] = None
+                    sources: list[Union[str, DocumentStream]] = []
+                    headers: Optional[dict[str, Any]] = None
                     if isinstance(task.request, ConvertDocumentFileSourcesRequest):
                         for file_source in task.request.file_sources:
                             sources.append(file_source.to_document_stream())

docling_serve/helper_functions.py

@@ -1,6 +1,6 @@
 import inspect
 import re
-from typing import List, Type, Union
+from typing import Union
 
 from fastapi import Depends, Form
 from pydantic import BaseModel
@@ -8,7 +8,7 @@ from pydantic import BaseModel
 
 # Adapted from
 # https://github.com/fastapi/fastapi/discussions/8971#discussioncomment-7892972
-def FormDepends(cls: Type[BaseModel]):
+def FormDepends(cls: type[BaseModel]):
     new_parameters = []
 
     for field_name, model_field in cls.model_fields.items():
@@ -34,8 +34,8 @@ def FormDepends(cls: Type[BaseModel]):
     return Depends(as_form_func)
 
 
-def _to_list_of_strings(input_value: Union[str, List[str]]) -> List[str]:
-    def split_and_strip(value: str) -> List[str]:
+def _to_list_of_strings(input_value: Union[str, list[str]]) -> list[str]:
+    def split_and_strip(value: str) -> list[str]:
         if re.search(r"[;,]", value):
             return [item.strip() for item in re.split(r"[;,]", value)]
         else:

docling_serve/response_preparation.py

@@ -3,8 +3,9 @@ import os
 import shutil
 import tempfile
 import time
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Union
+from typing import Union
 
 from fastapi import BackgroundTasks, HTTPException
 from fastapi.responses import FileResponse

pyproject.toml

@@ -145,7 +145,8 @@ select = [
     "S307", # eval
     # "T20",  # (disallow print statements) keep debugging statements out of the codebase
     "W",  # pycodestyle warnings
-    "ASYNC" # async
+    "ASYNC", # async
+    "UP", # pyupgrade
 ]
 
 ignore = [
@@ -154,6 +155,7 @@ ignore = [
     "F811", # "redefinition of the same function"
     "PL", # Pylint
     "RUF012", # Mutable Class Attributes
+    "UP007", # Option and Union
 ]
 
 #extend-select = []