Update app.py

app.py

@@ -108,33 +108,98 @@ 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": "",
+#     "CustomerName": "",
+#     "CustomerAddress": "",
+#     "CustomerGSTNO": "",
+#     "RefNo": "",
+#     "ShippingOrder": ""
+#   },
+#   "line_items": [
+#     {    
+#       "Description": "",
+#       "TaxPercentage": "",
+#       "TaxAmount": "",
+#       "Amount": 0
+#     }
+#   ]
+# }
+
 {
-  "invoice_headers": {
-    "VendorName": "",
-    "VendorAddress": "",
-    "VendorGSTNo": "",
-    "InvoiceNo": "",
-    "InvoiceDate": "",
-    "InvoiceCurrency": "",
-    "BaseAmount": "",
-    "TaxAmount": "",
-    "TotalInvoiceAmt": "",
-    "TypeofInvoice": "",
-    "CustomerName": "",
-    "CustomerAddress": "",
-    "CustomerGSTNO": "",
-    "RefNo": "",
-    "ShippingOrder": ""
-  },
-  "line_items": [
-    {    
-      "Description": "",
-      "TaxPercentage": "",
-      "TaxAmount": "",
-      "Amount": 0
-    }
-  ]
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "type": "object",
+    "title": "Invoice Information Extractor",
+    "description": "Schema for extracting specific information from invoices",
+    "properties": {
+        "invoice_headers": {
+            "type": "object",
+            "properties": {
+                "VendorName": { "type": "string", "description": "The name of the vendor" },
+                "VendorAddress": { "type": "string", "description": "The address of the vendor" },
+                "VendorGSTNo": { "type": "string", "description": "The GST number of the vendor" },
+                "InvoiceNo": { "type": "string", "description": "The number of the invoice" },
+                "InvoiceDate": { "type": "string", "format": "date", "description": "The date of the invoice in dd-MMM-yyyy format" },
+                "InvoiceCurrency": { "type": "string", "description": "The currency used in the invoice (e.g., USD, INR, AUD)" },
+                "BaseAmount": { "type": "number", "description": "The base amount before tax" },
+                "TaxAmount": { "type": "number", "description": "The tax amount on the invoice" },
+                "TotalInvoiceAmt": { "type": "number", "description": "The total amount on the invoice" },
+                "TypeofInvoice": { "type": "string", "description": "Type of invoice (e.g., Tax Invoice, Proforma Invoice)" },
+                "CustomerName": { "type": "string", "description": "The name of the customer" },
+                "CustomerAddress": { "type": "string", "description": "The address of the customer" },
+                "CustomerGSTNO": { "type": "string", "description": "The GST number of the customer" },
+                "RefNo": { "type": "string", "description": "Reference number related to shipping or order" },
+                "ShippingOrder": { "type": "string", "description": "Shipping order details" }
+            },
+            "required": [
+                "VendorName",
+                "VendorAddress",
+                "VendorGSTNo",
+                "InvoiceNo",
+                "InvoiceDate",
+                "InvoiceCurrency",
+                "BaseAmount",
+                "TaxAmount",
+                "TotalInvoiceAmt",
+                "TypeofInvoice",
+                "CustomerName",
+                "CustomerAddress",
+                "CustomerGSTNO",
+                "RefNo",
+                "ShippingOrder"
+            ],
+            "additionalProperties": false
+        },
+        "line_items": {
+            "type": "array",
+            "description": "List of line items on the invoice",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "Description": { "type": "string", "description": "Description of the product/service" },
+                    "TaxPercentage": { "type": "number", "description": "Tax percentage applied to the line item" },
+                    "TaxAmount": { "type": "number", "description": "Tax amount for the line item" },
+                    "Amount": { "type": "number", "description": "The total amount for the line item" }
+                },
+                "required": ["Description", "TaxPercentage", "TaxAmount", "Amount"],
+                "additionalProperties": false
+            }
+        }
+    },
+    "required": ["invoice_headers", "line_items"],
+    "additionalProperties": false
 }
+
 Guidelines for Processing:
 
 Ensure accurate extraction of data from the invoice by recognizing alternative naming conventions (e.g., Bill to, Taxpayer Name, etc.).