feat: Docling with auto-ocr (#403)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

Containerfile

@@ -58,7 +58,7 @@ RUN --mount=from=uv_stage,source=/uv,target=/bin/uv \
     uv sync ${UV_SYNC_ARGS} ${UV_SYNC_EXTRA_ARGS} --no-extra flash-attn && \
     FLASH_ATTENTION_SKIP_CUDA_BUILD=TRUE uv sync ${UV_SYNC_ARGS} ${UV_SYNC_EXTRA_ARGS} --no-build-isolation-package=flash-attn
 
-ARG MODELS_LIST="layout tableformer picture_classifier easyocr"
+ARG MODELS_LIST="layout tableformer picture_classifier rapidocr easyocr"
 
 RUN echo "Downloading models..." && \
     HF_HUB_DOWNLOAD_TIMEOUT="90" \

pyproject.toml

@@ -55,10 +55,12 @@ ui = [
 tesserocr = [
     "tesserocr~=2.7"
 ]
+easyocr = [
+    "easyocr>=1.7",
+]
 rapidocr = [
     "rapidocr (>=3.3,<4.0.0) ; python_version < '3.14'",
     "onnxruntime (>=1.7.0,<2.0.0)",
-      "modelscope>=1.29.0",
 ]
 flash-attn = [
   "flash-attn~=2.8.2; sys_platform == 'linux' and platform_machine == 'x86_64'"