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

docling_core/types/doc/document.py

@@ -26,6 +26,7 @@
 )
 from urllib.parse import unquote
 
+import numpy as np
 import pandas as pd
 import yaml
 from PIL import Image as PILImage
@@ -67,6 +68,13 @@
 from docling_core.types.doc.tokens import DocumentToken, TableToken
 from docling_core.types.doc.utils import parse_otsl_table_content, relative_path
 
+try:
+    import cv2
+
+    CV2_INSTALLED = True
+except ImportError:
+    CV2_INSTALLED = False
+
 _logger = logging.getLogger(__name__)
 
 Uint64 = typing.Annotated[int, Field(ge=0, le=(2**64 - 1))]
@@ -1107,12 +1115,26 @@ def validate_mimetype(cls, v):
             raise ValueError(f"'{v}' is not a valid MIME type")
         return v
 
-    @classmethod
-    def from_pil(cls, image: PILImage.Image, dpi: int) -> Self:
-        """Construct ImageRef from a PIL Image."""
+    @staticmethod
+    def _to_img_str_cv2(image: PILImage.Image) -> str:
+        _, buffered = cv2.imencode(".png", cv2.cvtColor(np.array(image), cv2.COLOR_RGBA2BGRA))
+        img_str = base64.b64encode(buffered.tobytes()).decode("utf-8")
+        return img_str
+
+    @staticmethod
+    def _to_img_str_pil(image: PILImage.Image) -> str:
         buffered = BytesIO()
         image.save(buffered, format="PNG")
         img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        return img_str
+
+    @classmethod
+    def from_pil(cls, image: PILImage.Image, dpi: int) -> Self:
+        """Construct ImageRef from a PIL Image."""
+        if CV2_INSTALLED:
+            img_str = cls._to_img_str_cv2(image)
+        else:
+            img_str = cls._to_img_str_pil(image)
         img_uri = f"data:image/png;base64,{img_str}"
         return cls(
             mimetype="image/png",

pyproject.toml

@@ -117,6 +117,7 @@ dev = [
     'tree-sitter-java-orchard (>=0.3.0,<1.0.0); python_version >= "3.10"',
     "ruff>=0.14.11",
     "types-defusedxml (>=0.7.0.20250822, <0.8.0)",
+    "opencv-python-headless>=4.6.0.66,<5.0.0.0",
 ]
 constraints = [
     'pandas (>=2.1.4,<3.0.0); python_version < "3.11"',