Update main.py

main.py

@@ -220,7 +220,20 @@ async def startup_event():
 
 
 
-
+def preprocess_image_for_ocr(image):
+    """Apply basic image processing to improve OCR results"""
+    # Convert to grayscale
+    image = image.convert('L')
+    
+    # Increase contrast
+    from PIL import ImageEnhance
+    enhancer = ImageEnhance.Contrast(image)
+    image = enhancer.enhance(2.0)
+    
+    # Apply threshold
+    image = image.point(lambda x: 0 if x < 128 else 255, '1')
+    
+    return image
 
 
 
@@ -310,17 +323,24 @@ def extract_text(content: bytes, file_ext: str) -> str:
             return "\n".join(page.get_text("text") for page in pdf)
         
         elif file_ext in {"jpg", "jpeg", "png"}:
+            # First try OCR
             try:
                 image = Image.open(io.BytesIO(content))
+                # Pre-process image for better OCR results
+                image = image.convert('L')  # Convert to grayscale
                 text = pytesseract.image_to_string(image, config='--psm 6')
                 if text.strip():
                     return text
-                
+            except Exception as ocr_error:
+                logger.warning(f"OCR failed: {str(ocr_error)}")
+            
+            # If OCR fails, try image captioning
+            try:
                 captioner = get_image_captioner()
                 result = captioner(image)
                 return result[0]['generated_text']
-            except Exception as img_e:
-                logger.error(f"Image processing failed: {str(img_e)}")
+            except Exception as caption_error:
+                logger.error(f"Image captioning failed: {str(caption_error)}")
                 raise ValueError("Could not extract text or caption from image")
         
     except Exception as e: