export_prompts.py

"""
Script to export all prompts used in the HBV AI Assistant project to a Word document.
Includes: Agent System Prompt, Validation Prompt, and HBV Assessment Prompt.
"""
from docx import Document
from docx.shared import Pt, RGBColor, Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
import sys
import os
import re

# Add the project root to the path
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))


def extract_system_message_from_agent():
    """Extract SYSTEM_MESSAGE from core/agent.py without importing it."""
    agent_path = os.path.join(os.path.dirname(__file__), 'core', 'agent.py')
    with open(agent_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Extract SYSTEM_MESSAGE using regex
    match = re.search(r'SYSTEM_MESSAGE = """(.*?)"""', content, re.DOTALL)
    if match:
        return match.group(1).strip()
    else:
        raise ValueError("Could not extract SYSTEM_MESSAGE from core/agent.py")


def extract_validation_prompt():
    """Extract validation prompt from core/validation.py without importing it."""
    validation_path = os.path.join(os.path.dirname(__file__), 'core', 'validation.py')
    with open(validation_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Find the _create_validation_system_prompt method and extract the return string
    match = re.search(r'def _create_validation_system_prompt\(self\) -> str:.*?return """(.*?)"""', content, re.DOTALL)
    if match:
        return match.group(1).strip()
    else:
        raise ValueError("Could not extract validation prompt from core/validation.py")


def extract_hbv_assessment_prompt():
    """Extract HBV assessment prompt from core/hbv_assessment.py without importing it."""
    assessment_path = os.path.join(os.path.dirname(__file__), 'core', 'hbv_assessment.py')
    with open(assessment_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Find the analysis_prompt in assess_hbv_eligibility function
    match = re.search(r'analysis_prompt = f"""(.*?)"""', content, re.DOTALL)
    if match:
        # Extract the prompt template (without f-string variables)
        prompt_template = match.group(1).strip()
        return prompt_template
    else:
        raise ValueError("Could not extract HBV assessment prompt from core/hbv_assessment.py")


def create_prompts_document():
    """Create a Word document with both prompts."""
    
    # Create a new Document
    doc = Document()
    
    # Add title
    title = doc.add_heading('HBV AI Assistant - System Prompts', 0)
    title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    
    # Add metadata
    metadata = doc.add_paragraph()
    metadata.add_run('Project: HBV Clinical Decision Support System\n').bold = True
    metadata.add_run('Generated: October 30, 2025\n')
    metadata.add_run('Description: This document contains all system prompts used by the HBV AI Assistant, including the main agent prompt, validation prompt, and HBV assessment prompt.')
    
    doc.add_page_break()
    
    # ==================== HBV ASSESSMENT PROMPT ====================
    doc.add_heading('1. HBV Assessment System Prompt', 1)
    
    # Add description
    desc3 = doc.add_paragraph()
    desc3.add_run('Purpose: ').bold = True
    desc3.add_run('Evaluates patient eligibility for HBV treatment based on SASLT 2021 guidelines\n')
    desc3.add_run('Location: ').bold = True
    desc3.add_run('core/hbv_assessment.py\n')
    desc3.add_run('Model: ').bold = True
    desc3.add_run('GPT-4 (configurable)\n')
    desc3.add_run('Function: ').bold = True
    desc3.add_run('assess_hbv_eligibility()')
    
    doc.add_paragraph()  # Spacing
    
    # Add assessment overview
    doc.add_heading('Assessment Process:', 2)
    process = doc.add_paragraph()
    process.add_run('The HBV assessment prompt analyzes patient data against SASLT 2021 guidelines:\n')
    process_list = [
        'Evaluates patient parameters (HBV DNA, ALT, fibrosis stage, etc.)',
        'Compares against treatment eligibility criteria from SASLT 2021',
        'Determines eligibility status (Eligible/Not Eligible/Borderline)',
        'Recommends first-line antiviral agents (ETV, TDF, TAF) if eligible',
        'Provides comprehensive assessment with inline citations',
        'Includes special considerations (pregnancy, immunosuppression, coinfections)'
    ]
    for item in process_list:
        doc.add_paragraph(item, style='List Bullet')
    
    doc.add_paragraph()  # Spacing
    
    # Add the actual HBV assessment prompt
    doc.add_heading('Prompt Content:', 2)
    hbv_assessment_prompt = extract_hbv_assessment_prompt()
    
    assessment_para = doc.add_paragraph(hbv_assessment_prompt)
    assessment_para.style = 'Normal'
    
    # Format the assessment prompt text
    for run in assessment_para.runs:
        run.font.size = Pt(10)
        run.font.name = 'Courier New'
    
    doc.add_page_break()
    
    # ==================== AGENT PROMPT ====================
    doc.add_heading('2. Agent System Prompt', 1)
    
    # Add description
    desc1 = doc.add_paragraph()
    desc1.add_run('Purpose: ').bold = True
    desc1.add_run('Main conversational AI agent for clinical decision support\n')
    desc1.add_run('Location: ').bold = True
    desc1.add_run('core/agent.py\n')
    desc1.add_run('Model: ').bold = True
    desc1.add_run('GPT-4 (configurable)')
    
    doc.add_paragraph()  # Spacing
    
    # Add the actual prompt
    doc.add_heading('Prompt Content:', 2)
    system_message = extract_system_message_from_agent()
    prompt_para = doc.add_paragraph(system_message)
    prompt_para.style = 'Normal'
    
    # Format the prompt text
    for run in prompt_para.runs:
        run.font.size = Pt(10)
        run.font.name = 'Courier New'
    
    doc.add_page_break()
    
    # ==================== VALIDATION PROMPT ====================
    doc.add_heading('3. Validation System Prompt', 1)
    
    # Add description
    desc2 = doc.add_paragraph()
    desc2.add_run('Purpose: ').bold = True
    desc2.add_run('Validates generated medical answers for quality assurance\n')
    desc2.add_run('Location: ').bold = True
    desc2.add_run('core/validation.py\n')
    desc2.add_run('Model: ').bold = True
    desc2.add_run('GPT-4o')
    
    doc.add_paragraph()  # Spacing
    
    # Add validation criteria overview
    doc.add_heading('Validation Criteria:', 2)
    criteria = doc.add_paragraph()
    criteria.add_run('The validation prompt evaluates answers on 6 dimensions:\n')
    criteria_list = [
        'Accuracy (0-100%): Factual correctness based on provided documents',
        'Coherence (0-100%): Logical structure, clarity, and readability',
        'Relevance (0-100%): Addresses user\'s question without off-topic information',
        'Completeness (0-100%): Includes all necessary information from documents',
        'Citations/Attribution (0-100%): Proper citation of all claims',
        'Length (0-100%): Appropriate detail without being too brief or verbose'
    ]
    for criterion in criteria_list:
        doc.add_paragraph(criterion, style='List Bullet')
    
    doc.add_paragraph()  # Spacing
    
    # Add the actual validation prompt
    doc.add_heading('Prompt Content:', 2)
    validation_prompt = extract_validation_prompt()
    
    validation_para = doc.add_paragraph(validation_prompt)
    validation_para.style = 'Normal'
    
    # Format the validation prompt text
    for run in validation_para.runs:
        run.font.size = Pt(10)
        run.font.name = 'Courier New'
    
    # Save the document
    output_path = 'HBV_AI_Assistant_System_Prompts.docx'
    doc.save(output_path)
    print(f"✓ Document created successfully: {output_path}")
    print(f"✓ File location: {os.path.abspath(output_path)}")
    print(f"\n📋 Exported Prompts:")
    print(f"   1. HBV Assessment Prompt (core/hbv_assessment.py)")
    print(f"   2. Agent System Prompt (core/agent.py)")
    print(f"   3. Validation System Prompt (core/validation.py)")
    
    return output_path


if __name__ == "__main__":
    try:
        create_prompts_document()
    except Exception as e:
        print(f"✗ Error creating document: {str(e)}")
        import traceback
        traceback.print_exc()