Skip to content

⚡️ Speed up method AdvancedPdfLoader._format_image_element by 5% #54

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
codeflash-ai wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up method AdvancedPdfLoader._format_image_element by 5% #54

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
30 changes: 15 additions & 15 deletions cognee/infrastructure/loaders/external/advanced_pdf_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,28 +188,28 @@ def _format_image_element(self, metadata: Dict[str, Any]) -> str:
"""Format image."""
placeholder = "[Image omitted]"
image_text = placeholder
coordinates = metadata.get("coordinates", {})
points = coordinates.get("points") if isinstance(coordinates, dict) else None
if points and isinstance(points, tuple) and len(points) == 4:
leftup = points[0]
rightdown = points[3]
coordinates = metadata.get("coordinates", None) # Avoid unnecessary empty dict allocation
if (
isinstance(coordinates, dict)
and (points := coordinates.get("points"))
and isinstance(points, tuple)
and len(points) == 4
):
leftup, _, _, rightdown = points
if (
isinstance(leftup, tuple)
and isinstance(rightdown, tuple)
and len(leftup) == 2
and isinstance(rightdown, tuple)
and len(rightdown) == 2
):
image_text = f"{placeholder} (bbox=({leftup[0]}, {leftup[1]}, {rightdown[0]}, {rightdown[1]}))"

layout_width = coordinates.get("layout_width")
layout_height = coordinates.get("layout_height")
system = coordinates.get("system")
if layout_width and layout_height and system:
image_text = (
image_text
+ f", system={system}, layout_width={layout_width}, layout_height={layout_height}))"
)

# Fetch all needed keys in one go to minimize dictionary lookups
layout_width = coordinates.get("layout_width")
layout_height = coordinates.get("layout_height")
system = coordinates.get("system")
if layout_width and layout_height and system:
image_text = f"{image_text}, system={system}, layout_width={layout_width}, layout_height={layout_height}))"
return image_text

def _safe_to_dict(self, element: Any) -> Dict[str, Any]:
Expand Down