Update app.py

app.py

@@ -1,18 +1,15 @@
 """
-Governance-GPT Quiz  ─  LLM-powered bucket report
+Governance-GPT Quiz – ASCII-safe, LLM-powered PDF
 Author: Rishabh Sharma · 2025-09-14
-One-file Gradio Space → 15-Q Likert survey → bucket scores → FLAN-T5 summary → PDF
 """
 
-import datetime, tempfile, warnings
+import datetime, tempfile, re, warnings
 import gradio as gr
 import pandas as pd
-from fpdf import FPDF                 # pure-Python PDF (core Helvetica font)
-from transformers import pipeline     # Hugging Face inference
+from fpdf import FPDF
+from transformers import pipeline
 
-# ───────────────────────────────────────────────────────────
-# 1.  Load a lightweight model once (≈ 80 M params, CPU-friendly)
-# ───────────────────────────────────────────────────────────
+# ── Load a lightweight CPU model ───────────────────────────────────
 warnings.filterwarnings("ignore", category=UserWarning)
 summariser = pipeline(
     task="text2text-generation",
@@ -21,9 +18,7 @@ summariser = pipeline(
     max_new_tokens=150,
 )
 
-# ───────────────────────────────────────────────────────────
-# 2.  Question bank & buckets
-# ───────────────────────────────────────────────────────────
+# ── Questions & buckets ────────────────────────────────────────────
 QUESTIONS = [
     "Governance framework is documented and communicated across the organisation.",
     "Roles & responsibilities for AI oversight are clearly assigned.",
@@ -62,24 +57,19 @@ TIERS = {
     "Optimized":  (4.51, 5.00),
 }
 
-# ───────────────────────────────────────────────────────────
-# 3.  Helper functions
-# ───────────────────────────────────────────────────────────
-def score_to_tier(avg: float) -> str:
-    for tier, (low, high) in TIERS.items():
-        if low <= avg <= high:
+# ── Helpers ─────────────────────────────────────────────────────────
+def score_to_tier(avg):
+    for tier, (lo, hi) in TIERS.items():
+        if lo <= avg <= hi:
             return tier
     return "Unclassified"
 
 def latin1(txt: str) -> str:
-    """Force text into Latin-1 for the core fonts used by FPDF."""
+    """Replace common Unicode chars with ASCII equivalents, then enforce Latin-1."""
+    txt = txt.replace("–", "-").replace("—", "-").replace("•", "-")
     return txt.encode("latin-1", "replace").decode("latin-1")
 
 def llm_remediation(product: str, bucket_avgs: dict, overall_tier: str) -> str:
-    """
-    Ask FLAN-T5-small to write a short markdown summary.
-    Uses only ASCII bullets ('-') so the PDF core font can render them.
-    """
     bucket_lines = "\n".join(f"- {b}: {v:.2f}" for b, v in bucket_avgs.items())
     prompt = (
         "You are an AI governance consultant.\n"
@@ -87,41 +77,42 @@ def llm_remediation(product: str, bucket_avgs: dict, overall_tier: str) -> str:
         f"Overall tier: {overall_tier}\n"
         "Bucket scores (1-5):\n"
         f"{bucket_lines}\n\n"
-        "Write a concise markdown summary (≤120 words) with:\n"
+        "Write a concise markdown summary (<=120 words) with:\n"
         "- One overall assessment sentence.\n"
         "- 3-5 bullet remediation actions referencing bucket names.\n"
         "Return only the summary."
     )
 
-    # Generate
-    raw = summariser(prompt)[0]["generated_text"].strip()
+    raw = summariser(prompt)[0]["generated_text"]
 
-    # Some T5 models echo a slice of the prompt. Remove if present.
-    if raw.startswith(prompt[:50]):
-        raw = raw[len(prompt):].strip()
+    # ── Strip any prompt echo or leftover instruction lines ──
+    lines = [
+        ln for ln in raw.splitlines()
+        if not re.search(r"bullet remediation|overall assessment|Write a concise", ln, re.I)
+    ]
+    cleaned = "\n".join(lines).strip()
 
-    # Replace any unicode bullets with ASCII "- "
-    summary = raw.replace("•", "- ")
-    return summary if summary else "Summary unavailable."
+    # Replace bullets with ASCII dash (in case model outputs •)
+    cleaned = cleaned.replace("•", "- ")
 
-def build_pdf(product: str, bucket_df: pd.DataFrame,
-              overall_avg: float, overall_tier: str,
-              file_path: str, summary_text: str):
+    return cleaned or "LLM summary unavailable."
+
+def build_pdf(product, bucket_df, overall_avg, overall_tier, pdf_path, summary):
     pdf = FPDF()
     pdf.set_auto_page_break(auto=True, margin=15)
     pdf.add_page()
 
     pdf.set_font("Helvetica", "B", 16)
-    pdf.cell(0, 10, latin1(f"AI Governance Maturity Report – {product}"), ln=1, align="C")
+    pdf.cell(0, 10, latin1(f"AI Governance Maturity Report - {product}"), ln=1, align="C")
 
     pdf.set_font("Helvetica", "", 12)
-    pdf.cell(0, 8, f"Generated on {datetime.date.today().isoformat()}", ln=1, align="C")
+    pdf.cell(0, 8, datetime.date.today().isoformat(), ln=1, align="C")
     pdf.ln(4)
 
     pdf.set_font("Helvetica", "B", 12)
-    pdf.cell(0, 8, latin1(f"Overall Score: {overall_avg:.2f}  |  Tier: {overall_tier}"), ln=1)
+    pdf.cell(0, 8, latin1(f"Overall Score: {overall_avg:.2f} | Tier: {overall_tier}"), ln=1)
     pdf.set_font("Helvetica", "", 11)
-    pdf.multi_cell(0, 6, latin1(summary_text))
+    pdf.multi_cell(0, 6, latin1(summary))
     pdf.ln(4)
 
     pdf.set_font("Helvetica", "B", 11)
@@ -139,19 +130,16 @@ def build_pdf(product: str, bucket_df: pd.DataFrame,
     pdf.cell(35, 8, f"{overall_avg:.2f}", 1)
     pdf.cell(35, 8, overall_tier, 1, ln=1)
 
-    pdf.output(file_path)
+    pdf.output(pdf_path)
 
-# ───────────────────────────────────────────────────────────
-# 4.  Gradio callback
-# ───────────────────────────────────────────────────────────
+# ── Gradio callback ────────────────────────────────────────────────
 def generate_report(product_name, *scores):
     product = product_name.strip() or "your product"
     scores = list(scores)
 
-    # Bucket averages
     bucket_avgs = {
-        bucket: sum(scores[i] for i in idxs) / len(idxs)
-        for bucket, idxs in BUCKETS.items()
+        b: sum(scores[i] for i in idxs) / len(idxs)
+        for b, idxs in BUCKETS.items()
     }
     overall_avg = sum(scores) / len(scores)
     overall_tier = score_to_tier(overall_avg)
@@ -169,24 +157,22 @@ def generate_report(product_name, *scores):
 
     return summary_md, tmp_pdf.name
 
-# ───────────────────────────────────────────────────────────
-# 5.  Gradio UI
-# ───────────────────────────────────────────────────────────
+# ── UI ────────────────────────────────────────────────────────────
 with gr.Blocks(title="Governance-GPT Quiz") as demo:
     gr.Markdown(
         """
 # Governance-GPT Quiz  
 Enter your **product / system name**, rate each statement from **1 (Strongly Disagree)** to **5 (Strongly Agree)**,  
-and receive an LLM-generated remediation plan plus a PDF bucket report.
+then download an LLM-generated remediation plan and bucket-level PDF.
         """
     )
 
-    product_inp = gr.Textbox(label="Product / System Name", placeholder="e.g. AcmeAI Recommendation Engine")
-    sliders = [gr.Slider(1, 5, value=3, step=1, label=q) for q in QUESTIONS]
+    product_inp = gr.Textbox(label="Product / System Name", placeholder="e.g. AcmeAI Recommender")
+    sliders = [gr.Slider(1, 5, 3, 1, label=q) for q in QUESTIONS]
 
     btn = gr.Button("Generate PDF Report")
     summary_out = gr.Markdown()
-    pdf_out = gr.File(label="⬇️ Download your PDF")
+    pdf_out = gr.File(label="⬇️ Download PDF")
 
     btn.click(fn=generate_report,
               inputs=[product_inp] + sliders,