Update app.py

app.py

@@ -5,21 +5,19 @@ import json
 
 def extract_fields(image):
     try:
-        # Extract text using Tesseract
         raw_text = pytesseract.image_to_string(image)
         lines = raw_text.split('\n')
         result = {}
 
         for line in lines:
+            line = line.strip()
             if ':' in line:
-                parts = line.split(':', 1)
-                key = parts[0].strip()
-                value = parts[1].strip()
-                result[key] = value
+                key, value = line.split(':', 1)
+                result[key.strip()] = value.strip()
+            elif len(line.split()) >= 2:
+                result["line_" + str(len(result))] = line
 
-        # Return as pretty JSON
         return json.dumps(result, indent=2)
-
     except Exception as e:
         return {"error": str(e)}
 
@@ -28,5 +26,5 @@ gr.Interface(
     inputs=gr.Image(type="pil"),
     outputs="json",
     title="Smart KYC OCR (Tesseract)",
-    description="Upload Aadhaar or PAN image to extract KYC fields as key-value pairs using Tesseract OCR."
+    description="Upload Aadhaar or PAN image to extract key-value KYC fields using Tesseract OCR."
 ).launch()