Create high_risk_ai_register.py

tools/high_risk_ai_register.py

@@ -0,0 +1,151 @@
+#!/usr/bin/env python
+# coding=utf-8
+import csv
+import datetime
+import os
+import re
+from fpdf import FPDF
+import gradio as gr
+from langdetect import detect
+
+# === PDF Export Function ===
+def export_text_to_pdf(text, output_path=None, language="en"):
+    if output_path is None:
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        output_path = f"high_risk_ai_summary_{timestamp}.pdf"
+
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_auto_page_break(auto=True, margin=15)
+
+    # Title
+    pdf.set_font("Arial", 'B', 16)
+    pdf.set_text_color(0, 51, 102)
+    title = "High-Risk AI System Documentation" if language == "en" else "Documentation des Systèmes IA à Haut Risque"
+    pdf.cell(0, 15, title, ln=True, align='C')
+    pdf.ln(10)
+
+    # Subtitle
+    pdf.set_font("Arial", 'I', 12)
+    pdf.set_text_color(90, 90, 90)
+    subtitle = f"Generated on {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"
+    pdf.cell(0, 10, subtitle, ln=True, align='C')
+    pdf.ln(5)
+
+    # Content formatting
+    pdf.set_font("Arial", '', 12)
+    pdf.set_text_color(0, 0, 0)
+
+    for line in text.strip().split('\n'):
+        line = line.strip()
+        if line.startswith("## "):
+            section_title = line.replace("## ", "").strip()
+            pdf.set_font("Arial", 'B', 13)
+            pdf.set_text_color(30, 30, 120)
+            pdf.ln(8)
+            pdf.cell(0, 10, section_title, ln=True)
+            pdf.set_font("Arial", '', 12)
+            pdf.set_text_color(0, 0, 0)
+        elif line.startswith("- **"):
+            match = re.match(r"- \*\*(.+?)\*\*: (.+)", line)
+            if match:
+                label, answer = match.groups()
+                pdf.set_font("Arial", 'B', 12)
+                pdf.cell(0, 10, f"{label}:", ln=True)
+                pdf.set_font("Arial", '', 12)
+                pdf.multi_cell(0, 10, f"{answer}")
+        elif line == "---":
+            pdf.line(10, pdf.get_y(), 200, pdf.get_y())
+            pdf.ln(5)
+        else:
+            pdf.multi_cell(0, 10, line)
+    pdf.output(output_path)
+    return output_path
+
+# === Questions for AI System Documentation ===
+QUESTIONS = [
+    ("system_name", "What is the name of your AI system?"),
+    ("system_purpose", "What is its intended purpose?"),
+    ("category", "Which Annex III category does it fall under?"),
+    ("developer", "Who developed it?"),
+    ("users", "Who will use it?"),
+    ("input_types", "What types of input data does it use?"),
+    ("output", "What actions does it perform?"),
+    ("dependencies", "List any critical dependencies (e.g., APIs, models)."),
+    ("context", "What is the intended deployment environment?"),
+    ("justification", "Why is it high-risk under the AI Act?"),
+]
+
+# === Conversation Logic ===
+def step_by_step(user_input, state):
+    if state is None:
+        state = {"step": 0, "answers": {}}
+
+    step = state["step"]
+    answers = state["answers"]
+
+    if step > 0:
+        key, _ = QUESTIONS[step - 1]
+        answers[key] = user_input
+
+    if step < len(QUESTIONS):
+        next_q = QUESTIONS[step][1]
+        state["step"] += 1
+        return next_q, state, None
+
+    # === Format document ===
+    content = f"""
+# High-Risk AI System Summary
+## General Info
+- **System Name**: {answers.get('system_name', '')}
+- **Purpose**: {answers.get('system_purpose', '')}
+- **Annex III Category**: {answers.get('category', '')}
+- **Developer**: {answers.get('developer', '')}
+- **Intended Users**: {answers.get('users', '')}
+- **Deployment Context**: {answers.get('context', '')}
+
+## Technical Info
+- **Input Types**: {answers.get('input_types', '')}
+- **System Output**: {answers.get('output', '')}
+- **Dependencies**: {answers.get('dependencies', '')}
+
+## Risk Classification
+- **Justification for High-Risk**: {answers.get('justification', '')}
+---
+Generated by AI Act Assistant.
+"""
+
+    lang = detect(content)
+    pdf_path = export_text_to_pdf(content, language=lang)
+
+    return f"✅ All data collected!\n📝 Your summary is ready. Click below to download your PDF.", {"done": True}, pdf_path
+
+# === Gradio UI ===
+def launch_ui():
+    with gr.Blocks(title="High-Risk AI Summary Tool") as demo:
+        chatbot = gr.Chatbot(label="🛡️ High-Risk AI Summary Assistant")
+        user_input = gr.Textbox(placeholder="Your answer...", label="Answer")
+        state = gr.State()
+        file_output = gr.File(label="Download PDF", visible=True)
+        reset_btn = gr.Button("🔁 Start Over")
+
+        first_q = QUESTIONS[0][1]
+        chatbot.value = [gr.ChatMessage(role="assistant", content=first_q)]
+
+        def run_chat(msg, state):
+            reply, state, pdf = step_by_step(msg, state)
+            messages = [gr.ChatMessage(role="user", content=msg)]
+            if reply:
+                messages.append(gr.ChatMessage(role="assistant", content=reply))
+            return messages, state, pdf
+
+        def reset_all():
+            return [gr.ChatMessage(role="assistant", content=QUESTIONS[0][1])], {"step": 0, "answers": {}}, None
+
+        user_input.submit(run_chat, [user_input, state], [chatbot, state, file_output])
+        reset_btn.click(reset_all, outputs=[chatbot, state, file_output])
+
+    demo.launch()
+
+if __name__ == "__main__":
+    launch_ui()