Update app.py

app.py

@@ -54,44 +54,78 @@ def process_files_fixed(image_path, page_identifier, error_pages):
         error_pages.append(page_identifier)
         return []
 
-        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": [
-            {
-                "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"
-            
-            }
-            ...
-        ]
-    }
-
+        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": [
+                    {
+                        "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"
+                    }
+                ]
+                }
+                
+                """
 
-    
-    """
+        
 
     payload = {
         "model": "gpt-4-vision-preview",