From 27b896b9388364d2077950b9c59a5fd2d4d6a5e6 Mon Sep 17 00:00:00 2001
From: Christoph Auer <cau@zurich.ibm.com>
Date: Mon, 10 Feb 2025 16:59:52 +0100
Subject: [PATCH] Updates for reading-order implementation

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---
 docs/examples/batch_convert.py | 22 +++++++++++++++-------
 poetry.lock                    |  2 +-
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/docs/examples/batch_convert.py b/docs/examples/batch_convert.py
index 536b9aae..c21a4645 100644
--- a/docs/examples/batch_convert.py
+++ b/docs/examples/batch_convert.py
@@ -7,10 +7,11 @@ from typing import Iterable
 import yaml
 from docling_core.types.doc import ImageRefMode
 
-from docling.datamodel.base_models import ConversionStatus
+from docling.datamodel.base_models import ConversionStatus, InputFormat
 from docling.datamodel.document import ConversionResult
+from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.datamodel.settings import settings
-from docling.document_converter import DocumentConverter
+from docling.document_converter import DocumentConverter, PdfFormatOption
 
 _log = logging.getLogger(__name__)
 
@@ -38,6 +39,10 @@ def export_documents(
                     output_dir / f"{doc_filename}.json",
                     image_mode=ImageRefMode.PLACEHOLDER,
                 )
+                conv_res.document.save_as_html(
+                    output_dir / f"{doc_filename}.html",
+                    image_mode=ImageRefMode.EMBEDDED,
+                )
                 conv_res.document.save_as_document_tokens(
                     output_dir / f"{doc_filename}.doctags.txt"
                 )
@@ -50,10 +55,6 @@ def export_documents(
                     image_mode=ImageRefMode.PLACEHOLDER,
                     strict_text=True,
                 )
-                conv_res.document.save_as_html(
-                    output_dir / f"{doc_filename}.html",
-                    image_mode=ImageRefMode.EMBEDDED,
-                )
 
                 # Export Docling document format to YAML:
                 with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
@@ -125,7 +126,14 @@ def main():
     # settings.debug.visualize_tables = True
     # settings.debug.visualize_cells = True
 
-    doc_converter = DocumentConverter()
+    pipeline_options = PdfPipelineOptions()
+    pipeline_options.generate_page_images = True
+
+    doc_converter = DocumentConverter(
+        format_options={
+            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+        }
+    )
 
     start_time = time.time()
 
diff --git a/poetry.lock b/poetry.lock
index f2007744..d7b9fb92 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -879,7 +879,7 @@ transformers = [
 type = "git"
 url = "https://github.com/DS4SD/docling-ibm-models.git"
 reference = "dev/add-reading-order"
-resolved_reference = "2f88418a493321a1ee82a01604f617488f6a8feb"
+resolved_reference = "6892adfa4fcf0878b938e8efc1407dec46e96bdd"
 
 [[package]]
 name = "docling-parse"