Update app.py

app.py

@@ -54,76 +54,76 @@ def process_files_fixed(image_path, page_identifier, error_pages):
         error_pages.append(page_identifier)
         return []
 
-        prompt = """**Objective:** Extract specific data from a table within an image using OCR.
-
-                **Image Description:** The image contains a table with student information.
-                
-                **Columns of Interest:**
-                
-                *   S.No (Serial Number)
-                *   Admission No.
-                *   Date of Admission
-                *   Name of Student
-                *   Father's Name
-                *   Date of Birth
-                *   Telephone No. 
-                *   Address
-                *   F.CNIC (Father's CNIC) 
-                *   S.CNIC (Student's CNIC) - Located under the "REMARKS" column 
-                *   M.Name (Mother's Name) - Located under the "REMARKS" column
-                
-                **Instructions:**
-                
-                1. **Perform OCR:** Use Optical Character Recognition to extract text from the image. 
-                2. **Table Detection:** Identify the table within the image. 
-                3. **Column Identification:**
-                *   If table headers are present and visible, use them to identify the columns of interest.
-                *   If headers are missing or unclear, assume the order of columns as specified above. 
-                4. **Data Extraction:**
-                *   Extract data from each row of the table for the specified columns only.
-                *   Disregard any additional columns present in the table.
-                *   **Important:** Extract data from all rows, do not skip any rows. 
-                *   For "Telephone No.", focus on the number itself and ignore any labels like "office" or "residence" associated with it. 
-                *   For "F.CNIC", "S.CNIC", and "M.Name", extract this information from the "REMARKS" column. 
-                5. **Data Verification:**
-                *   Implement checks to ensure the accuracy of extracted data, especially for numerical values like "S.No" and "Telephone No." 
-                *   Consider using checksums or validation rules based on known formats (e.g., CNIC format).
-                
-                **Output Format:**
-                
-                ```json
+    prompt = """**Objective:** Extract specific data from a table within an image using OCR.
+
+            **Image Description:** The image contains a table with student information.
+            
+            **Columns of Interest:**
+            
+            *   S.No (Serial Number)
+            *   Admission No.
+            *   Date of Admission
+            *   Name of Student
+            *   Father's Name
+            *   Date of Birth
+            *   Telephone No. 
+            *   Address
+            *   F.CNIC (Father's CNIC) 
+            *   S.CNIC (Student's CNIC) - Located under the "REMARKS" column 
+            *   M.Name (Mother's Name) - Located under the "REMARKS" column
+            
+            **Instructions:**
+            
+            1. **Perform OCR:** Use Optical Character Recognition to extract text from the image. 
+            2. **Table Detection:** Identify the table within the image. 
+            3. **Column Identification:**
+            *   If table headers are present and visible, use them to identify the columns of interest.
+            *   If headers are missing or unclear, assume the order of columns as specified above. 
+            4. **Data Extraction:**
+            *   Extract data from each row of the table for the specified columns only.
+            *   Disregard any additional columns present in the table.
+            *   **Important:** Extract data from all rows, do not skip any rows. 
+            *   For "Telephone No.", focus on the number itself and ignore any labels like "office" or "residence" associated with it. 
+            *   For "F.CNIC", "S.CNIC", and "M.Name", extract this information from the "REMARKS" column. 
+            5. **Data Verification:**
+            *   Implement checks to ensure the accuracy of extracted data, especially for numerical values like "S.No" and "Telephone No." 
+            *   Consider using checksums or validation rules based on known formats (e.g., CNIC format).
+            
+            **Output Format:**
+            
+            ```json
+            {
+            "data": [
                 {
-                "data": [
-                    {
-                        "S_No": "1",
-                        "Admission No.": "1604",
-                        "Date of Admission": "25-4-17",
-                        "Name of Student": "Maham Tariq",
-                        "Father's Name": "Tariq Mehman",
-                        "Date of Birth": "12-05-12",
-                        "Telephone No.": "03125350838",
-                        "Address": "Dewan-e-umar Masjid F1014",
-                        "F.CNIC": "61101-9729652-7",
-                        "S.CNIC": "61101-8018797-4",
-                        "M.Name": "Nasira"
-                    },
-                    {
-                        "S_No": "2",
-                            "Admission No.": "1640",
-                            "Date of Admission": "05-10-20",
-                            "Name of Student": "Areej Jibran",
-                            "Father's Name": "M.Jibran",
-                            "Date of Birth": "05-04-14",
-                            "Telephone No.": "03335173534",
-                            "Address": "H#65 st#11 G11/I isb",
-                            "F. CNIC": "37405-0393951-3",
-                            "S.CNIC": "37405-5642572-3",
-                            "M.Name": "Taqdees Jibran"
-                    }
-                ]
+                    "S_No": "1",
+                    "Admission No.": "1604",
+                    "Date of Admission": "25-4-17",
+                    "Name of Student": "Maham Tariq",
+                    "Father's Name": "Tariq Mehman",
+                    "Date of Birth": "12-05-12",
+                    "Telephone No.": "03125350838",
+                    "Address": "Dewan-e-umar Masjid F1014",
+                    "F.CNIC": "61101-9729652-7",
+                    "S.CNIC": "61101-8018797-4",
+                    "M.Name": "Nasira"
+                },
+                {
+                    "S_No": "2",
+                        "Admission No.": "1640",
+                        "Date of Admission": "05-10-20",
+                        "Name of Student": "Areej Jibran",
+                        "Father's Name": "M.Jibran",
+                        "Date of Birth": "05-04-14",
+                        "Telephone No.": "03335173534",
+                        "Address": "H#65 st#11 G11/I isb",
+                        "F. CNIC": "37405-0393951-3",
+                        "S.CNIC": "37405-5642572-3",
+                        "M.Name": "Taqdees Jibran"
                 }
-                
-                """
+            ]
+            }
+            
+            """