Update app.py

app.py

@@ -7,13 +7,13 @@ import cv2
 import numpy as np
 import re
 import os
-from groq import Groq
 import json
+from groq import Groq
 
-st.set_page_config(page_title="Invoice Intelligence Engine", layout="wide")
+st.set_page_config(page_title="AI Invoice Intelligence Engine", layout="wide")
 
-st.title("🚀 Invoice Intelligence Engine")
-st.write("Upload ANY invoice / receipt document")
+st.title("🚀 AI Invoice Intelligence Engine")
+st.write("Upload ANY invoice, receipt, subscription, or purchase document")
 
 uploaded_file = st.file_uploader(
     "Upload File",
@@ -44,11 +44,12 @@ def extract_text(uploaded_file):
 
 
 # ---------------------------------------------------------
-# STRUCTURED GST PARSER (FAST + ACCURATE)
+# STRUCTURED GST PARSER (FAST)
 # ---------------------------------------------------------
 
 def extract_structured_gst(text):
 
+    # Fix OCR noise
     text = text.replace("INVO1CE", "INVOICE")
     text = text.replace("GSTlN", "GSTIN")
     text = text.replace("T0tal", "Total")
@@ -86,7 +87,7 @@ def extract_structured_gst(text):
 
 
 # ---------------------------------------------------------
-# AI FALLBACK (FOR UNKNOWN FORMATS)
+# AI FALLBACK (UNIVERSAL)
 # ---------------------------------------------------------
 
 def ai_extract_invoice(text):
@@ -94,13 +95,36 @@ def ai_extract_invoice(text):
     client = Groq(api_key=os.getenv("GROQ_API_KEY"))
 
     prompt = f"""
-    Extract purchase/invoice information from this document.
-
-    Return JSON array with:
-    invoice_or_order_number, invoice_date,
-    vendor_name, total_amount.
-
-    If no purchase found, return [].
+    You are a financial document extraction engine.
+
+    If this document contains:
+    - payment confirmation
+    - subscription charge
+    - invoice
+    - receipt
+    - order confirmation
+    - total amount charged
+
+    Extract structured JSON array.
+
+    Format:
+
+    [
+      {{
+        "document_type": "",
+        "invoice_or_order_number": "",
+        "invoice_date": "",
+        "vendor_name": "",
+        "vendor_gstin": null,
+        "taxable_amount": null,
+        "cgst": null,
+        "sgst": null,
+        "igst": null,
+        "total_amount": null
+      }}
+    ]
+
+    If not purchase-related, return [].
 
     Document:
     {text}
@@ -117,38 +141,56 @@ def ai_extract_invoice(text):
         result = result.replace("```json", "").replace("```", "")
         return json.loads(result)
 
-    except:
+    except Exception as e:
+        print("AI error:", e)
         return []
 
 
 # ---------------------------------------------------------
-# MAIN EXECUTION
+# CONFIDENCE SCORE
+# ---------------------------------------------------------
+
+def calculate_confidence(row):
+
+    total_fields = len(row.keys())
+    filled_fields = sum(
+        1 for v in row.values()
+        if v not in [None, "", "null"]
+    )
+
+    return round((filled_fields / total_fields) * 100, 2)
+
+
+# ---------------------------------------------------------
+# MAIN
 # ---------------------------------------------------------
 
 if uploaded_file:
 
     raw_text = extract_text(uploaded_file)
 
-    st.subheader("Raw Text Preview")
-    st.text_area("Preview", raw_text[:2000], height=200)
+    st.subheader("📄 Raw Text Preview")
+    st.text_area("Preview", raw_text[:3000], height=200)
 
-    # Try structured GST extraction first
+    # Step 1: Try structured GST parsing
     invoices = extract_structured_gst(raw_text)
 
-    # If none found → use AI
+    # Step 2: If none found, use AI fallback
     if not invoices:
         invoices = ai_extract_invoice(raw_text)
 
     if invoices:
         df = pd.DataFrame(invoices)
-        st.success(f"✅ {len(df)} invoice(s) detected")
+        df["confidence_%"] = df.apply(calculate_confidence, axis=1)
+
+        st.success(f"✅ {len(df)} document(s) detected")
         st.dataframe(df, use_container_width=True)
 
         st.download_button(
-            "Download CSV",
+            "⬇ Download CSV",
             df.to_csv(index=False),
             "invoice_output.csv",
             "text/csv"
         )
     else:
-        st.warning("⚠ No invoice detected.")
+        st.warning("⚠ No financial transaction detected.")