Update app.py

app.py

@@ -79,18 +79,34 @@ st.markdown(
 )
 
 # =============================
-# Currency Helper (₹)
+# Currency helpers (₹ with Indian grouping)
 # =============================
 CURRENCY = "₹"
 
-def fmt_currency(x: float) -> str:
+def format_inr(x: float) -> str:
+    """Format number with Indian digit grouping, no decimals."""
     try:
-        return f"{CURRENCY}{x:,.0f}"
+        n = int(round(float(x)))
     except Exception:
         return f"{CURRENCY}{x}"
+    s = str(n)
+    if len(s) <= 3:
+        return f"{CURRENCY}{s}"
+    last3 = s[-3:]
+    rest = s[:-3]
+    parts = []
+    while len(rest) > 2:
+        parts.insert(0, rest[-2:])
+        rest = rest[:-2]
+    if rest:
+        parts.insert(0, rest)
+    return f"{CURRENCY}{','.join(parts + [last3])}"
+
+def fmt_currency(x: float) -> str:
+    return format_inr(x)
 
 # =============================
-# Config & LLM Client (resilient)
+# LLM client (resilient)
 # =============================
 @dataclass
 class LLMConfig:
@@ -105,12 +121,10 @@ class LLMConfig:
     max_retries: int = int(os.getenv("OPENAI_MAX_RETRIES", "5"))
     temperature: float = float(os.getenv("OPENAI_TEMPERATURE", "0.5"))
 
-
 def _post_json(url: str, headers: Dict[str, str], payload: Dict[str, Any], timeout: int):
     import requests
     return requests.post(url, headers=headers, json=payload, timeout=timeout)
 
-
 class UniversalLLMClient:
     def __init__(self, cfg: LLMConfig):
         self.cfg = cfg
@@ -203,22 +217,22 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
         order_value = round(unit_price * qty, 2)
 
         po = {
-            'po_number': f"PO{str(i+1).zfill(6)}",
-            'vendor': random.choice(vendors),
-            'material_category': random.choice(categories),
-            'order_date': order_date,
-            'promised_date': promised_date,
-            'delivery_date': delivery_date,
-            'late_delivery': late,
-            'order_value': order_value,
-            'quantity': qty,
-            'unit_price': unit_price,
-            'status': random.choice(['Open', 'Delivered', 'Invoiced', 'Paid']),
-            'plant': random.choice(['Plant_001', 'Plant_002', 'Plant_003']),
-            'buyer': fake.name(),
-            'currency': 'INR',
-            'payment_terms': random.choice(['30 Days', '45 Days', '60 Days', '90 Days']),
-            'quality_score': round(np.clip(np.random.normal(8.5, 0.8), 5.0, 10.0), 1),
+            "po_number": f"PO{str(i+1).zfill(6)}",
+            "vendor": random.choice(vendors),
+            "material_category": random.choice(categories),
+            "order_date": order_date,
+            "promised_date": promised_date,
+            "delivery_date": delivery_date,
+            "late_delivery": late,
+            "order_value": order_value,
+            "quantity": qty,
+            "unit_price": unit_price,
+            "status": random.choice(["Open", "Delivered", "Invoiced", "Paid"]),
+            "plant": random.choice(["Plant_001", "Plant_002", "Plant_003"]),
+            "buyer": fake.name(),
+            "currency": "INR",
+            "payment_terms": random.choice(["30 Days", "45 Days", "60 Days", "90 Days"]),
+            "quality_score": round(np.clip(np.random.normal(8.5, 0.8), 5.0, 10.0), 1),
         }
         purchase_orders.append(po)
 
@@ -226,12 +240,12 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
     for v in vendors:
         for c in categories:
             spend_rows.append({
-                'vendor': v,
-                'category': c,
-                'total_spend': round(random.uniform(10000, 700000), 2),
-                'contract_compliance': round(random.uniform(78, 100), 1),
-                'risk_score': round(random.uniform(1, 10), 1),
-                'savings_potential': round(random.uniform(5, 25), 1),
+                "vendor": v,
+                "category": c,
+                "total_spend": round(random.uniform(10000, 700000), 2),
+                "contract_compliance": round(random.uniform(78, 100), 1),
+                "risk_score": round(random.uniform(1, 10), 1),
+                "savings_potential": round(random.uniform(5, 25), 1),
             })
 
     po_df = pd.DataFrame(purchase_orders)
@@ -244,49 +258,66 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
 class ProcurementAnalytics:
     def __init__(self, po_df: pd.DataFrame):
         self.df = po_df.copy()
-        self.df['order_date'] = pd.to_datetime(self.df['order_date'])
-        self.df['month'] = self.df['order_date'].dt.to_period('M').dt.to_timestamp()
+        self.df["order_date"] = pd.to_datetime(self.df["order_date"])
+        self.df["month"] = self.df["order_date"].dt.to_period("M").dt.to_timestamp()
 
     def kpis(self) -> Dict[str, Any]:
         df = self.df
         return {
-            'total_spend': float(df['order_value'].sum()),
-            'avg_order_value': float(df['order_value'].mean()),
-            'active_vendors': int(df['vendor'].nunique()),
-            'on_time_rate': float((~df['late_delivery']).mean()),
-            'quality_avg': float(df['quality_score'].mean()),
+            "total_spend": float(df["order_value"].sum()),
+            "avg_order_value": float(df["order_value"].mean()),
+            "active_vendors": int(df["vendor"].nunique()),
+            "on_time_rate": float((~df["late_delivery"]).mean()),
+            "quality_avg": float(df["quality_score"].mean()),
         }
 
     def category_spend(self) -> pd.DataFrame:
-        return self.df.groupby('material_category', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False)
+        return (
+            self.df.groupby("material_category", as_index=False)["order_value"]
+            .sum()
+            .sort_values("order_value", ascending=False)
+        )
 
     def vendor_spend(self, top_n: int = 8) -> pd.DataFrame:
-        return self.df.groupby('vendor', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False).head(top_n)
+        return (
+            self.df.groupby("vendor", as_index=False)["order_value"]
+            .sum()
+            .sort_values("order_value", ascending=False)
+            .head(top_n)
+        )
 
     def monthly_spend(self) -> pd.DataFrame:
-        return self.df.groupby('month', as_index=False)['order_value'].sum().sort_values('month')
+        return (
+            self.df.groupby("month", as_index=False)["order_value"]
+            .sum()
+            .sort_values("month")
+        )
 
     def vendor_performance(self) -> pd.DataFrame:
-        g = self.df.groupby('vendor').agg(
-            total_spend=('order_value', 'sum'),
-            on_time=('late_delivery', lambda s: 1 - s.mean()),
-            quality=('quality_score', 'mean'),
-            orders=('po_number', 'count'),
+        g = self.df.groupby("vendor").agg(
+            total_spend=("order_value", "sum"),
+            on_time=("late_delivery", lambda s: 1 - s.mean()),
+            quality=("quality_score", "mean"),
+            orders=("po_number", "count"),
         )
-        g['on_time'] = (g['on_time'] * 100).round(1)
-        g['quality'] = g['quality'].round(2)
-        g['total_spend'] = g['total_spend'].round(2)
-        return g.sort_values('total_spend', ascending=False)
+        g["on_time"] = (g["on_time"] * 100).round(1)
+        g["quality"] = g["quality"].round(2)
+        g["total_spend"] = g["total_spend"].round(2)
+        return g.sort_values("total_spend", ascending=False)
 
     def top_n_categories(self, n: int = 3) -> List[Tuple[str, float]]:
         cat = self.category_spend()
-        total = float(cat['order_value'].sum()) or 1.0
-        return [(r['material_category'], (r['order_value']/total)*100) for _, r in cat.head(n).iterrows()]
+        total = float(cat["order_value"].sum()) or 1.0
+        return [(r["material_category"], (r["order_value"] / total) * 100) for _, r in cat.head(n).iterrows()]
 
     def top_n_vendors(self, n: int = 3) -> List[Tuple[str, float]]:
-        ven = self.df.groupby('vendor', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False)
-        total = float(ven['order_value'].sum()) or 1.0
-        return [(r['vendor'], (r['order_value']/total)*100) for _, r in ven.head(n).iterrows()]
+        ven = (
+            self.df.groupby("vendor", as_index=False)["order_value"]
+            .sum()
+            .sort_values("order_value", ascending=False)
+        )
+        total = float(ven["order_value"].sum()) or 1.0
+        return [(r["vendor"], (r["order_value"] / total) * 100) for _, r in ven.head(n).iterrows()]
 
 # =============================
 # Agent with tighter prompts & INR formatting
@@ -299,51 +330,48 @@ class UniversalProcurementAgent:
         self.analytics = ProcurementAnalytics(po_df)
 
     def executive_summary(self) -> str:
-    if not self.llm.available:
-        return self._rule_summary()
-
-    k = self.analytics.kpis()
-    top_cats = self.analytics.top_n_categories(3)
-    top_vens = self.analytics.top_n_vendors(3)
-    data_summary = {
-        "total_spend": k['total_spend'],
-        "total_orders": int(len(self.po_data)),
-        "vendor_count": int(self.po_data['vendor'].nunique()),
-        "avg_order_value": k['avg_order_value'],
-        "on_time_delivery": k['on_time_rate'],
-        "avg_quality": k['quality_avg'],
-        "top_categories": top_cats,
-        "top_vendors": top_vens,
-    }
-
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are a senior procurement analyst. Use bullet points, be concise, "
-                "and always use the ₹ symbol. When summarizing, include top categories "
-                "and vendors with percentages, then 2-3 quantified actions."
-            ),
-        },
-        {
-            "role": "user",
-            "content": (
-                "Executive summary. Format amounts with commas (e.g., ₹12,34,567).\n\n"
-                f"Data: {json.dumps(data_summary)}"
-            ),
-        },
-    ]
+        if not self.llm.available:
+            return self._rule_summary()
 
-    try:
-        return (
-            "🧠 **[AI-Powered Analysis]**\n\n"
-            + self.llm.chat(messages, max_tokens=550)
-        )
-    except Exception as e:
-        return self._rule_summary() + f"\n\n*AI fallback due to: {e}*"
+        k = self.analytics.kpis()
+        top_cats = self.analytics.top_n_categories(3)
+        top_vens = self.analytics.top_n_vendors(3)
+        data_summary = {
+            "total_spend": k["total_spend"],
+            "total_orders": int(len(self.po_data)),
+            "vendor_count": int(self.po_data["vendor"].nunique()),
+            "avg_order_value": k["avg_order_value"],
+            "on_time_delivery": k["on_time_rate"],
+            "avg_quality": k["quality_avg"],
+            "top_categories": top_cats,
+            "top_vendors": top_vens,
+        }
 
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a senior procurement analyst. Use bullet points, be concise, "
+                    "and always use the ₹ symbol. When summarizing, include top categories "
+                    "and vendors with percentages, then 2-3 quantified actions."
+                ),
+            },
+            {
+                "role": "user",
+                "content": (
+                    "Executive summary. Format amounts with Indian commas (e.g., ₹12,34,567).\n\n"
+                    f"Data: {json.dumps(data_summary)}"
+                ),
+            },
+        ]
 
-*AI fallback due to: {e}*"
+        try:
+            return (
+                "🧠 **[AI-Powered Analysis]**\n\n"
+                + self.llm.chat(messages, max_tokens=550)
+            )
+        except Exception as e:
+            return self._rule_summary() + f"\n\n*AI fallback due to: {e}*"
 
     def _rule_summary(self) -> str:
         k = self.analytics.kpis()
@@ -352,31 +380,27 @@ class UniversalProcurementAgent:
         topc_str = ", ".join([f"{n} – {s:.0f}%" for n, s in top_c])
         topv_str = ", ".join([f"{n} – {s:.0f}%" for n, s in top_v])
         return (
-            "🤖 **[Rule-Based Summary]**
-"
-            + f"• Total spend: {fmt_currency(k['total_spend'])} across {len(self.po_data):,} POs
-"
-            + f"• On-time delivery: {k['on_time_rate']*100:.1f}% | Avg quality: {k['quality_avg']:.1f}/10
-"
-            + f"• Top categories: {topc_str}
-"
-            + f"• Top vendors: {topv_str}
-"
+            "🤖 **[Rule-Based Summary]**\n"
+            + f"• Total spend: {fmt_currency(k['total_spend'])} across {len(self.po_data):,} POs\n"
+            + f"• On-time delivery: {k['on_time_rate']*100:.1f}% | Avg quality: {k['quality_avg']:.1f}/10\n"
+            + f"• Top categories: {topc_str}\n"
+            + f"• Top vendors: {topv_str}\n"
             + "Actions: Consolidate long tail; multi-year terms with top vendors; auto-approve low-value POs."
         )
 
     def chat_with_data(self, question: str) -> str:
         if not self.llm.available:
             return self._rule_answer(question)
+
         k = self.analytics.kpis()
         top_c = self.analytics.top_n_categories(3)
         top_v = self.analytics.top_n_vendors(3)
         context = {
-            "total_spend": k['total_spend'],
+            "total_spend": k["total_spend"],
             "orders": int(len(self.po_data)),
-            "vendors": int(self.po_data['vendor'].nunique()),
-            "on_time": k['on_time_rate'],
-            "quality": k['quality_avg'],
+            "vendors": int(self.po_data["vendor"].nunique()),
+            "on_time": k["on_time_rate"],
+            "quality": k["quality_avg"],
             "top_categories": top_c,
             "top_vendors": top_v,
         }
@@ -387,29 +411,22 @@ class UniversalProcurementAgent:
         )
         messages = [
             {"role": "system", "content": "You are a precise procurement co-pilot. Be direct, metric-first, and action-oriented."},
-            {"role": "user", "content": f"Q: {question}
-
-Context: {json.dumps(context)}
-
-{style_rules}"},
+            {"role": "user", "content": f"Q: {question}\n\nContext: {json.dumps(context)}\n\n{style_rules}"},
         ]
         try:
             return (
-                "🧠 **[AI Response]**
-
-"
+                "🧠 **[AI Response]**\n\n"
                 + self.llm.chat(messages, max_tokens=450)
             )
         except Exception as e:
-            return self._rule_answer(question) + f"
-
-*AI fallback due to: {e}*"
+            return self._rule_answer(question) + f"\n\n*AI fallback due to: {e}*"
 
     def _rule_answer(self, question: str) -> str:
         q = question.lower()
         k = self.analytics.kpis()
         top_c = self.analytics.top_n_categories(3)
         top_v = self.analytics.top_n_vendors(3)
+
         if ("spend" in q) or ("spending" in q) or ("cost" in q):
             lines = [
                 f"• Total spend: {fmt_currency(k['total_spend'])}",
@@ -417,50 +434,45 @@ Context: {json.dumps(context)}
                 "• Top vendors: " + ", ".join([f"{n} – {s:.0f}%" for n, s in top_v]),
                 "• Action: Run sourcing events for top 2 categories; target 8–12% savings via volume tiers.",
             ]
-            return "🤖 **[Rule-Based Spend]**
-" + "
-".join(lines)
+            return "🤖 **[Rule-Based Spend]**\n" + "\n".join(lines)
+
         if ("vendor" in q) or ("supplier" in q) or ("partner" in q):
-            vp = self.po_data.groupby('vendor').agg(
-                spend=('order_value','sum'),
-                late_rate=('late_delivery','mean'),
-                quality=('quality_score','mean'),
-            ).sort_values('spend', ascending=False)
+            vp = self.po_data.groupby("vendor").agg(
+                spend=("order_value", "sum"),
+                late_rate=("late_delivery", "mean"),
+                quality=("quality_score", "mean"),
+            ).sort_values("spend", ascending=False)
             best = vp.head(1)
-            worst = vp.sort_values('late_rate', ascending=False).head(1)
+            worst = vp.sort_values("late_rate", ascending=False).head(1)
             bname, wname = best.index[0], worst.index[0]
-            blate = float(best.iloc[0]['late_rate'])*100
-            wlate = float(worst.iloc[0]['late_rate'])*100
+            blate = float(best.iloc[0]["late_rate"]) * 100
+            wlate = float(worst.iloc[0]["late_rate"]) * 100
             lines = [
                 f"• Best by spend: {bname} (late {blate:.1f}%)",
                 f"• Worst by late deliveries: {wname} (late {wlate:.1f}%)",
                 "• Action: Extend terms with best performer; corrective plan and SLA penalties for the worst.",
             ]
-            return "🤖 **[Rule-Based Vendor]**
-" + "
-".join(lines)
+            return "🤖 **[Rule-Based Vendor]**\n" + "\n".join(lines)
+
         if ("risk" in q) or ("late" in q) or ("delay" in q):
-            late = float(self.po_data['late_delivery'].mean())*100
+            late = float(self.po_data["late_delivery"].mean()) * 100
             lines = [
                 f"• Late delivery rate: {late:.1f}%",
                 "• Action: Add 5–10 day buffers; fast-track chronic offenders; add service credits for misses.",
             ]
-            return "🤖 **[Rule-Based Risk]**
-" + "
-".join(lines)
+            return "🤖 **[Rule-Based Risk]**\n" + "\n".join(lines)
+
         return (
-            "🤖 **[Rule-Based]**
-"
-            + "• I can analyze spend (top categories/vendors), vendor performance (best/worst), risk (late %), and trends.
-"
+            "🤖 **[Rule-Based]**\n"
+            + "• I can analyze spend (top categories/vendors), vendor performance (best/worst), risk (late %), and trends.\n"
             + f"• Snapshot: {fmt_currency(k['total_spend'])}, {len(self.po_data):,} POs, {self.po_data['vendor'].nunique()} vendors, on-time {k['on_time_rate']*100:.1f}%"
         )
 
 # =============================
 # App State & Initialization
 # =============================
-if 'data_loaded' not in st.session_state:
-    with st.spinner('🔄 Generating synthetic SAP S/4HANA procurement data...'):
+if "data_loaded" not in st.session_state:
+    with st.spinner("🔄 Generating synthetic SAP S/4HANA procurement data..."):
         st.session_state.po_df, st.session_state.spend_df = generate_synthetic_procurement_data()
         st.session_state.data_loaded = True
 
@@ -477,7 +489,7 @@ status = {
     "last_error": client.last_error or "OK",
     "model": client.cfg.model,
 }
-api_status = "🟢 Connected" if status['available'] else "🔴 Not Connected"
+api_status = "🟢 Connected" if status["available"] else "🔴 Not Connected"
 
 # =============================
 # Header
@@ -506,8 +518,8 @@ with st.sidebar:
 
     selected = option_menu(
         "Navigation",
-        ["🏠 Dashboard", "💬 AI Chat", "📊 Analytics", "🧪 What‑If", "🎯 Recommendations"],
-        icons=['house', 'chat', 'bar-chart', 'beaker', 'target'],
+        ["🏠 Dashboard", "💬 AI Chat", "📊 Analytics", "🧪 What-If", "🎯 Recommendations"],
+        icons=["house", "chat", "bar-chart", "beaker", "target"],
         menu_icon="cast",
         default_index=0,
         styles={
@@ -523,7 +535,7 @@ with st.sidebar:
 # =============================
 if selected == "🏠 Dashboard":
     st.markdown("### 🧠 AI Executive Summary")
-    with st.spinner('🤖 Analyzing procurement data...'):
+    with st.spinner("🤖 Analyzing procurement data..."):
         summary = agent.executive_summary()
     st.markdown(
         (
@@ -575,7 +587,7 @@ if selected == "🏠 Dashboard":
         st.markdown(
             (
                 "<div class='metric-card'>"
-                "<h3 style='color: var(--primary-color); margin:0;'>On‑Time Delivery</h3>"
+                "<h3 style='color: var(--primary-color); margin:0;'>On-Time Delivery</h3>"
                 + f"<h2 style='margin: .5rem 0;'>{k['on_time_rate']*100:.1f}%</h2>"
                 "<p style='color:#28a745;margin:0;'>⏱ Performance</p>"
                 "</div>"
@@ -588,20 +600,20 @@ if selected == "🏠 Dashboard":
 
     with colA:
         cat = analytics.category_spend()
-        fig = px.pie(cat, values='order_value', names='material_category', title='Spend Distribution by Category')
+        fig = px.pie(cat, values="order_value", names="material_category", title="Spend Distribution by Category")
         fig.update_layout(title_font_size=16, title_x=0.5, height=420)
         st.plotly_chart(fig, use_container_width=True)
 
     with colB:
         vend = analytics.vendor_spend(top_n=8)
-        fig2 = px.bar(vend, x='vendor', y='order_value', title='Top Vendors by Spend')
+        fig2 = px.bar(vend, x="vendor", y="order_value", title="Top Vendors by Spend")
         fig2.update_layout(title_font_size=16, title_x=0.5, xaxis_tickangle=45, height=420)
         st.plotly_chart(fig2, use_container_width=True)
 
     colC, colD = st.columns(2)
     with colC:
         ms = analytics.monthly_spend()
-        fig3 = px.line(ms, x='month', y='order_value', markers=True, title='Monthly Spend Trend')
+        fig3 = px.line(ms, x="month", y="order_value", markers=True, title="Monthly Spend Trend")
         fig3.update_layout(title_font_size=16, title_x=0.5, height=420)
         st.plotly_chart(fig3, use_container_width=True)
 
@@ -627,7 +639,7 @@ elif selected == "💬 AI Chat":
 
     if "messages" not in st.session_state:
         st.session_state.messages = [
-            {"role": "assistant", "content": "Hello! Try: 'What are my biggest spending areas?' or 'Which vendor is the weakest on delivery?'"}
+            {"role": "assistant", "content": "Hello! Try: 'What are my biggest spending areas?' or 'Which vendor is the weakest on delivery?'"},
         ]
 
     for m in st.session_state.messages:
@@ -661,29 +673,34 @@ elif selected == "💬 AI Chat":
 elif selected == "📊 Analytics":
     st.markdown("### 📈 Advanced Analytics Dashboard")
     vp = analytics.vendor_performance()
-    st.dataframe(vp.rename(columns={
-        'total_spend': 'Total Spend (₹)',
-        'on_time': 'On-Time Delivery %',
-        'quality': 'Quality Score',
-        'orders': 'Order Count',
-    }), use_container_width=True)
+    st.dataframe(
+        vp.rename(
+            columns={
+                "total_spend": "Total Spend (₹)",
+                "on_time": "On-Time Delivery %",
+                "quality": "Quality Score",
+                "orders": "Order Count",
+            }
+        ),
+        use_container_width=True,
+    )
 
     st.download_button(
         label="⬇️ Download Vendor Performance (CSV)",
-        data=vp.to_csv().encode('utf-8'),
+        data=vp.to_csv().encode("utf-8"),
         file_name="vendor_performance.csv",
         mime="text/csv",
     )
 
-elif selected == "🧪 What‑If":
-    st.markdown("### 🧪 What‑If: Vendor Consolidation Simulator")
+elif selected == "🧪 What-If":
+    st.markdown("### 🧪 What-If: Vendor Consolidation Simulator")
     top_n = st.slider("Keep top N vendors by spend", min_value=2, max_value=10, value=6, step=1)
 
-    g = st.session_state.po_df.groupby('vendor')['order_value'].sum().sort_values(ascending=False)
+    g = st.session_state.po_df.groupby("vendor")["order_value"].sum().sort_values(ascending=False)
     kept_vendors = list(g.head(top_n).index)
-    kept_spend = st.session_state.po_df[st.session_state.po_df['vendor'].isin(kept_vendors)]['order_value'].sum()
-    total_spend = st.session_state.po_df['order_value'].sum()
-    share = (kept_spend/total_spend) if total_spend else 0
+    kept_spend = st.session_state.po_df[st.session_state.po_df["vendor"].isin(kept_vendors)]["order_value"].sum()
+    total_spend = st.session_state.po_df["order_value"].sum()
+    share = (kept_spend / total_spend) if total_spend else 0
     est_savings = max(0.03, min(0.18, 0.05 + (0.12 * (1 - share))))
 
     kept_names = ", ".join(kept_vendors)
@@ -699,7 +716,7 @@ elif selected == "🧪 What‑If":
     )
 
     if st.checkbox("Show detailed vendor spend"):
-        st.dataframe(g.reset_index().rename(columns={'index':'vendor','order_value':'spend (₹)'}), use_container_width=True)
+        st.dataframe(g.reset_index().rename(columns={"index": "vendor", "order_value": "spend (₹)"}), use_container_width=True)
 
 elif selected == "🎯 Recommendations":
     st.markdown("### 🚀 Strategic Recommendations")