Update app.py

app.py

@@ -14,37 +14,19 @@ def process_file(files):
         response = ocr_request(file.name)
         response_arr.append(response)
 
-    print("Main file :", response_arr)
-    
-    #i= [[{'invoice_number': '349136', 'product_description': '1ST FLOOR WALLS', 'predicted_material': 'Framing', 'confidence': 0.8}, {'invoice_number': '349136', 'product_description': "11.875 X 16 ' Pro Lam 2.0 LVL 1.75 ( 7 @ 16 ' , 4 @\n8 ' )", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "COLUMN\n11.875 X 10 ' Pro Lam 2.0 LVL 1.75", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '3495565136', 'product_description': "Power Column 3 1/2 X 5 1/2 - 08 '", 'predicted_material': 'Framing', 'confidence': 0.9}],[{'invoice_number': '349136', 'product_description': ' FLOOR WALLS', 'predicted_material': 'Framing', 'confidence': 0.8}, {'invoice_number': '349136', 'product_description': "11.875 X 16 ' Pro Lam 2.0 LVL 1.75 ( 7 @ 16 ' , 4 @\n8 ' )", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "COLUMN\n11.875 X 10 ' Pro Lam 2.0 LVL 1.75", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "Power Column 3 1/2 X 5 1/2 - 08 '", 'predicted_material': 'Framing', 'confidence': 0.9}]] 
-    # flat_list = []
-
-    # for item in response_arr:
-    #     invoice_number = item['invoice_number']
-        
-    #     # Extracting product descriptions
-    #     products = item.get('predictions', []) or item.get('product_description', [])
-        
-    #     for product in products:
-    #         # Rename 'description' key to 'product_description' for uniformity across all products
-    #         product_description = product.get('product_description', product.get('description'))
-    #         predicted_material = product['predicted_material']
-    #         confidence = product['confidence']
-            
-    #         flat_list.append({
-    #             'invoice_number': invoice_number,
-    #             'product_description': product_description,
-    #             'predicted_material': predicted_material,
-    #             'confidence': confidence
-    #         })
-
+    print("Main file :", response_arr)    
+ 
     load_dotenv()
     # Initialize OpenAI with your API key
     openai.api_key = os.getenv("OPENAI_API_KEY")
 
     prompt =f"""
-    you are an excellent programmer and an anlyst. Given a json array or a json, you need to analyse it and convert into a json format which can be converted in dataframe of pandas easily. You have a singular task : 
-    Once you have thought through, produce a json, easily convertible to a dataframe in python, which would contain invoice number, product description, predicted material, confidence. Remember: You just have to share the o/p json, no thought process or anything else.   
+    you are an excellent programmer and an anlyst. Given a json array or a json, you need to analyse it and convert into a json format which can be converted in dataframe of pandas easily. 
+    You have a singular task : 
+    Once you have thought through, produce a json, easily convertible to a dataframe in python, which would contain invoice number, product description, predicted material, confidence. 
+    Remember:You just have to share the output json, NO thought process or extra words or anything else.
+    If it is a nested structure, flatten it. ONLY JSON should be in the output, not json within a list.
+    
 
     Here is the json array/json : {json.dumps(response_arr)}
     """