perf: Use OpenCV over PIL for PNG encoding in ImageRef.from_pil

docling_core/types/doc/document.py

@@ -12,7 +12,6 @@
 import typing
 import warnings
 from collections.abc import Sequence
-from dataclasses import dataclass
 from enum import Enum
 from io import BytesIO
 from pathlib import Path
@@ -26,6 +25,8 @@
 )
 from urllib.parse import unquote
 
+import cv2
+import numpy as np
 import pandas as pd
 import yaml
 from PIL import Image as PILImage
@@ -1109,9 +1110,8 @@ def validate_mimetype(cls, v):
     @classmethod
     def from_pil(cls, image: PILImage.Image, dpi: int) -> Self:
         """Construct ImageRef from a PIL Image."""
-        buffered = BytesIO()
-        image.save(buffered, format="PNG")
-        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        _, buffered = cv2.imencode(".png", cv2.cvtColor(np.array(image), cv2.COLOR_RGBA2BGRA))
+        img_str = base64.b64encode(buffered.tobytes()).decode("utf-8")
         img_uri = f"data:image/png;base64,{img_str}"
         return cls(
             mimetype="image/png",

pyproject.toml

@@ -50,6 +50,7 @@ dependencies = [
     'typer (>=0.12.5,<0.25.0)',
     'latex2mathml (>=3.77.0,<4.0.0)',
     "defusedxml (>=0.7.1, <0.8.0)",
+    "opencv-python-headless>=4.13.0.92",
 ]
 
 [project.urls]