Upload folder using huggingface_hub

builders/build_excel.py

@@ -417,6 +417,10 @@ def _dcf_sheet(wb, data):
     debt = debt_history[-1] if debt_history else 0
     
     # Inputs
+    val_snap = data.get("valuation_snapshot", {})
+    wacc_est = val_snap.get("wacc_estimate", 0.10)
+    target_price = val_snap.get("target_mean_price", "N/A")
+    
     r = 4
     _sec(ws, r, "Model Inputs (Editable - Yellow Cells)", 2); r += 1
     
@@ -424,7 +428,7 @@ def _dcf_sheet(wb, data):
     ws.cell(row=r, column=2, value=latest_fcf).font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_MONEY; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="FFFFE0"); r += 1
     
     ws.cell(row=r, column=1, value="WACC (Discount Rate)").font = LBL_FONT
-    ws.cell(row=r, column=2, value=0.10).font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_PCT; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="FFFFE0"); r += 1
+    ws.cell(row=r, column=2, value=wacc_est).font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_PCT; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="FFFFE0"); r += 1
     
     ws.cell(row=r, column=1, value="Terminal Growth Rate").font = LBL_FONT
     ws.cell(row=r, column=2, value=0.025).font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_PCT; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="FFFFE0"); r += 1
@@ -494,8 +498,11 @@ def _dcf_sheet(wb, data):
     ws.cell(row=r, column=1, value="Implied Equity Value").font = LBL_FONT
     ws.cell(row=r, column=2, value="=B23+B8-B9").font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_MONEY; r += 1
     
-    ws.cell(row=r, column=1, value="Implied Share Price").font = Font(name="Calibri", size=12, bold=True, color="1F4E78")
-    ws.cell(row=r, column=2, value="=B24/B10").font = Font(name="Calibri", size=12, bold=True); ws.cell(row=r, column=2).number_format = FMT_DEC; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="DDEBF7")
+    ws.cell(row=r, column=1, value="Implied Share Price").font = Font(name="Calibri", size=12, bold=True)
+    ws.cell(row=r, column=2, value="=B24/B10").font = Font(name="Calibri", size=12, bold=True); ws.cell(row=r, column=2).number_format = FMT_MONEY; r += 1
+    
+    ws.cell(row=r, column=1, value="Analyst Mean Target Price").font = LBL_FONT
+    ws.cell(row=r, column=2, value=target_price).font = DAT_FONT; ws.cell(row=r, column=2).number_format = FMT_MONEY; ws.cell(row=r, column=2).fill = PatternFill("solid", fgColor="DDEBF7"); r += 1
     
     _widths(ws, [30, 20, 20, 20, 20, 20])
 

builders/build_pptx.py

@@ -1,449 +1,439 @@
-"""
-builders/build_pptx.py — PowerPoint presentation builder.
-
-Generates a widescreen (16:9) PPTX presentation summarizing the financial analysis
-and AI narrative, strictly matching user-defined theme, colors, and layout structure.
-"""
-import os
-import sys
-import datetime
-from pathlib import Path
-from typing import Dict, List
-
-# import python-pptx classes
-from pptx import Presentation
-from pptx.util import Inches, Pt
-from pptx.dml.color import RGBColor
-from pptx.enum.text import PP_ALIGN
-from pptx.enum.shapes import MSO_SHAPE
-from pptx.enum.shapes import MSO_CONNECTOR
-
-# Color Palette defined in User Rules
-COLOR_DARK_TEXT = RGBColor(0, 0, 0)         # 000000 (Black)
-COLOR_LIGHT_BG = RGBColor(255, 255, 255)     # FFFFFF (White)
-COLOR_DARK_GREEN = RGBColor(0, 132, 0)      # 008400 (Green Bar 1)
-COLOR_LIGHT_GREEN = RGBColor(149, 203, 137)  # 95CB89 (Green Bar 2)
-COLOR_GRAY_LINE = RGBColor(0, 0, 0)         # 000000 (Black bottom line)
-COLOR_DARK_SLATE = RGBColor(69, 95, 81)     # 455F51 (Dark slate green)
-COLOR_LIGHT_GRAY = RGBColor(227, 222, 209)  # E3DED1 (Light warm gray/beige)
-COLOR_ACCENT = RGBColor(84, 158, 57)        # 549E39 (Accent green)
-
-FONT_MAJOR = "Helvetica Neue Bold"
-FONT_MINOR = "Helvetica Neue Light"
-FONT_MAJOR_FALLBACK = "Arial"
-FONT_MINOR_FALLBACK = "Arial"
-
-def _apply_theme_decorations(slide, prs):
-    """
-    Applies the layout rectangles and bottom line strictly defined in the
-    Slide Master Layout.
-    """
-    # 1. Decorative top-left dark green bar
-    # rect: x: 0.15, y: 0.0, w: 0.36, h: 1.16
-    rect1 = slide.shapes.add_shape(
-        MSO_SHAPE.RECTANGLE, 
-        Inches(0.15), Inches(0.0), Inches(0.36), Inches(1.16)
-    )
-    rect1.fill.solid()
-    rect1.fill.fore_color.rgb = COLOR_DARK_GREEN
-    rect1.line.fill.background()  # No border line
-
-    # 2. Decorative top-left light green bar
-    # rect: x: 0.55, y: 0.0, w: 0.11, h: 1.39
-    rect2 = slide.shapes.add_shape(
-        MSO_SHAPE.RECTANGLE, 
-        Inches(0.55), Inches(0.0), Inches(0.11), Inches(1.39)
-    )
-    rect2.fill.solid()
-    rect2.fill.fore_color.rgb = COLOR_LIGHT_GREEN
-    rect2.line.fill.background()  # No border line
-
-    # 3. Decorative bottom line
-    # line: x: 0.67, y: 6.83, w: 12.0, h: 0.0
-    connector = slide.shapes.add_connector(
-        MSO_CONNECTOR.STRAIGHT,
-        Inches(0.67), Inches(6.83), Inches(12.67), Inches(6.83)
-    )
-    connector.line.color.rgb = COLOR_GRAY_LINE
-    connector.line.width = Pt(1)
-
-def _add_slide_title(slide, text: str):
-    """
-    Adds the Slide Title using Layout 7 Title configurations:
-    placeholder: x: 0.81, y: 0.29, w: 11.74, h: 0.38, align: left, valign: top
-    """
-    tx_box = slide.shapes.add_textbox(
-        Inches(0.81), Inches(0.29), Inches(11.74), Inches(0.38)
-    )
-    tf = tx_box.text_frame
-    tf.word_wrap = True
-    tf.margin_top = 0
-    tf.margin_bottom = 0
-    tf.margin_left = 0
-    tf.margin_right = 0
-    
-    p = tf.paragraphs[0]
-    p.text = text
-    p.font.name = FONT_MAJOR
-    p.font.size = Pt(20)
-    p.font.bold = True
-    p.font.color.rgb = COLOR_DARK_TEXT
-    p.alignment = PP_ALIGN.LEFT
-
-def _add_bullet_points(slide, bullets: List[str], top_inch=1.56, height_inch=5.14):
-    """
-    Adds bullet points body text block using Master 2 Body:
-    placeholder: x: 0.67, y: top, w: 12.0, h: height
-    """
-    tx_box = slide.shapes.add_textbox(
-        Inches(0.67), Inches(top_inch), Inches(12.0), Inches(height_inch)
-    )
-    tf = tx_box.text_frame
-    tf.word_wrap = True
-    tf.margin_top = 0
-    tf.margin_bottom = 0
-    tf.margin_left = 0
-    tf.margin_right = 0
-    
-    for i, b in enumerate(bullets):
-        p = tf.add_paragraph() if i > 0 else tf.paragraphs[0]
-        p.text = "•  " + b
-        p.font.name = FONT_MINOR
-        p.font.size = Pt(15)
-        p.font.color.rgb = COLOR_DARK_TEXT
-        p.space_after = Pt(8)
-        p.line_spacing = 1.2
-
-def _style_table_cell(cell, text: str, font_name=FONT_MINOR, font_size=11, bold=False, text_color=COLOR_DARK_TEXT, bg_color=None, align=PP_ALIGN.CENTER):
-    """Styles cell texts and background fills."""
-    cell.text = text
-    p = cell.text_frame.paragraphs[0]
-    p.alignment = align
-    p.font.name = font_name
-    p.font.size = Pt(font_size)
-    p.font.bold = bold
-    p.font.color.rgb = text_color
-    
-    if bg_color:
-        cell.fill.solid()
-        cell.fill.fore_color.rgb = bg_color
-
-def build_presentation(data: Dict, output_path: str):
-    """
-    Assembles a widescreen PowerPoint report from scraped financial data and AI models output.
-    """
-    prs = Presentation()
-    
-    # Strictly configure widescreen 16:9 aspect ratio
-    prs.slide_width = Inches(13.333)
-    prs.slide_height = Inches(7.5)
-    
-    blank_layout = prs.slide_layouts[6] # Blank slide template
-    
-    company_name = data.get("company", {}).get("name", "Unknown Company")
-    ticker = data.get("company", {}).get("ticker", "N/A")
-    industry = data.get("company", {}).get("industry", "N/A")
-    sector = data.get("company", {}).get("sector", "N/A")
-    date_str = data.get("company", {}).get("report_date", datetime.date.today().isoformat())
-    years = data.get("years", [])
-    
-    # ==========================================
-    # SLIDE 1: Title Slide
-    # ==========================================
-    slide_title = prs.slides.add_slide(blank_layout)
-    _apply_theme_decorations(slide_title, prs)
-    
-    # Title Text Frame
-    title_box = slide_title.shapes.add_textbox(
-        Inches(1.0), Inches(2.2), Inches(11.3), Inches(2.0)
-    )
-    tf = title_box.text_frame
-    tf.word_wrap = True
-    p1 = tf.paragraphs[0]
-    p1.text = company_name
-    p1.font.name = FONT_MAJOR
-    p1.font.size = Pt(40)
-    p1.font.bold = True
-    p1.font.color.rgb = COLOR_DARK_TEXT
-    
-    p2 = tf.add_paragraph()
-    p2.text = f"Financial Analysis & Investment Insights ({ticker})"
-    p2.font.name = FONT_MINOR
-    p2.font.size = Pt(22)
-    p2.font.color.rgb = COLOR_DARK_SLATE
-    p2.space_before = Pt(8)
-
-    # Subtitle Info (Date / Authors)
-    sub_box = slide_title.shapes.add_textbox(
-        Inches(1.0), Inches(5.0), Inches(11.3), Inches(1.2)
-    )
-    tf_sub = sub_box.text_frame
-    p_sub = tf_sub.paragraphs[0]
-    p_sub.text = f"Report Date: {date_str}  |  Sector: {sector}  |  Industry: {industry}"
-    p_sub.font.name = FONT_MINOR
-    p_sub.font.size = Pt(13)
-    p_sub.font.color.rgb = COLOR_DARK_SLATE
-    
-    p_sub2 = tf_sub.add_paragraph()
-    p_sub2.text = "Disclaimer: This report is for informational purposes only and does not constitute investment advice."
-    p_sub2.font.name = FONT_MINOR
-    p_sub2.font.size = Pt(11)
-    p_sub2.font.color.rgb = COLOR_DARK_SLATE
-    p_sub2.space_before = Pt(6)
-
-    # ==========================================
-    # SLIDE 2: Executive Summary
-    # ==========================================
-    exec_summary_text = data.get("executive_summary", "")
-    if exec_summary_text and len(exec_summary_text) > 50:
-        slide_exec = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_exec, prs)
-        _add_slide_title(slide_exec, "Executive Summary")
-        
-        # Clean up text and divide into bullet blocks
-        paragraphs = [p.strip() for p in exec_summary_text.split('\n') if p.strip()]
-        _add_bullet_points(slide_exec, paragraphs[:5])
-
-    # ==========================================
-    # SLIDE 3: Key Financial Highlights Table
-    # ==========================================
-    if years:
-        slide_metrics = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_metrics, prs)
-        _add_slide_title(slide_metrics, "Key Financial Performance")
-        
-        # Build Grid Table
-        cols = len(years) + 1
-        rows = 6
-        table_shape = slide_metrics.shapes.add_table(
-            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.8)
-        )
-        table = table_shape.table
-        
-        # Column Headers
-        _style_table_cell(table.cell(0, 0), "Financial Metric", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
-        for idx, y in enumerate(years):
-            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
-            
-        metrics = [
-            ("Revenue", "revenue", "income_statement", 1.0),
-            ("Gross Profit", "gross_profit", "income_statement", 1.0),
-            ("Operating Income (EBIT)", "operating_income", "income_statement", 1.0),
-            ("Net Income", "net_income", "income_statement", 1.0),
-            ("Operating Cash Flow (OCF)", "cash_from_operations", "cash_flow", 1.0)
-        ]
-        
-        currency = data.get("company", {}).get("currency", "USD")
-        units = data.get("company", {}).get("units", "millions")
-        
-        for r_idx, (m_label, dict_key, sheet_name, scale) in enumerate(metrics):
-            curr_row = r_idx + 1
-            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
-            
-            # Label cell
-            _style_table_cell(table.cell(curr_row, 0), f"{m_label} ({currency} {units.capitalize()})", FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
-            
-            # Values cells
-            sheet_data = data.get(sheet_name, {})
-            val_list = sheet_data.get(dict_key, [])
-            for c_idx, y in enumerate(years):
-                val_str = "N/A"
-                if c_idx < len(val_list) and val_list[c_idx] is not None:
-                    val_str = f"{val_list[c_idx]:,.1f}"
-                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
-                
-        # Brief Narrative summary underneath table
-        rev_commentary = data.get("trend_analysis", {}).get("revenue_and_profitability", "")
-        if rev_commentary:
-            comment_box = slide_metrics.shapes.add_textbox(Inches(0.8), Inches(5.6), Inches(11.7), Inches(1.1))
-            tf_c = comment_box.text_frame
-            tf_c.word_wrap = True
-            p_c = tf_c.paragraphs[0]
-            p_c.text = "Key Takeaway: " + (rev_commentary[:260] + "..." if len(rev_commentary) > 260 else rev_commentary)
-            p_c.font.name = FONT_MINOR
-            p_c.font.size = Pt(12)
-            p_c.font.italic = True
-            p_c.font.color.rgb = COLOR_DARK_SLATE
-
-    # ==========================================
-    # SLIDE 4: Dupont ROE Decomposition
-    # ==========================================
-    dp_data = data.get("dupont", {})
-    if dp_data and "years" in dp_data:
-        slide_dp = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_dp, prs)
-        _add_slide_title(slide_dp, "DuPont ROE Analysis (Latest 3 Years)")
-        
-        dp_years = dp_data.get("years", [])
-        cols = len(dp_years) + 1
-        rows = 5
-        table_shape = slide_dp.shapes.add_table(
-            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
-        )
-        table = table_shape.table
-        
-        # Headers
-        _style_table_cell(table.cell(0, 0), "DuPont Component", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
-        for idx, y in enumerate(dp_years):
-            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
-            
-        components = [
-            ("Net Profit Margin (%)", "Net Margin"),
-            ("Asset Turnover (x)", "Asset Turnover"),
-            ("Equity Multiplier (x)", "Equity Multiplier"),
-            ("Return on Equity (ROE %)", "ROE")
-        ]
-        
-        for r_idx, (c_label, key) in enumerate(components):
-            curr_row = r_idx + 1
-            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
-            is_bold = (curr_row == 4)  # Bold ROE row
-            
-            _style_table_cell(table.cell(curr_row, 0), c_label, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
-            
-            vals_list = dp_data.get(key, [])
-            for c_idx, y in enumerate(dp_years):
-                val_str = "N/A"
-                if c_idx < len(vals_list) and vals_list[c_idx] is not None:
-                    val_val = vals_list[c_idx]
-                    if "%" in c_label or "ROE" in key:
-                        val_str = f"{val_val * 100:.1f}%" if val_val < 1.0 else f"{val_val:.1f}%"
-                    else:
-                        val_str = f"{val_val:.2f}x"
-                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color)
-                
-        # DuPont Commentary Text Box
-        commentary = data.get("trend_analysis", {}).get("balance_sheet_strength", "")
-        if commentary:
-            comment_box = slide_dp.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
-            tf_c = comment_box.text_frame
-            tf_c.word_wrap = True
-            p_c = tf_c.paragraphs[0]
-            p_c.text = "DuPont Drivers & Balance Sheet Strength: " + (commentary[:380] + "..." if len(commentary) > 380 else commentary)
-            p_c.font.name = FONT_MINOR
-            p_c.font.size = Pt(12)
-            p_c.font.color.rgb = COLOR_DARK_TEXT
-            p_c.line_spacing = 1.2
-
-    # ==========================================
-    # SLIDE 5: Competitor Benchmarking
-    # ==========================================
-    peers_list = data.get("peers", [])
-    if peers_list:
-        slide_peers = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_peers, prs)
-        _add_slide_title(slide_peers, "Competitor Benchmarking")
-        
-        # Build Grid Table
-        cols = 5
-        rows = min(len(peers_list) + 1, 6)
-        table_shape = slide_peers.shapes.add_table(
-            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
-        )
-        table = table_shape.table
-        
-        # Headers
-        headers = ["Company", "Revenue Growth", "Operating Margin", "P/E Ratio", "ROE"]
-        for c_idx, h in enumerate(headers):
-            _style_table_cell(table.cell(0, c_idx), h, FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT if c_idx == 0 else PP_ALIGN.CENTER)
-            
-        for r_idx in range(rows - 1):
-            peer = peers_list[r_idx]
-            curr_row = r_idx + 1
-            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
-            
-            # Format peer outputs
-            rev_gr = peer.get("revenue_growth", "N/A")
-            if isinstance(rev_gr, float): rev_gr = f"{rev_gr*100:.1f}%"
-            op_marg = peer.get("operating_margin", "N/A")
-            if isinstance(op_marg, float): op_marg = f"{op_marg*100:.1f}%"
-            pe_r = peer.get("pe_ratio", "N/A")
-            if isinstance(pe_r, float): pe_r = f"{pe_r:.1f}x"
-            roe_val = peer.get("roe", "N/A")
-            if isinstance(roe_val, float): roe_val = f"{roe_val*100:.1f}%"
-            
-            _style_table_cell(table.cell(curr_row, 0), peer.get("name", "N/A"), FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
-            _style_table_cell(table.cell(curr_row, 1), str(rev_gr), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
-            _style_table_cell(table.cell(curr_row, 2), str(op_marg), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
-            _style_table_cell(table.cell(curr_row, 3), str(pe_r), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
-            _style_table_cell(table.cell(curr_row, 4), str(roe_val), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
-            
-        # Peer comparison commentary
-        peer_comm = data.get("peer_comparison_commentary", "")
-        if peer_comm:
-            comment_box = slide_peers.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
-            tf_c = comment_box.text_frame
-            tf_c.word_wrap = True
-            p_c = tf_c.paragraphs[0]
-            p_c.text = "Benchmarking Insights: " + (peer_comm[:380] + "..." if len(peer_comm) > 380 else peer_comm)
-            p_c.font.name = FONT_MINOR
-            p_c.font.size = Pt(12)
-            p_c.font.color.rgb = COLOR_DARK_TEXT
-            p_c.line_spacing = 1.2
-
-    # ==========================================
-    # SLIDE 6: Financial Visualizations
-    # ==========================================
-    try:
-        from builders.chart_builder import generate_all_charts
-        charts = generate_all_charts(data)
-        
-        for chart_key, title in [
-            ("revenue_net_income", "Revenue & Net Income Trend"),
-            ("margins", "Profitability Margins"),
-            ("cash_flow", "Cash Flow & CAPEX Overview")
-        ]:
-            if charts.get(chart_key):
-                slide_chart = prs.slides.add_slide(blank_layout)
-                _apply_theme_decorations(slide_chart, prs)
-                _add_slide_title(slide_chart, title)
-                
-                # Add picture centrally
-                slide_chart.shapes.add_picture(
-                    charts[chart_key],
-                    Inches(1.5), Inches(1.5), width=Inches(10.0)
-                )
-    except Exception as e:
-        import sys
-        print(f"Warning: Could not generate PPTX charts: {e}", file=sys.stderr)
-
-    # ==========================================
-    # SLIDE 7: Key Synthesis Insights
-    # ==========================================
-    insights_list = data.get("key_insights", [])
-    if insights_list:
-        slide_insights = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_insights, prs)
-        _add_slide_title(slide_insights, "Synthesized Key Insights")
-        
-        # Clean insights
-        clean_insights = []
-        for ins in insights_list:
-            if isinstance(ins, dict):
-                clean_insights.append(f"{ins.get('title', '')}: {ins.get('text', '')}")
-            else:
-                clean_insights.append(str(ins))
-                
-        _add_bullet_points(slide_insights, clean_insights[:4])
-
-    # ==========================================
-    # SLIDE 7: Risks & Red Flags
-    # ==========================================
-    risks_list = data.get("risks", [])
-    if risks_list:
-        slide_risks = prs.slides.add_slide(blank_layout)
-        _apply_theme_decorations(slide_risks, prs)
-        _add_slide_title(slide_risks, "Investment Risks & Key Red Flags")
-        
-        clean_risks = []
-        for r in risks_list:
-            if isinstance(r, dict):
-                clean_risks.append(f"{r.get('title', '')} ({r.get('impact', 'Medium Impact')}): {r.get('text', '')}")
-            else:
-                clean_risks.append(str(r))
-                
-        _add_bullet_points(slide_risks, clean_risks[:4])
-
-    # Save Presentation
-    os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
-    prs.save(output_path)
+"""
+builders/build_pptx.py — PowerPoint presentation builder.
+
+Generates a widescreen (16:9) PPTX presentation summarizing the financial analysis
+and AI narrative, strictly matching user-defined theme, colors, and layout structure.
+"""
+import os
+import sys
+import datetime
+from pathlib import Path
+from typing import Dict, List
+
+# import python-pptx classes
+from pptx import Presentation
+from pptx.util import Inches, Pt
+from pptx.dml.color import RGBColor
+from pptx.enum.text import PP_ALIGN
+from pptx.enum.shapes import MSO_SHAPE
+from pptx.enum.shapes import MSO_CONNECTOR
+
+# Color Palette defined in User Rules
+COLOR_DARK_TEXT = RGBColor(0, 0, 0)         # 000000 (Black)
+COLOR_LIGHT_BG = RGBColor(255, 255, 255)     # FFFFFF (White)
+COLOR_DARK_GREEN = RGBColor(0, 132, 0)      # 008400 (Green Bar 1)
+COLOR_LIGHT_GREEN = RGBColor(149, 203, 137)  # 95CB89 (Green Bar 2)
+COLOR_GRAY_LINE = RGBColor(0, 0, 0)         # 000000 (Black bottom line)
+COLOR_DARK_SLATE = RGBColor(69, 95, 81)     # 455F51 (Dark slate green)
+COLOR_LIGHT_GRAY = RGBColor(227, 222, 209)  # E3DED1 (Light warm gray/beige)
+COLOR_ACCENT = RGBColor(84, 158, 57)        # 549E39 (Accent green)
+
+FONT_MAJOR = "Helvetica Neue Bold"
+FONT_MINOR = "Helvetica Neue Light"
+FONT_MAJOR_FALLBACK = "Arial"
+FONT_MINOR_FALLBACK = "Arial"
+
+def _apply_theme_decorations(slide, prs):
+    """
+    Applies the layout rectangles and bottom line strictly defined in the
+    Slide Master Layout.
+    """
+    # 1. Decorative top-left dark green bar
+    # rect: x: 0.15, y: 0.0, w: 0.36, h: 1.16
+    rect1 = slide.shapes.add_shape(
+        MSO_SHAPE.RECTANGLE, 
+        Inches(0.15), Inches(0.0), Inches(0.36), Inches(1.16)
+    )
+    rect1.fill.solid()
+    rect1.fill.fore_color.rgb = COLOR_DARK_GREEN
+    rect1.line.fill.background()  # No border line
+
+    # 2. Decorative top-left light green bar
+    # rect: x: 0.55, y: 0.0, w: 0.11, h: 1.39
+    rect2 = slide.shapes.add_shape(
+        MSO_SHAPE.RECTANGLE, 
+        Inches(0.55), Inches(0.0), Inches(0.11), Inches(1.39)
+    )
+    rect2.fill.solid()
+    rect2.fill.fore_color.rgb = COLOR_LIGHT_GREEN
+    rect2.line.fill.background()  # No border line
+
+    # 3. Decorative bottom line
+    # line: x: 0.67, y: 6.83, w: 12.0, h: 0.0
+    connector = slide.shapes.add_connector(
+        MSO_CONNECTOR.STRAIGHT,
+        Inches(0.67), Inches(6.83), Inches(12.67), Inches(6.83)
+    )
+    connector.line.color.rgb = COLOR_GRAY_LINE
+    connector.line.width = Pt(1)
+
+def _add_slide_title(slide, text: str):
+    """
+    Adds the Slide Title using Layout 7 Title configurations:
+    placeholder: x: 0.81, y: 0.29, w: 11.74, h: 0.38, align: left, valign: top
+    """
+    tx_box = slide.shapes.add_textbox(
+        Inches(0.81), Inches(0.29), Inches(11.74), Inches(0.38)
+    )
+    tf = tx_box.text_frame
+    tf.word_wrap = True
+    tf.margin_top = 0
+    tf.margin_bottom = 0
+    tf.margin_left = 0
+    tf.margin_right = 0
+    
+    p = tf.paragraphs[0]
+    p.text = text
+    p.font.name = FONT_MAJOR
+    p.font.size = Pt(20)
+    p.font.bold = True
+    p.font.color.rgb = COLOR_DARK_TEXT
+    p.alignment = PP_ALIGN.LEFT
+
+def _add_bullet_points(slide, bullets: List[str], top_inch=1.56, height_inch=5.14):
+    """
+    Adds bullet points body text block using Master 2 Body:
+    placeholder: x: 0.67, y: top, w: 12.0, h: height
+    """
+    tx_box = slide.shapes.add_textbox(
+        Inches(0.67), Inches(top_inch), Inches(12.0), Inches(height_inch)
+    )
+    tf = tx_box.text_frame
+    tf.word_wrap = True
+    tf.margin_top = 0
+    tf.margin_bottom = 0
+    tf.margin_left = 0
+    tf.margin_right = 0
+    
+    for i, b in enumerate(bullets):
+        p = tf.add_paragraph() if i > 0 else tf.paragraphs[0]
+        p.text = "•  " + b
+        p.font.name = FONT_MINOR
+        p.font.size = Pt(15)
+        p.font.color.rgb = COLOR_DARK_TEXT
+        p.space_after = Pt(8)
+        p.line_spacing = 1.2
+
+def _style_table_cell(cell, text: str, font_name=FONT_MINOR, font_size=11, bold=False, text_color=COLOR_DARK_TEXT, bg_color=None, align=PP_ALIGN.CENTER):
+    """Styles cell texts and background fills."""
+    cell.text = text
+    p = cell.text_frame.paragraphs[0]
+    p.alignment = align
+    p.font.name = font_name
+    p.font.size = Pt(font_size)
+    p.font.bold = bold
+    p.font.color.rgb = text_color
+    
+    if bg_color:
+        cell.fill.solid()
+        cell.fill.fore_color.rgb = bg_color
+
+def build_presentation(data: Dict, output_path: str):
+    """
+    Assembles a widescreen PowerPoint report from scraped financial data and AI models output.
+    """
+    prs = Presentation()
+    
+    # Strictly configure widescreen 16:9 aspect ratio
+    prs.slide_width = Inches(13.333)
+    prs.slide_height = Inches(7.5)
+    
+    blank_layout = prs.slide_layouts[6] # Blank slide template
+    
+    company_name = data.get("company", {}).get("name", "Unknown Company")
+    ticker = data.get("company", {}).get("ticker", "N/A")
+    industry = data.get("company", {}).get("industry", "N/A")
+    sector = data.get("company", {}).get("sector", "N/A")
+    date_str = data.get("company", {}).get("report_date", datetime.date.today().isoformat())
+    years = data.get("years", [])
+    
+    # ==========================================
+    # SLIDE 1: Title Slide
+    # ==========================================
+    slide_title = prs.slides.add_slide(blank_layout)
+    _apply_theme_decorations(slide_title, prs)
+    
+    # Title Text Frame
+    title_box = slide_title.shapes.add_textbox(
+        Inches(1.0), Inches(2.2), Inches(11.3), Inches(2.0)
+    )
+    tf = title_box.text_frame
+    tf.word_wrap = True
+    p1 = tf.paragraphs[0]
+    p1.text = company_name
+    p1.font.name = FONT_MAJOR
+    p1.font.size = Pt(40)
+    p1.font.bold = True
+    p1.font.color.rgb = COLOR_DARK_TEXT
+    
+    p2 = tf.add_paragraph()
+    p2.text = f"Financial Analysis & Investment Insights ({ticker})"
+    p2.font.name = FONT_MINOR
+    p2.font.size = Pt(22)
+    p2.font.color.rgb = COLOR_DARK_SLATE
+    p2.space_before = Pt(8)
+
+    # Subtitle Info (Date / Authors)
+    sub_box = slide_title.shapes.add_textbox(
+        Inches(1.0), Inches(5.0), Inches(11.3), Inches(1.2)
+    )
+    tf_sub = sub_box.text_frame
+    p_sub = tf_sub.paragraphs[0]
+    p_sub.text = f"Report Date: {date_str}  |  Sector: {sector}  |  Industry: {industry}"
+    p_sub.font.name = FONT_MINOR
+    p_sub.font.size = Pt(13)
+    p_sub.font.color.rgb = COLOR_DARK_SLATE
+    
+    p_sub2 = tf_sub.add_paragraph()
+    p_sub2.text = "Disclaimer: This report is for informational purposes only and does not constitute investment advice."
+    p_sub2.font.name = FONT_MINOR
+    p_sub2.font.size = Pt(11)
+    p_sub2.font.color.rgb = COLOR_DARK_SLATE
+    p_sub2.space_before = Pt(6)
+
+    # ==========================================
+    # DYNAMIC AI SLIDES (From ppt_json)
+    # ==========================================
+    import json
+    import re
+    
+    ppt_json_str = data.get("ppt_json", "")
+    ai_slides = []
+    if ppt_json_str:
+        match = re.search(r'\[.*\]', ppt_json_str, re.DOTALL)
+        if match:
+            try:
+                ai_slides = json.loads(match.group(0))
+            except Exception:
+                pass
+                
+    if ai_slides:
+        for slide_data in ai_slides:
+            title = slide_data.get("title", "Analysis Slide")
+            bullets = slide_data.get("bullets", [])
+            
+            if not bullets: continue
+            
+            s = prs.slides.add_slide(blank_layout)
+            _apply_theme_decorations(s, prs)
+            _add_slide_title(s, title)
+            
+            clean_bullets = [str(b).strip() for b in bullets if b]
+            _add_bullet_points(s, clean_bullets)
+    else:
+        # Fallback to Exec Summary if JSON parsing failed
+        exec_summary_text = data.get("executive_summary", "")
+        if exec_summary_text and len(exec_summary_text) > 50:
+            slide_exec = prs.slides.add_slide(blank_layout)
+            _apply_theme_decorations(slide_exec, prs)
+            _add_slide_title(slide_exec, "Executive Summary")
+            
+            paragraphs = [p.strip() for p in exec_summary_text.split('\n') if p.strip()]
+            _add_bullet_points(slide_exec, paragraphs[:5])
+
+    # ==========================================
+    # SLIDE 3: Key Financial Highlights Table
+    # ==========================================
+    if years:
+        slide_metrics = prs.slides.add_slide(blank_layout)
+        _apply_theme_decorations(slide_metrics, prs)
+        _add_slide_title(slide_metrics, "Key Financial Performance")
+        
+        # Build Grid Table
+        cols = len(years) + 1
+        rows = 6
+        table_shape = slide_metrics.shapes.add_table(
+            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.8)
+        )
+        table = table_shape.table
+        
+        # Column Headers
+        _style_table_cell(table.cell(0, 0), "Financial Metric", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
+        for idx, y in enumerate(years):
+            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
+            
+        metrics = [
+            ("Revenue", "revenue", "income_statement", 1.0),
+            ("Gross Profit", "gross_profit", "income_statement", 1.0),
+            ("Operating Income (EBIT)", "operating_income", "income_statement", 1.0),
+            ("Net Income", "net_income", "income_statement", 1.0),
+            ("Operating Cash Flow (OCF)", "cash_from_operations", "cash_flow", 1.0)
+        ]
+        
+        currency = data.get("company", {}).get("currency", "USD")
+        units = data.get("company", {}).get("units", "millions")
+        
+        for r_idx, (m_label, dict_key, sheet_name, scale) in enumerate(metrics):
+            curr_row = r_idx + 1
+            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
+            
+            # Label cell
+            _style_table_cell(table.cell(curr_row, 0), f"{m_label} ({currency} {units.capitalize()})", FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
+            
+            # Values cells
+            sheet_data = data.get(sheet_name, {})
+            val_list = sheet_data.get(dict_key, [])
+            for c_idx, y in enumerate(years):
+                val_str = "N/A"
+                if c_idx < len(val_list) and val_list[c_idx] is not None:
+                    val_str = f"{val_list[c_idx]:,.1f}"
+                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
+                
+        # Brief Narrative summary underneath table
+        rev_commentary = data.get("trend_analysis", {}).get("revenue_and_profitability", "")
+        if rev_commentary:
+            comment_box = slide_metrics.shapes.add_textbox(Inches(0.8), Inches(5.6), Inches(11.7), Inches(1.1))
+            tf_c = comment_box.text_frame
+            tf_c.word_wrap = True
+            p_c = tf_c.paragraphs[0]
+            p_c.text = "Key Takeaway: " + (rev_commentary[:260] + "..." if len(rev_commentary) > 260 else rev_commentary)
+            p_c.font.name = FONT_MINOR
+            p_c.font.size = Pt(12)
+            p_c.font.italic = True
+            p_c.font.color.rgb = COLOR_DARK_SLATE
+
+    # ==========================================
+    # SLIDE 4: Dupont ROE Decomposition
+    # ==========================================
+    dp_data = data.get("dupont", {})
+    if dp_data and "years" in dp_data:
+        slide_dp = prs.slides.add_slide(blank_layout)
+        _apply_theme_decorations(slide_dp, prs)
+        _add_slide_title(slide_dp, "DuPont ROE Analysis (Latest 3 Years)")
+        
+        dp_years = dp_data.get("years", [])
+        cols = len(dp_years) + 1
+        rows = 5
+        table_shape = slide_dp.shapes.add_table(
+            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
+        )
+        table = table_shape.table
+        
+        # Headers
+        _style_table_cell(table.cell(0, 0), "DuPont Component", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
+        for idx, y in enumerate(dp_years):
+            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
+            
+        components = [
+            ("Net Profit Margin (%)", "Net Margin"),
+            ("Asset Turnover (x)", "Asset Turnover"),
+            ("Equity Multiplier (x)", "Equity Multiplier"),
+            ("Return on Equity (ROE %)", "ROE")
+        ]
+        
+        for r_idx, (c_label, key) in enumerate(components):
+            curr_row = r_idx + 1
+            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
+            is_bold = (curr_row == 4)  # Bold ROE row
+            
+            _style_table_cell(table.cell(curr_row, 0), c_label, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
+            
+            vals_list = dp_data.get(key, [])
+            for c_idx, y in enumerate(dp_years):
+                val_str = "N/A"
+                if c_idx < len(vals_list) and vals_list[c_idx] is not None:
+                    val_val = vals_list[c_idx]
+                    if "%" in c_label or "ROE" in key:
+                        val_str = f"{val_val * 100:.1f}%" if val_val < 1.0 else f"{val_val:.1f}%"
+                    else:
+                        val_str = f"{val_val:.2f}x"
+                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color)
+                
+        # DuPont Commentary Text Box
+        commentary = data.get("trend_analysis", {}).get("balance_sheet_strength", "")
+        if commentary:
+            comment_box = slide_dp.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
+            tf_c = comment_box.text_frame
+            tf_c.word_wrap = True
+            p_c = tf_c.paragraphs[0]
+            p_c.text = "DuPont Drivers & Balance Sheet Strength: " + (commentary[:380] + "..." if len(commentary) > 380 else commentary)
+            p_c.font.name = FONT_MINOR
+            p_c.font.size = Pt(12)
+            p_c.font.color.rgb = COLOR_DARK_TEXT
+            p_c.line_spacing = 1.2
+
+    # ==========================================
+    # SLIDE 5: Competitor Benchmarking
+    # ==========================================
+    peers_list = data.get("peers", [])
+    if peers_list:
+        slide_peers = prs.slides.add_slide(blank_layout)
+        _apply_theme_decorations(slide_peers, prs)
+        _add_slide_title(slide_peers, "Competitor Benchmarking")
+        
+        # Build Grid Table
+        cols = 5
+        rows = min(len(peers_list) + 1, 6)
+        table_shape = slide_peers.shapes.add_table(
+            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
+        )
+        table = table_shape.table
+        
+        # Headers
+        headers = ["Company", "Revenue Growth", "Operating Margin", "P/E Ratio", "ROE"]
+        for c_idx, h in enumerate(headers):
+            _style_table_cell(table.cell(0, c_idx), h, FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT if c_idx == 0 else PP_ALIGN.CENTER)
+            
+        for r_idx in range(rows - 1):
+            peer = peers_list[r_idx]
+            curr_row = r_idx + 1
+            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
+            
+            # Format peer outputs
+            rev_gr = peer.get("revenue_growth", "N/A")
+            if isinstance(rev_gr, float): rev_gr = f"{rev_gr*100:.1f}%"
+            op_marg = peer.get("operating_margin", "N/A")
+            if isinstance(op_marg, float): op_marg = f"{op_marg*100:.1f}%"
+            pe_r = peer.get("pe_ratio", "N/A")
+            if isinstance(pe_r, float): pe_r = f"{pe_r:.1f}x"
+            roe_val = peer.get("roe", "N/A")
+            if isinstance(roe_val, float): roe_val = f"{roe_val*100:.1f}%"
+            
+            _style_table_cell(table.cell(curr_row, 0), peer.get("name", "N/A"), FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
+            _style_table_cell(table.cell(curr_row, 1), str(rev_gr), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
+            _style_table_cell(table.cell(curr_row, 2), str(op_marg), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
+            _style_table_cell(table.cell(curr_row, 3), str(pe_r), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
+            _style_table_cell(table.cell(curr_row, 4), str(roe_val), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
+            
+        # Peer comparison commentary
+        peer_comm = data.get("peer_comparison_commentary", "")
+        if peer_comm:
+            comment_box = slide_peers.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
+            tf_c = comment_box.text_frame
+            tf_c.word_wrap = True
+            p_c = tf_c.paragraphs[0]
+            p_c.text = "Benchmarking Insights: " + (peer_comm[:380] + "..." if len(peer_comm) > 380 else peer_comm)
+            p_c.font.name = FONT_MINOR
+            p_c.font.size = Pt(12)
+            p_c.font.color.rgb = COLOR_DARK_TEXT
+            p_c.line_spacing = 1.2
+
+    # ==========================================
+    # SLIDE 6: Financial Visualizations
+    # ==========================================
+    try:
+        from builders.chart_builder import generate_all_charts
+        charts = generate_all_charts(data)
+        
+        for chart_key, title in [
+            ("revenue_net_income", "Revenue & Net Income Trend"),
+            ("margins", "Profitability Margins"),
+            ("cash_flow", "Cash Flow & CAPEX Overview")
+        ]:
+            if charts.get(chart_key):
+                slide_chart = prs.slides.add_slide(blank_layout)
+                _apply_theme_decorations(slide_chart, prs)
+                _add_slide_title(slide_chart, title)
+                
+                # Add picture centrally
+                slide_chart.shapes.add_picture(
+                    charts[chart_key],
+                    Inches(1.5), Inches(1.5), width=Inches(10.0)
+                )
+    except Exception as e:
+        import sys
+        print(f"Warning: Could not generate PPTX charts: {e}", file=sys.stderr)
+
+    # Save Presentation
+    os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
+    prs.save(output_path)

pipeline/analyst.py

@@ -209,7 +209,7 @@ Guidelines:
 - Numbers should be expressed in appropriate units (Cr for large INR amounts, B/M for USD)
 """
 
-# ── Synthesis Prompt ──────────────────────────────────────────────────────────
+# ── Synthesis & PPT Prompts ──────────────────────────────────────────────────────────
 
 SYNTHESIS_PROMPT = """You are a master financial editor. You have been given {num_drafts} different AI-generated drafts for the '{section}' section of a financial report.
 Your job is to synthesize these drafts into a single, cohesive, authoritative, and brilliantly written section.
@@ -222,6 +222,16 @@ Guidelines:
 - Output ONLY the final synthesized text, with NO markdown formatting, NO introductory text, and NO commentary. Just the plain text paragraphs.
 """
 
+GENERATE_PPT_JSON = """You are a professional investment banker creating a pitch deck from financial data.
+Your task is to generate the structure and content for a PowerPoint presentation summarizing the company's financial health.
+Output a strict JSON array of slide objects. Each slide object MUST have:
+- "title": A short, punchy title for the slide
+- "bullets": An array of 3-5 strings, each containing a compelling insight, metric, or trend based on the data.
+
+Do not include any markdown fences, introduction, or conclusion. Just the raw JSON array.
+Focus on: Executive Summary, Revenue & Margin Trends, Cash Flow Health, Valuation, and Key Risks.
+"""
+
 # ── Section prompts ───────────────────────────────────────────────────────────
 
 SECTION_PROMPTS = {
@@ -659,14 +669,38 @@ def generate_narrative(
                     if log_fn: log_fn(f"[Warning] {name} thread failed: {e}")
 
         if len(drafts) == 0:
-            return f"[{section}: All AI models failed to generate a response]"
-        elif len(drafts) == 1:
+            return ""
+        if len(drafts) == 1:
             return list(drafts.values())[0]
-        else:
-            return _synthesize_drafts(section, drafts)
+            
+        return _synthesize_drafts(section, drafts)
+        
+    def _generate_ppt_json() -> str:
+        # Pick the smartest model available for structured JSON generation
+        synthesizer = None
+        if use_openai:  synthesizer = ("ChatGPT", _openai_generate)
+        elif use_claude: synthesizer = ("Claude", _claude_generate)
+        elif use_gemini: synthesizer = ("Gemini", _gemini_generate)
+        elif use_nvidia: synthesizer = ("NVIDIA", _nvidia_generate)
+        elif use_groq:   synthesizer = ("Groq", _groq_generate)
+        
+        if not synthesizer:
+            return ""
+            
+        name, fn = synthesizer
+        log(f"\n[PPT] Generating PowerPoint Structure using {name} ...")
+        
+        original_prompt = SECTION_PROMPTS.get("ppt_json", "")
+        SECTION_PROMPTS["ppt_json"] = GENERATE_PPT_JSON
+        try:
+            res = fn(context, "ppt_json")
+        finally:
+            if "ppt_json" in SECTION_PROMPTS:
+                del SECTION_PROMPTS["ppt_json"]
+                
+        return res if res else ""
 
-    # Generate all sections
-    log("  Generating executive summary …")
+    log("  > Executing section: Executive Summary")
     exec_summary = gen("executive_summary")
 
     log("  Generating company profile …")
@@ -708,6 +742,8 @@ def generate_narrative(
     log("  Generating limitations …")
     lim_raw = gen("limitations")
     limitations = _parse_bullets(lim_raw)
+    
+    ppt_json = _generate_ppt_json()
 
     log("  ✓ AI narrative generation complete")
 
@@ -729,6 +765,7 @@ def generate_narrative(
         "things_to_watch":             things_to_watch,
         "limitations_and_caveats":     limitations,
         "models_used":                 models,
+        "ppt_json":                    ppt_json,
     }
 
 
@@ -747,4 +784,5 @@ def _empty_narrative() -> Dict:
         "things_to_watch":           [],
         "limitations_and_caveats":   [],
         "models_used":               [],
+        "ppt_json":                  "",
     }

pipeline/fetcher.py

@@ -74,85 +74,79 @@ def _fetch_yfinance(ticker: str, years: int, log_fn=None) -> Optional[Dict]:
                     for c in use_cols_asc:   # iterate oldest→newest
                         if c in df.columns:
                             v = df.at[k, c]
-                            vals.append(None if (v != v or v is None) else float(v))
-                        else:
-                            vals.append(None)
-                    return vals
-            return [None] * n
-
-        currency = info.get("currency", "INR")
-
-        # Determine display scale
-        # INR: raw values are in rupees → divide by 1e7 to get Crores
-        # USD/others: raw values in dollars → divide by 1e6 for Millions
         if currency == "INR":
-            scale = 1e7          # rupees → crores
+            scale = 1e7
             units = "Crores"
             units_label = "INR Crores (₹ Cr)"
         else:
-            scale = 1e6          # dollars → millions
+            scale = 1e6
             units = "Millions"
             units_label = f"{currency} Millions"
 
+        def col(df, *keys):
+            for k in keys:
+                if k in df.columns:
+                    return df[k].tolist()
+            return [None] * len(df)
+
         def sc(lst):
-            """Scale a list of raw values."""
-            return [round(v / scale, 2) if v is not None else None for v in lst]
+            return [round(v / scale, 2) if v is not None and not pd.isna(v) else None for v in lst]
 
         income = {
-            "revenue":            sc(col(fin, "Total Revenue", "Operating Revenue")),
-            "cost_of_revenue":    sc(col(fin, "Cost Of Revenue", "Reconciled Cost Of Revenue")),
-            "gross_profit":       sc(col(fin, "Gross Profit")),
-            "operating_expenses": sc(col(fin, "Operating Expense")),
-            "operating_income":   sc(col(fin, "Operating Income", "EBIT")),
-            "ebitda":             sc(col(fin, "EBITDA", "Normalized EBITDA")),
-            "depreciation_amort": sc(col(fin, "Reconciled Depreciation", "Depreciation And Amortization")),
-            "interest_expense":   sc(col(fin, "Interest Expense Non Operating", "Interest Expense")),
-            "pretax_income":      sc(col(fin, "Pretax Income")),
-            "tax_expense":        sc(col(fin, "Tax Provision")),
-            "net_income":         sc(col(fin, "Net Income", "Net Income Common Stockholders")),
-            "diluted_eps":        col(fin, "Diluted EPS"),      # EPS not scaled
-            "diluted_shares":     col(fin, "Diluted Average Shares"),  # not scaled
+            "revenue":            sc(col(inc, "TotalRevenue", "OperatingRevenue")),
+            "cost_of_revenue":    sc(col(inc, "CostOfRevenue", "ReconciledCostOfRevenue")),
+            "gross_profit":       sc(col(inc, "GrossProfit")),
+            "operating_expenses": sc(col(inc, "OperatingExpense")),
+            "operating_income":   sc(col(inc, "OperatingIncome", "EBIT")),
+            "ebitda":             sc(col(inc, "EBITDA", "NormalizedEBITDA")),
+            "depreciation_amort": sc(col(inc, "ReconciledDepreciation", "DepreciationAndAmortization")),
+            "interest_expense":   sc(col(inc, "InterestExpenseNonOperating", "InterestExpense")),
+            "pretax_income":      sc(col(inc, "PretaxIncome")),
+            "tax_expense":        sc(col(inc, "TaxProvision")),
+            "net_income":         sc(col(inc, "NetIncome", "NetIncomeCommonStockholders")),
+            "diluted_eps":        col(inc, "DilutedEPS"),
+            "diluted_shares":     col(inc, "DilutedAverageShares"),
         }
 
         balance = {
-            "cash_and_equivalents":       sc(col(bs, "Cash And Cash Equivalents", "Cash Financial")),
-            "short_term_investments":     sc(col(bs, "Other Short Term Investments")),
-            "receivables":                sc(col(bs, "Accounts Receivable", "Other Receivables")),
+            "cash_and_equivalents":       sc(col(bs, "CashAndCashEquivalents", "CashFinancial")),
+            "short_term_investments":     sc(col(bs, "OtherShortTermInvestments")),
+            "receivables":                sc(col(bs, "AccountsReceivable", "Receivables")),
             "inventory":                  sc(col(bs, "Inventory")),
-            "other_current_assets":       sc(col(bs, "Other Current Assets")),
-            "total_current_assets":       sc(col(bs, "Current Assets")),
-            "ppe_net":                    sc(col(bs, "Net PPE")),
+            "other_current_assets":       sc(col(bs, "OtherCurrentAssets")),
+            "total_current_assets":       sc(col(bs, "CurrentAssets")),
+            "ppe_net":                    sc(col(bs, "NetPPE")),
             "goodwill":                   sc(col(bs, "Goodwill")),
-            "intangibles":                sc(col(bs, "Other Intangible Assets")),
-            "other_long_term_assets":     sc(col(bs, "Other Non Current Assets")),
-            "total_assets":               sc(col(bs, "Total Assets")),
-            "accounts_payable":           sc(col(bs, "Accounts Payable", "Payables")),
-            "short_term_debt":            sc(col(bs, "Current Debt", "Current Debt And Capital Lease Obligation")),
-            "other_current_liabilities":  sc(col(bs, "Other Current Liabilities")),
-            "total_current_liabilities":  sc(col(bs, "Current Liabilities")),
-            "long_term_debt":             sc(col(bs, "Long Term Debt", "Long Term Debt And Capital Lease Obligation")),
-            "other_long_term_liabilities":sc(col(bs, "Other Non Current Liabilities")),
-            "total_liabilities":          sc(col(bs, "Total Liabilities Net Minority Interest")),
-            "total_equity":               sc(col(bs, "Stockholders Equity", "Common Stock Equity")),
-            "total_liab_and_equity":      sc(col(bs, "Total Assets")),
+            "intangibles":                sc(col(bs, "OtherIntangibleAssets")),
+            "other_long_term_assets":     sc(col(bs, "OtherNonCurrentAssets")),
+            "total_assets":               sc(col(bs, "TotalAssets")),
+            "accounts_payable":           sc(col(bs, "AccountsPayable", "Payables")),
+            "short_term_debt":            sc(col(bs, "CurrentDebt", "CurrentDebtAndCapitalLeaseObligation")),
+            "other_current_liabilities":  sc(col(bs, "OtherCurrentLiabilities")),
+            "total_current_liabilities":  sc(col(bs, "CurrentLiabilities")),
+            "long_term_debt":             sc(col(bs, "LongTermDebt", "LongTermDebtAndCapitalLeaseObligation")),
+            "other_long_term_liabilities":sc(col(bs, "OtherNonCurrentLiabilities")),
+            "total_liabilities":          sc(col(bs, "TotalLiabilitiesNetMinorityInterest", "TotalLiabilities")),
+            "total_equity":               sc(col(bs, "StockholdersEquity", "CommonStockEquity")),
+            "total_liab_and_equity":      sc(col(bs, "TotalAssets")),
         }
 
         cashflow = {
-            "net_income":              sc(col(cf, "Net Income From Continuing Operations")),
-            "depreciation_amort":      sc(col(cf, "Depreciation And Amortization", "Depreciation")),
-            "stock_based_comp":        [None] * n,
-            "working_capital_changes": sc(col(cf, "Change In Working Capital")),
-            "other_operating":         sc(col(cf, "Other Non Cash Items")),
-            "cash_from_operations":    sc(col(cf, "Operating Cash Flow")),
-            "capex":                   sc(col(cf, "Capital Expenditure", "Purchase Of PPE")),
-            "acquisitions":            [None] * n,
-            "cash_from_investing":     sc(col(cf, "Investing Cash Flow")),
-            "debt_issuance_repayment": sc(col(cf, "Net Long Term Debt Issuance")),
-            "stock_buybacks":          sc(col(cf, "Net Common Stock Issuance")),
-            "dividends_paid":          sc(col(cf, "Cash Dividends Paid")),
-            "cash_from_financing":     sc(col(cf, "Financing Cash Flow")),
-            "net_change_in_cash":      sc(col(cf, "Changes In Cash")),
-            "free_cash_flow":          sc(col(cf, "Free Cash Flow")),
+            "net_income":              sc(col(cf, "NetIncomeFromContinuingOperations", "NetIncome")),
+            "depreciation_amort":      sc(col(cf, "DepreciationAndAmortization", "Depreciation")),
+            "stock_based_comp":        sc(col(cf, "StockBasedCompensation")),
+            "working_capital_changes": sc(col(cf, "ChangeInWorkingCapital")),
+            "other_operating":         [None] * n,
+            "cash_from_operations":    sc(col(cf, "OperatingCashFlow", "CashFlowFromContinuingOperatingActivities")),
+            "capex":                   sc(col(cf, "CapitalExpenditure", "PurchaseOfPPE")),
+            "acquisitions":            sc(col(cf, "PurchaseOfBusiness")),
+            "cash_from_investing":     sc(col(cf, "InvestingCashFlow", "CashFlowFromContinuingInvestingActivities")),
+            "debt_issuance_repayment": sc(col(cf, "NetLongTermDebtIssuance", "NetIssuancePaymentsOfDebt")),
+            "stock_buybacks":          sc(col(cf, "NetCommonStockIssuance", "RepurchaseOfCapitalStock")),
+            "dividends_paid":          sc(col(cf, "CashDividendsPaid")),
+            "cash_from_financing":     sc(col(cf, "FinancingCashFlow", "CashFlowFromContinuingFinancingActivities")),
+            "net_change_in_cash":      sc(col(cf, "ChangesInCash", "ChangeInCashSupplementalAsReported")),
+            "free_cash_flow":          sc(col(cf, "FreeCashFlow")),
         }
 
         # Compute FCF if missing
@@ -162,8 +156,22 @@ def _fetch_yfinance(ticker: str, years: int, log_fn=None) -> Optional[Dict]:
                 cap = cashflow["capex"][i]
                 if cfo is not None and cap is not None:
                     cashflow["free_cash_flow"][i] = round(cfo + cap, 2)
+                    
+        # Extract valuation snapshot and analyst targets
+        val_snap = {}
+        fd = t.financial_data
+        if fd and ticker in fd and isinstance(fd[ticker], dict):
+            val_snap["target_mean_price"] = fd[ticker].get("targetMeanPrice")
+            val_snap["target_high_price"] = fd[ticker].get("targetHighPrice")
+            val_snap["target_low_price"] = fd[ticker].get("targetLowPrice")
+            val_snap["wacc_estimate"] = 0.10 # default fallback
+        
+        info = t.summary_detail
+        if info and ticker in info and isinstance(info[ticker], dict):
+            val_snap["pe_ttm"] = info[ticker].get("trailingPE")
+            val_snap["dividend_yield"] = info[ticker].get("dividendYield")
 
-        log(f"  ✓ yfinance data ready ({n} years, {currency}, in {units})")
+        log(f"  ✓ yahooquery data ready ({n} years, {currency}, in {units})")
 
         return {
             "years": year_labels,
@@ -174,20 +182,12 @@ def _fetch_yfinance(ticker: str, years: int, log_fn=None) -> Optional[Dict]:
             "units":            units,
             "units_label":      units_label,
             "scale":            scale,
-            "source":           "Yahoo Finance (yfinance)",
-            "valuation_snapshot": {
-                "pe_ttm":         _s(info.get("trailingPE")),
-                "pb":             _s(info.get("priceToBook")),
-                "ps":             _s(info.get("priceToSalesTrailing12Months")),
-                "ev_ebitda":      _s(info.get("enterpriseToEbitda")),
-                "ev_revenue":     _s(info.get("enterpriseToRevenue")),
-                "fcf_yield":      None,
-                "dividend_yield": _s(info.get("dividendYield")),
-            },
+            "source":           "Yahoo Finance (yahooquery)",
+            "valuation_snapshot": val_snap,
         }
     except Exception as e:
         import traceback
-        if log_fn: log_fn(f"  ✗ yfinance error: {e}\n{traceback.format_exc()}")
+        if log_fn: log_fn(f"  ✗ yahooquery error: {e}\n{traceback.format_exc()}")
         return None
 
 
@@ -712,26 +712,26 @@ def fetch_all(meta: CompanyMeta, years: int = DEFAULT_YEARS,
             
         # Fallback to yfinance if screener fails or yields nothing
         if not result or not result.get("years"):
-            log("  → screener.in failed. Falling back to yfinance ...")
-            result = _fetch_yfinance(ticker, years, log_fn)
+            log("  → screener.in failed. Falling back to yahooquery ...")
+            result = _fetch_yahooquery(ticker, years, log_fn)
             if result and len(result.get("years", [])) < years:
-                warnings.append(f"yfinance only provides {len(result['years'])} years of historical data for free.")
+                warnings.append(f"yahooquery only provides {len(result['years'])} years of historical data.")
 
     # 2. Global/US Stocks
     else:
-        # If requesting > 4 years, try stockanalysis.com first because yfinance limits to 4 years
+        # If requesting > 4 years, try stockanalysis.com first because yahooquery limits to 4 years
         if years > 4:
             log("  → Horizon > 4 years requested. Prioritizing stockanalysis.com for global stock ...")
             result = _scrape_stockanalysis(ticker, years, log_fn)
             if result:
                 warnings.append("Data sourced from stockanalysis.com. Verify against company filings.")
         
-        # Fallback to yfinance
+        # Fallback to yahooquery
         if not result or not result.get("years"):
-            log("  → Trying yfinance ...")
-            result = _fetch_yfinance(ticker, years, log_fn)
+            log("  → Trying yahooquery ...")
+            result = _fetch_yahooquery(ticker, years, log_fn)
             if result and len(result.get("years", [])) < years:
-                warnings.append(f"yfinance only provides {len(result['years'])} years of historical data for free.")
+                warnings.append(f"yahooquery only provides {len(result['years'])} years of historical data.")
                 
         # Fallback to FMP
         if (not result or not result.get("years")) and FMP_API_KEY:

web_app/app.py

@@ -215,7 +215,7 @@ with st.sidebar.expander("ChatGPT (OpenAI) — paid", expanded=False):
 
 st.sidebar.markdown("---")
 st.sidebar.markdown("<h3 style='color:#34D399;'>👤 User Profile</h3>", unsafe_allow_html=True)
-username = st.sidebar.text_input("Username / Email", value="guest@local", help="Logged in the audit trail")
+username = st.sidebar.text_input("Username / Email", value="", placeholder="name@company.com", help="Mandatory for audit trail")
 
 # ── Main Dashboard Layout ──────────────────────────────────────────────
 st.markdown("<h1 class='dashboard-title'>📈 Financial Statement Analyzer</h1>", unsafe_allow_html=True)
@@ -345,7 +345,9 @@ with col2:
 
 # ── Analysis Runner ───────────────────────────────────────────────────
 if start_btn:
-    if not ticker_input:
+    if not username or "@" not in username:
+        st.error("Please enter a valid email address in the User Profile section before analyzing.")
+    elif not ticker_input:
         st.error("Please enter a stock ticker or company name.")
     elif not (chk_excel or chk_word or chk_pptx):
         st.error("Please select at least one download format checkbox.")

web_app/requirements.txt

@@ -16,4 +16,5 @@ Pillow
 yfinance
 matplotlib
 seaborn
-huggingface_hub
+huggingface_hub
+yahooquery