Update docling versions

Signed-off-by: Aakanksha Duggal <aduggal@redhat.com>

Author: aakankshaduggal

requirements.txt

@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: Apache-2.0
 click>=8.1.7,<9.0.0
 datasets>=2.18.0,<3.0.0
-docling[tesserocr]>=2.4.2,<=2.8.3; sys_platform != 'darwin'
-docling>=2.4.2,<=2.8.3; sys_platform == 'darwin'
-docling-parse>=2.0.0,<3.0.0
+docling[tesserocr]>=2.9.0; sys_platform != 'darwin'
+docling>=2.9.0; sys_platform == 'darwin'
+docling-parse>=3.3.0
 GitPython>=3.1.42,<4.0.0
 gguf>=0.6.0
 httpx>=0.25.0,<1.0.0

src/instructlab/sdg/utils/taxonomy.py

@@ -151,7 +151,7 @@ def extract_text_from_pdf(file_path: str) -> str:
             )
             page_text = "\n".join(text_lines)
             pdf_text += page_text + "\n"
-        except Exception as e:
+        except Exception as e:  # pylint: disable=broad-exception-caught
             logger.warning(
                 f"Error extracting text from page {page_no} of '{file_path}': {e}"
             )