Update app.py

app.py

@@ -12,6 +12,9 @@ import json
 os.system("apt-get update")
 os.system("apt-get install poppler-utils")
 
+logging.basicConfig(level=logging.ERROR, format='%(asctime)s - %(levelname)s - %(message)s')
+
+
 # Function to convert PDF to images or open a single image
 def get_images(file_path):
     images = []
@@ -32,21 +35,25 @@ def encode_image_to_base64(image):
     image.save(buffered, format="JPEG")
     return base64.b64encode(buffered.getvalue()).decode("utf-8")
 
+
 def process_files_fixed(image_path, page_identifier, error_pages):
-    api_key= os.getenv('OPENAI_API_KEY')
+    api_key = os.getenv('OPENAI_API_KEY')
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {api_key}"
     }
 
-    # read the image and create image object
-    image = Image.open(image_path)
-    base64_image = encode_image_to_base64(image)
+    try:
+        image = Image.open(image_path)
+        base64_image = encode_image_to_base64(image)
+    except Exception as e:
+        logging.error(f"Failed to process image at {image_path}: {e}")
+        error_pages.append(page_identifier)
+        return []
 
     prompt = """Perform OCR on this image. Analyze the table in the provided image, focusing on the first five columns labeled S.No, Reg #, Roll No. and Marks. Get the marks from the 6th column and write them in fifth column in integers, make sure to check them as well for correct integer number, I don't want any mistakes in the obtained marks. 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. The obtained marks are written in both integral and written format as well. Verify both for better ocr in integers.
 
-Return the response in the following JSoN response format:
-```
+Return the response in the following JSON response format:
 {
     "data": [
         {
@@ -55,16 +62,9 @@ Return the response in the following JSoN response format:
             "Roll_No": "2345234",
             "Marks": "20"
         },
-        {
-            "S_No": "2",
-            "Reg": "059288",
-            "Roll_No": "2345235",
-            "Marks": "25"
-        },
         ...
     ]
-}
-```"""
+}"""
 
     payload = {
         "model": "gpt-4-vision-preview",
@@ -78,43 +78,43 @@ Return the response in the following JSoN response format:
                     },
                     {
                         "type": "image_url",
-                        "image_url": {
-                            "url": f"data:image/jpeg;base64,{base64_image}",
-                            "detail": "high",
-                        }
+                        "image_url": f"data:image/jpeg;base64,{base64_image}"
                     }
                 ]
             }
         ],
-        "max_tokens": 4096,
+        "max_tokens": 4096
     }
 
-    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
-
     try:
+        response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
         if response.status_code == 200:
             json_response = response.json()
             response_content = json_response["choices"][0]["message"]["content"]
-
             if response_content:
-                json_string = response_content[response_content.find("{"): response_content.rfind("}") + 1]
-                json_data = json.loads(json_string)
-                if "data" in json_data and json_data["data"]:
-                    return json_data["data"]
-                else:
-                    print(f"No records found in page/file: {page_identifier}")
+                try:
+                    json_string = response_content[response_content.find("{"): response_content.rfind("}") + 1]
+                    json_data = json.loads(json_string)
+                    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 []
             else:
-                print(f"No content in JSON response for page/file: {page_identifier}")
+                logging.error(f"No content in JSON response for page/file {page_identifier}")
                 error_pages.append(page_identifier)
                 return []
         else:
-            print(f"Error in API call 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 []
-    except Exception as e:
-        print(f"Exception processing page/file {page_identifier}: {e}")
+    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 []