fix(pdf): convert CMYK images before vision analysis (#6917)

2026-11-01 02:32:21 +01:00 · 2026-10-31 13:22:55 +00:00
parent 70fc58225c
commit 48c3a7fc36
2 changed files with 102 additions and 1 deletions
@@ -142,7 +142,10 @@ def _process_pdf(
                        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
                            temp_img_path = tmp.name
                        try:
-                            img.image.save(temp_img_path, "PNG")  # pypdf -> PIL image
+                            image = img.image
+                            if image.mode == "CMYK":
+                                image = image.convert("RGB")
+                            image.save(temp_img_path, "PNG")
                            ocr_text = analyze_image_with_vl(temp_img_path, owner=owner)
                            if ocr_text and "unavailable" not in ocr_text.lower():
                                pdf_text += f"\n\n[Page {page_num + 1} image {img_index + 1} text]: {ocr_text}"