feat: added support for exporting DocItem to an image when page image…

… is available (#379) * Updated minimum docling-core version to 2.4.0 Signed-off-by: Shubham Gupta <[email protected]> * Deprecated the generate_table_images option Signed-off-by: Shubham Gupta <[email protected]> * Updated examples to use get_image instead of element.image Signed-off-by: Shubham Gupta <[email protected]> --------- Signed-off-by: Shubham Gupta <[email protected]>
DS4SD · Nov 19, 2024 · 3f91e7d · 3f91e7d
1 parent 911c3bd
commit 3f91e7d
Show file tree

Hide file tree

Showing 5 changed files with 31 additions and 8 deletions.
diff --git a/docling/datamodel/pipeline_options.py b/docling/datamodel/pipeline_options.py
@@ -82,4 +82,11 @@ class PdfPipelineOptions(PipelineOptions):
     images_scale: float = 1.0
     generate_page_images: bool = False
     generate_picture_images: bool = False
-    generate_table_images: bool = False
+    generate_table_images: bool = Field(
+        default=False,
+        deprecated=(
+            "Field `generate_table_images` is deprecated. "
+            "To obtain table images, set `PdfPipelineOptions.generate_page_images = True` "
+            "before conversion and then use the `TableItem.get_image` function."
+        ),
+    )
diff --git a/docs/examples/develop_picture_enrichment.py b/docs/examples/develop_picture_enrichment.py
@@ -39,7 +39,7 @@ def __call__(
             assert isinstance(element, PictureItem)
 
             # uncomment this to interactively visualize the image
-            # element.image.pil_image.show()
+            # element.get_image(doc).show()
 
             element.annotations.append(
                 PictureClassificationData(

diff --git a/docs/examples/export_figures.py b/docs/examples/export_figures.py
@@ -28,7 +28,6 @@ def main():
     pipeline_options = PdfPipelineOptions()
     pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE
     pipeline_options.generate_page_images = True
-    pipeline_options.generate_table_images = True
     pipeline_options.generate_picture_images = True
 
     doc_converter = DocumentConverter(
@@ -61,15 +60,15 @@ def main():
                 output_dir / f"{doc_filename}-table-{table_counter}.png"
             )
             with element_image_filename.open("wb") as fp:
-                element.image.pil_image.save(fp, "PNG")
+                element.get_image(conv_res.document).save(fp, "PNG")
 
         if isinstance(element, PictureItem):
             picture_counter += 1
             element_image_filename = (
                 output_dir / f"{doc_filename}-picture-{picture_counter}.png"
             )
             with element_image_filename.open("wb") as fp:
-                element.image.pil_image.save(fp, "PNG")
+                element.get_image(conv_res.document).save(fp, "PNG")
 
     # Save markdown with embedded pictures
     content_md = conv_res.document.export_to_markdown(image_mode=ImageRefMode.EMBEDDED)

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -26,7 +26,7 @@ packages = [{include = "docling"}]
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^2.3.0"
+docling-core = "^2.4.0"
 docling-ibm-models = "^2.0.3"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"