Skip to content

fix: add type checks to prevent AttributeError when LLM returns malformed JSON #210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 1 commit into
base: main
Choose a base branch
from
+6 −3
Open

fix: add type checks to prevent AttributeError when LLM returns malformed JSON #210

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions pageindex/page_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -584,9 +584,12 @@ def process_no_toc(page_list, start_index=1, model=None, logger=None):
logger.info(f'len(group_texts): {len(group_texts)}')

toc_with_page_number= generate_toc_init(group_texts[0], model)
if not isinstance(toc_with_page_number, list):
toc_with_page_number = []
for group_text in group_texts[1:]:
toc_with_page_number_additional = generate_toc_continue(toc_with_page_number, group_text, model)
toc_with_page_number.extend(toc_with_page_number_additional)
toc_with_page_number_additional = generate_toc_continue(toc_with_page_number, group_text, model)
if isinstance(toc_with_page_number_additional, list):
toc_with_page_number.extend(toc_with_page_number_additional)
logger.info(f'generate_toc: {toc_with_page_number}')

toc_with_page_number = convert_physical_index_to_int(toc_with_page_number)
Expand Down Expand Up @@ -967,7 +970,7 @@ async def meta_processor(page_list, mode=None, toc_content=None, toc_page_list=N
else:
toc_with_page_number = process_no_toc(page_list, start_index=start_index, model=opt.model, logger=logger)

toc_with_page_number = [item for item in toc_with_page_number if item.get('physical_index') is not None]
toc_with_page_number = [item for item in toc_with_page_number if isinstance(item, dict) and item.get('physical_index') is not None]

toc_with_page_number = validate_and_truncate_physical_indices(
toc_with_page_number,
Expand Down