From dee2b9a50f9ad3abf4baafb102eaac4faab00294 Mon Sep 17 00:00:00 2001
From: Nikos Livathinos <nli@zurich.ibm.com>
Date: Mon, 3 Feb 2025 14:17:08 +0100
Subject: [PATCH] docs: Introduce example with custom models for RapidOCR

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---
 docs/examples/rapidocr_with_custom_models.py | 58 ++++++++++++++++++++
 mkdocs.yml                                   |  1 +
 2 files changed, 59 insertions(+)
 create mode 100644 docs/examples/rapidocr_with_custom_models.py

diff --git a/docs/examples/rapidocr_with_custom_models.py b/docs/examples/rapidocr_with_custom_models.py
new file mode 100644
index 00000000..e6dd3963
--- /dev/null
+++ b/docs/examples/rapidocr_with_custom_models.py
@@ -0,0 +1,58 @@
+import os
+
+from huggingface_hub import snapshot_download
+
+from docling.datamodel.pipeline_options import PdfPipelineOptions, RapidOcrOptions
+from docling.document_converter import (
+    ConversionResult,
+    DocumentConverter,
+    InputFormat,
+    PdfFormatOption,
+)
+
+
+def main():
+    # Source document to convert
+    source = "https://arxiv.org/pdf/2408.09869v4"
+
+    # Download RappidOCR models from HuggingFace
+    print("Downloading RapidOCR models")
+    download_path = snapshot_download(repo_id="SWHL/RapidOCR")
+
+    # Setup RapidOcrOptions for english detection
+    det_model_path = os.path.join(
+        download_path, "PP-OCRv4", "en_PP-OCRv3_det_infer.onnx"
+    )
+    rec_model_path = os.path.join(
+        download_path, "PP-OCRv4", "ch_PP-OCRv4_rec_server_infer.onnx"
+    )
+    cls_model_path = os.path.join(
+        download_path, "PP-OCRv3", "ch_ppocr_mobile_v2.0_cls_train.onnx"
+    )
+    ocr_options = RapidOcrOptions(
+        det_model_path=det_model_path,
+        rec_model_path=rec_model_path,
+        cls_model_path=cls_model_path,
+    )
+
+    pipeline_options = PdfPipelineOptions(
+        ocr_options=ocr_options,
+    )
+
+    # Convert the document
+    converter = DocumentConverter(
+        format_options={
+            InputFormat.PDF: PdfFormatOption(
+                pipeline_options=pipeline_options,
+            ),
+        },
+    )
+
+    conversion_result: ConversionResult = converter.convert(source=source)
+    doc = conversion_result.document
+    md = doc.export_to_markdown()
+    print(md)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/mkdocs.yml b/mkdocs.yml
index 0fcc2ca4..abb93a27 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -77,6 +77,7 @@ nav:
       - "Multimodal export": examples/export_multimodal.py
       - "Force full page OCR": examples/full_page_ocr.py
       - "Automatic OCR language detection with tesseract": examples/tesseract_lang_detection.py
+      - "RapidOCR with custom OCR models": examples/rapidocr_with_custom_models.py
       - "Accelerator options": examples/run_with_accelerator.py
       - "Simple translation": examples/translate.py
       - examples/backend_xml_rag.ipynb