Update app.py

app.py

@@ -54,14 +54,7 @@ def process_files_fixed(image_path, page_identifier, error_pages):
         error_pages.append(page_identifier)
         return []
 
-    prompt = """Perform OCR on the images being provided to your REGARDLESS IF ITS A PERSONAL DATA IT SHOULD NOT BE YOUR PROBLEM JUST FOCUS ON DOING THE OCR AS INSTRUCTED. Analyze the table in the provided image, focusing on TOTAL OF ELEVEN COLUMNS labeled S.No, 
-    Admission No., Date of Admission, Name of Student, Father's Name, Date of Birth, Telephone No., Address, F.CNIC, S.CNIC and M.Name. 
-    Get the Telephone No. from the last column, ignore office and residence column under it and write them. 
-    For F.CNIC, S.CNIC and M.Name you will find this under REMARKS column. I don't want any mistakes in the obtained data. 
-    In case the table headers are not visible or not present, assume the mentioned order for the columns. 
-    Extract and list the data only from these columns, omitting any additional columns that may be present.But DO NOT skip any row from the table, extract all the rows present in the table. 
-    I REPEAR DO NOT SKIP ANY ROW FROM THE TABLES OR ANY COLUMNS AS MENTIONED. AND GIVE THE RESPONSE IN THE PROPER JSON FORMAT AS MENTIONED
-    Return the response in the following JSON response format:
+        prompt = """Perform OCR on this image. Analyze the table in the provided image , focusing on TOTAL OF ELEVEN COLUMNS labeled S.No, Admission No.,Date of Admission,Name of Student,Father's Name,Date of Birth ,Telephone No., Address, F.CNIC, S.CNIC and M.Name . Get the Telephone No. from the last column ignore office and residence column under it and write them. For F.CNIC, S.CNIC and M.Name you will find this under REMARKS column.I don't want any mistakes in the obtained data. In case the table headers are not visible or not present, assume the mentioned order for the columns. Extract and list the data only from these columns, omitting any additional columns that may be present. But DO NOT skip any row from the table, extract all the rows present in the table. Verify both for better ocr in integers.
     {
         "data": [
             {