Update the pypdf2 to pypdf because pypdf2 is no longer maintained

Signed-off-by: Aakanksha Duggal <[email protected]>

requirements.txt

@@ -10,6 +10,7 @@ openai>=1.13.3,<2.0.0
 #       removed once that one is removed.
 # do not use 8.4.0 due to a bug in the library
 # https://github.com/instructlab/instructlab/issues/1389
+pypdf>=5.0.0
 tabulate>=0.9.0
 tenacity>=8.3.0,!=8.4.0
 transformers>=4.44.2

src/instructlab/sdg/utils/taxonomy.py

@@ -18,7 +18,7 @@
 )
 import git
 import gitdb
-import PyPDF2
+from pypdf import PdfReader
 import yaml
 
 # Local
@@ -103,7 +103,6 @@ def _get_taxonomy(repo="taxonomy"):
                 taxonomy_file_paths.append(str(file_path))
     return taxonomy_file_paths
 
-
 def _get_documents(
     source: Dict[str, Union[str, List[str]]],
     skip_checkout: bool = False,
@@ -145,10 +144,10 @@ def _get_documents(
                         elif file_path.endswith(".pdf"):
                             # Process PDF files
                             with open(file_path, "rb") as file:
-                                reader = PyPDF2.PdfReader(file)
+                                reader = PdfReader(file)  # Use pypdf PdfReader
                                 pdf_text = ""
-                                for page in range(len(reader.pages)):
-                                    pdf_text += reader.pages[page].extract_text()
+                                for page in reader.pages:  # Iterating through pages
+                                    pdf_text += page.extract_text()
                                 file_contents.append(pdf_text)
 
             if file_contents:
@@ -158,7 +157,6 @@ def _get_documents(
         except (OSError, git.exc.GitCommandError, FileNotFoundError) as e:
             logger.error("Error retrieving documents: %s", str(e))
             raise e
-
 
 # pylint: disable=broad-exception-caught
 def _read_taxonomy_file(file_path: str | Path, yamllint_config: str | None = None):