feat: expose ocr-lang in CLI (#375)

* feat: expose ocr-lang in CLI Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use regex for supporting multiple sep Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2024-11-19 15:58:49 +01:00
parent 926dfd29d5
commit ed785ea122
2 changed files with 19 additions and 0 deletions
--- a/docling/datamodel/pipeline_options.py
+++ b/docling/datamodel/pipeline_options.py
@@ -22,6 +22,7 @@ class TableStructureOptions(BaseModel):

 class OcrOptions(BaseModel):
    kind: str
+    lang: List[str]
    force_full_page_ocr: bool = False  # If enabled a full page OCR is always applied
    bitmap_area_threshold: float = (
        0.05  # percentage of the area for a bitmap to processed with OCR