fix: Introduce Image format options in CLI. Silence the tqdm downloading messages. (#544)

* fix: main: Introduce format options for Image with the same pdf pipeline_options.
Add RapidOcrOptions to the Union of ocr_options for PdfPipelineOptions

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: Silence the tqdm messages during the downloading of model files

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: Code styling

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: Use the HF API to disable the tqdm progress bars

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

---------

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

docling/cli/main.py

@@ -372,11 +372,13 @@ def convert(
         else:
             raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
-        format_options: Dict[InputFormat, FormatOption] = {
-            InputFormat.PDF: PdfFormatOption(
+        pdf_format_option = PdfFormatOption(
             pipeline_options=pipeline_options,
             backend=backend,  # pdf_backend
         )
+        format_options: Dict[InputFormat, FormatOption] = {
+            InputFormat.PDF: pdf_format_option,
+            InputFormat.IMAGE: pdf_format_option,
         }
         doc_converter = DocumentConverter(
             allowed_formats=from_formats,

docling/datamodel/pipeline_options.py

@@ -143,7 +143,11 @@ class PdfPipelineOptions(PipelineOptions):
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
     ocr_options: Union[
-        EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, OcrMacOptions
+        EasyOcrOptions,
+        TesseractCliOcrOptions,
+        TesseractOcrOptions,
+        OcrMacOptions,
+        RapidOcrOptions,
     ] = Field(EasyOcrOptions(), discriminator="kind")
 
     images_scale: float = 1.0

docling/pipeline/standard_pdf_pipeline.py

@@ -97,7 +97,9 @@ class StandardPdfPipeline(PaginatedPipeline):
         local_dir: Optional[Path] = None, force: bool = False
     ) -> Path:
         from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
 
+        disable_progress_bars()
         download_path = snapshot_download(
             repo_id="ds4sd/docling-models",
             force_download=force,