Skip to content

Ensuring citation peeks aren't multimodal #1138

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

Merged
merged 2 commits into from
Oct 16, 2025
Merged

Ensuring citation peeks aren't multimodal #1138

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3308720
Ensuring citation peeks aren't multimodal
jamesbraza Oct 15, 2025
fd3acb7
Ensuring peeked texts don't get used
jamesbraza Oct 15, 2025
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
3 changes: 2 additions & 1 deletion src/paperqa/docs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,7 +281,7 @@ async def aadd( # noqa: PLR0912
overlap=parse_config.overlap,
page_size_limit=parse_config.page_size_limit,
use_block_parsing=parse_config.pdfs_use_block_parsing,
parse_images=parse_config.multimodal,
parse_images=False, # Peeking is text only
parse_pdf=parse_config.parse_pdf,
)
if not texts or not texts[0].text.strip():
Expand All @@ -300,6 +300,7 @@ async def aadd( # noqa: PLR0912
or "insufficient" in citation
):
citation = f"Unknown, {os.path.basename(path)}, {datetime.now().year}"
del result, texts # Ensure we don't reuse

doc = Doc(
docname=self._get_unique_name(
Expand Down