Update app.py

app.py

@@ -53,28 +53,26 @@ 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.
-Return the response in the following JSON response format:
-{
-    "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"
-            
-           
-        },
-        ...
-    ]
-}"""
+    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.
+    Return the response in the following JSON response format:
+    {
+        "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"
+            },
+            ...
+        ]
+    }"""
 
     payload = {
         "model": "gpt-4-vision-preview",
@@ -96,38 +94,37 @@ Return the response in the following JSON response format:
         "max_tokens": 4096
     }
 
-   try:
-    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
-    logging.info(f"Full API response: {response.text}")
-    if response.status_code == 200:
-        response_text = response.text
-        # Use regex to extract JSON from the API response content
-        matches = re.findall(r"```json\n(\{.*?\})\n```", response_text, re.DOTALL)
-        if matches:
-            try:
-                json_data = json.loads(matches[0])  # Assuming the first match is the required JSON data
-                if "data" in json_data and json_data["data"]:
-                    return json_data["data"]
-                else:
-                    logging.error(f"No records found in page/file: {page_identifier}")
+    try:
+        response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+        logging.info(f"Full API response: {response.text}")
+        if response.status_code == 200:
+            response_text = response.text
+            matches = re.findall(r"```json\n(\{.*?\})\n```", response_text, re.DOTALL)
+            if matches:
+                try:
+                    json_data = json.loads(matches[0])
+                    if "data" in json_data and json_data["data"]:
+                        return json_data["data"]
+                    else:
+                        logging.error(f"No records found in page/file: {page_identifier}")
+                        error_pages.append(page_identifier)
+                        return []
+                except json.JSONDecodeError:
+                    logging.error(f"JSON parsing error in response for page/file {page_identifier}")
                     error_pages.append(page_identifier)
                     return []
-            except json.JSONDecodeError:
-                logging.error(f"JSON parsing error in response for page/file {page_identifier}")
+            else:
+                logging.error(f"No valid JSON found in response for page/file {page_identifier}")
                 error_pages.append(page_identifier)
                 return []
         else:
-            logging.error(f"No valid JSON found in response for page/file {page_identifier}")
+            logging.error(f"Error in API call for page/file {page_identifier}: HTTP {response.status_code} - {response.text}")
             error_pages.append(page_identifier)
             return []
-    else:
-        logging.error(f"Error in API call for page/file {page_identifier}: HTTP {response.status_code} - {response.text}")
+    except requests.exceptions.RequestException as e:
+        logging.error(f"Network or API error when processing page/file {page_identifier}: {e}")
         error_pages.append(page_identifier)
         return []
-except requests.exceptions.RequestException as e:
-    logging.error(f"Network or API error when processing page/file {page_identifier}: {e}")
-    error_pages.append(page_identifier)
-    return []
 
 def process_pdf_and_generate_csv(file_path):
     error_pages = []  # Initialize the list to track error pages or files