diff options
author | A.J. Shulman <Shulman.aj@gmail.com> | 2025-04-03 11:45:02 -0400 |
---|---|---|
committer | A.J. Shulman <Shulman.aj@gmail.com> | 2025-04-03 11:45:02 -0400 |
commit | a99d8df26d331d87bae4f27cd52ce5ec4d97fa7a (patch) | |
tree | ad1df355214acd734ecf4b25fa1157f5b252f4f0 /src/server/chunker/pdf_chunker.py | |
parent | 45a9f5789fa6eaacca9a39cb96cc2a8e3ebe649c (diff) |
attempt
Diffstat (limited to 'src/server/chunker/pdf_chunker.py')
-rw-r--r-- | src/server/chunker/pdf_chunker.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/server/chunker/pdf_chunker.py b/src/server/chunker/pdf_chunker.py index 697550f2e..9d4cfb1b2 100644 --- a/src/server/chunker/pdf_chunker.py +++ b/src/server/chunker/pdf_chunker.py @@ -153,7 +153,7 @@ class ElementExtractor: xref = img_info[0] # XREF of the image in the PDF base_image = page.parent.extract_image(xref) # Extract the image by its XREF image_bytes = base_image["image"] - image = Image.open(io.BytesIO(image_bytes)) # Convert bytes to PIL image + image = Image.open(io.BytesIO(image_bytes)).convert("RGB") # Ensure it's RGB before saving as PNG width_ratio = img.width / page.rect.width # Scale factor for width height_ratio = img.height / page.rect.height # Scale factor for height |