ok

app/api/v1/convert.py

@@ -1,10 +1,8 @@
 from __future__ import annotations
 
 import asyncio
-import concurrent.futures
 import hashlib
 import json as json_mod
-import os
 from typing import Annotated, Any, Dict, Optional
 from urllib.parse import urlparse
 
@@ -29,6 +27,7 @@ from app.api.deps import (
 )
 from app.config import get_settings
 from app.core.logger import get_logger
+from app.core.thread_pool import thread_pool as _thread_pool
 from app.models.domain import ConversionError, count_tokens
 from app.models.schemas import ConversionMetadata, ConversionResponse, UrlRequest
 from app.services.converter_service import ConverterService
@@ -39,8 +38,6 @@ router = APIRouter()
 _logger = get_logger(__name__)
 _settings = get_settings()
 _MAX_UPLOAD_BYTES = _settings.max_upload_bytes
-_MAX_WORKERS = min(32, (os.cpu_count() or 1) + 4)
-_thread_pool = concurrent.futures.ThreadPoolExecutor(max_workers=_MAX_WORKERS)
 
 
 def _build_metadata(result) -> ConversionMetadata:

app/api/v1/embeddings.py

@@ -1,8 +1,6 @@
 from __future__ import annotations
 
 import asyncio
-import concurrent.futures
-import os
 import time
 
 from fastapi import APIRouter, Depends, HTTPException
@@ -10,14 +8,13 @@ from fastapi import APIRouter, Depends, HTTPException
 from app.api.deps import get_embeddings_service, require_auth
 from app.config import get_settings
 from app.core.logger import get_logger
+from app.core.thread_pool import thread_pool as _thread_pool
 from app.models.schemas import EmbeddingItem, EmbeddingRequest, EmbeddingResponse
 from app.services.embeddings_service import EmbeddingService
 
 router = APIRouter()
 _logger = get_logger(__name__)
 _settings = get_settings()
-_MAX_WORKERS = min(32, (os.cpu_count() or 1) + 4)
-_thread_pool = concurrent.futures.ThreadPoolExecutor(max_workers=_MAX_WORKERS)
 @router.post(
     "/embeddings",
     response_model=EmbeddingResponse,

app/core/thread_pool.py

@@ -0,0 +1,10 @@
+from __future__ import annotations
+
+import concurrent.futures
+import os
+
+_MAX_WORKERS = min(32, (os.cpu_count() or 1) + 4)
+
+thread_pool = concurrent.futures.ThreadPoolExecutor(
+    max_workers=_MAX_WORKERS, thread_name_prefix="shared"
+)

app/services/dataset_metadata_service.py

@@ -11,8 +11,6 @@ import asyncio
 import csv
 import io
 import logging
-import os
-from concurrent.futures import ThreadPoolExecutor
 from dataclasses import dataclass, field
 from enum import Enum
 from pathlib import Path
@@ -35,6 +33,8 @@ import openpyxl  # noqa: F401 – needed as engine for .xlsx
 import pandas as pd
 import xlrd  # noqa: F401 – needed as engine for .xls
 
+from app.core.thread_pool import thread_pool
+
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
 
@@ -47,9 +47,6 @@ _DEFAULT_SAMPLE_ROWS: int = 5
 _MAX_FILE_SIZE: int = 2 * 1024 * 1024 * 1024       # 2 GiB
 _DOWNLOAD_CHUNK_SIZE: int = 256 * 1024              # 256 KiB streaming chunks
 _DEFAULT_TIMEOUT_SECONDS: int = 120
-_THREAD_POOL = ThreadPoolExecutor(
-    max_workers=min(32, (os.cpu_count() or 4) + 4),
-)
 
 # Magic bytes for binary file-type detection
 _XLSX_MAGIC: bytes = b"PK\x03\x04"
@@ -375,7 +372,7 @@ def _read_xls_metadata(data: bytes, config: ExtractionConfig) -> Dict[str, Any]:
 async def _read_from_file_like(file_obj: BinaryIO) -> Tuple[bytes, Optional[str]]:
     """Read all bytes from a synchronous file-like object off the event loop."""
     loop = asyncio.get_running_loop()
-    data: bytes = await loop.run_in_executor(_THREAD_POOL, file_obj.read)
+    data: bytes = await loop.run_in_executor(thread_pool, file_obj.read)
     filename: Optional[str] = getattr(file_obj, "name", None)
     return data, filename
 
@@ -387,7 +384,7 @@ async def _read_from_path(path: Path) -> Tuple[bytes, str]:
     if not path.is_file():
         raise IsADirectoryError(f"Path is not a regular file: {path}")
     loop = asyncio.get_running_loop()
-    data: bytes = await loop.run_in_executor(_THREAD_POOL, path.read_bytes)
+    data: bytes = await loop.run_in_executor(thread_pool, path.read_bytes)
     return data, path.name
 
 
@@ -599,7 +596,7 @@ async def extract_metadata(
     reader = readers[file_type]
     loop = asyncio.get_running_loop()
     result: Dict[str, Any] = await loop.run_in_executor(
-        _THREAD_POOL,
+        thread_pool,
         reader,
         data,
         config,

app/services/qr_decoder_service.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import asyncio
 import io
 import ipaddress
 import os
@@ -14,6 +15,7 @@ import numpy as np
 from PIL import Image, UnidentifiedImageError
 
 from app.core.logger import get_logger
+from app.core.thread_pool import thread_pool
 
 logger = get_logger(__name__)
 
@@ -211,14 +213,14 @@ class QRDecoderService:
     # ------------------------------------------------------------------
 
     async def _load_cv_image_async(self, raw_bytes: bytes, origin: str) -> np.ndarray:
-        loop = asyncio_get_loop()
-        return await loop.run_in_executor(None, self._load_cv_image, raw_bytes, origin)
+        loop = asyncio.get_running_loop()
+        return await loop.run_in_executor(thread_pool, self._load_cv_image, raw_bytes, origin)
 
     async def _decode_async(
         self, image: np.ndarray, source: str
     ) -> QRDecoderResult:
-        loop = asyncio_get_loop()
-        return await loop.run_in_executor(None, self._decode_sync, image, source)
+        loop = asyncio.get_running_loop()
+        return await loop.run_in_executor(thread_pool, self._decode_sync, image, source)
 
     # ------------------------------------------------------------------
     # Synchronous CPU-bound implementations
@@ -424,9 +426,4 @@ class QRDecoderService:
             ) from exc
 
 
-def asyncio_get_loop():
-    import asyncio
-    try:
-        return asyncio.get_running_loop()
-    except RuntimeError:
-        return asyncio.new_event_loop()
+