Update app.py

app.py

@@ -62,7 +62,67 @@ def fetch_file_from_s3_file(file_key):
 
 # Function to summarize text using OpenAI GPT
 def summarize_text(text):
-    system_prompt = "You are a helpful assistant that summarizes extracted Invoice OCR text into JSON format always."
+    system_prompt = """You are tasked with extracting and structuring all relevant information from an invoice in a standardized JSON format for storing invoice headers and line items. The invoice headers should include the following details:
+
+Vendor Information:
+
+Vendor Name
+Vendor Address
+Vendor GST No.
+Invoice Details:
+
+Invoice No./Bill No./Consecutive Serial No./Serial No. of Invoice/INVOICE → Considered as InvoiceNo.
+Invoice Date/Date/Date of Supply/Bill Date/Issuing Date/Dated → Considered as InvoiceDate (formatted as dd-MMM-yyyy).
+Invoice Currency/Currency
+Base Amount/Amount
+Tax Amount
+Total Invoice Amount
+Type of Invoice (e.g., "Tax Invoice", "Proforma Invoice", etc.)
+Billing Party Information:
+
+Invoice Party/Bill To Name/Sold-to-Party/Taxpayer Name/M/s./CB No./Buyer (Bill to)/Billing Party/Customer Name & Address/Name → Considered as BillToName.
+Invoice Party to / Bill To Address
+Invoice Party to / Bill To GST No.
+Shipping and References:
+
+MBL No./HBL No./Container No./Shipping Bill No./Shipper Invoice No./Manifest No./MAWB/HAWB/OBL No./Bill of Lading Number/REF/Ocean Bill of Lading/House Bill of Lading/BL No./Job No. → Considered as RefNo.
+Shipping Order
+You should extract this data and structure it into a table-like format in the following JSON format:
+{
+  "invoice_headers": {
+    "VendorName": "",
+    "VendorAddress": "",
+    "VendorGSTNo": "",
+    "InvoiceNo": "",
+    "InvoiceDate": "",
+    "InvoiceCurrency": "",
+    "BaseAmount": "",
+    "TaxAmount": "",
+    "TotalInvoiceAmt": "",
+    "TypeofInvoice": "",
+    "BillToName": "",
+    "BillToAddress": "",
+    "BillToGSTNO": "",
+    "RefNo": "",
+    "ShippingOrder": ""
+  },
+  "line_items": [
+    {    
+      "Description": "",
+      "TaxPercentage": "",
+      "TaxAmount": "",
+      "Amount": 0
+    }
+  ]
+}
+Guidelines for Processing:
+
+Ensure accurate extraction of data from the invoice by recognizing alternative naming conventions (e.g., Bill to, Taxpayer Name, etc.).
+Convert the Invoice Date to the specified dd-MMM-yyyy format.
+Use the correct currency and amounts for each invoice field.
+For each line item, provide the Description, Tax Percentage, Tax Amount, and Amount.
+If certain values are missing or not applicable, leave them empty or set them as null where necessary.
+This JSON format will be used to store and manage invoices in a structured and uniform way."""
     try:
         response = openai.ChatCompletion.create(
             model="gpt-4o-mini",
@@ -74,14 +134,14 @@ def summarize_text(text):
             max_tokens=16384
         )
         content = response.choices[0].message.content.strip()
-        cleaned_content = re.sub(r'^```json\n', '', content)  # Remove '```json\n' at the beginning
-        cleaned_content = re.sub(r'\n```$', '', cleaned_content)  # Remove '\n```' at the end
+       # cleaned_content = re.sub(r'^```json\n', '', content)  # Remove '```json\n' at the beginning
+        #cleaned_content = re.sub(r'\n```$', '', cleaned_content)  # Remove '\n```' at the end
 
         # Step 2: Parse the cleaned content as JSON
-        parsed_content = json.loads(cleaned_content)
+        #parsed_content = json.loads(cleaned_content)
 
         # Step 3: Print the parsed JSON object
-        return parsed_content
+        return content # parsed_content
     except Exception as e:
         return f"Error in summarization: {str(e)}"
 # Dependency to check API Key