Add export router to app.py and update requirements.txt for document generation libraries

api/app.py

@@ -6,7 +6,7 @@ from fastapi.exceptions import RequestValidationError
 from starlette.exceptions import HTTPException as StarletteHTTPException
 
 # Import routers
-from api.routers import medical, health
+from api.routers import medical, health, export
 from api.middleware import (
     ProcessTimeMiddleware, 
     LoggingMiddleware, 
@@ -73,6 +73,7 @@ app.add_exception_handler(Exception, general_exception_handler)
 # Include routers
 app.include_router(health.router)
 app.include_router(medical.router)
+app.include_router(export.router)
 
 # Root endpoint
 @app.get("/")
@@ -87,7 +88,8 @@ async def root():
         "endpoints": {
             "ask": "/ask",
             "ask_stream": "/ask/stream",
-            "initialization_status": "/health/initialization"
+            "initialization_status": "/health/initialization",
+            "export": "/export/{format}?session_id={session_id}"
         }
     }
 

api/routers/export.py

@@ -0,0 +1,266 @@
+"""
+Export Router for Conversation History
+"""
+import io
+import sys
+import os
+from datetime import datetime
+from fastapi import APIRouter, HTTPException
+from fastapi.responses import StreamingResponse
+from docx import Document
+from docx.shared import Pt, RGBColor, Inches
+from docx.enum.text import WD_ALIGN_PARAGRAPH
+from reportlab.lib.pagesizes import letter
+from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+from reportlab.lib.units import inch
+from reportlab.lib.colors import Color, HexColor
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
+from reportlab.lib.enums import TA_LEFT, TA_RIGHT
+
+# Add src to path for imports
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
+
+from core.agent import _memory_manager
+
+router = APIRouter(tags=["export"])
+
+
+def get_conversation_history(session_id: str):
+    """
+    Retrieve conversation history from memory manager.
+    
+    Args:
+        session_id: Session identifier
+        
+    Returns:
+        List of message dictionaries with 'role' and 'content'
+    """
+    try:
+        memory = _memory_manager.get_memory(session_id)
+        messages = []
+        
+        # Get chat history from memory
+        if hasattr(memory, 'chat_memory') and hasattr(memory.chat_memory, 'messages'):
+            for msg in memory.chat_memory.messages:
+                # LangChain messages have type and content
+                role = "User" if msg.type == "human" else "Assistant"
+                messages.append({
+                    "role": role,
+                    "content": msg.content
+                })
+        
+        return messages
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error retrieving conversation history: {str(e)}"
+        )
+
+
+def generate_docx(session_id: str, messages: list) -> io.BytesIO:
+    """
+    Generate a Word document from conversation history.
+    
+    Args:
+        session_id: Session identifier
+        messages: List of message dictionaries
+        
+    Returns:
+        BytesIO object containing the Word document
+    """
+    doc = Document()
+    
+    # Add title
+    title = doc.add_heading('Conversation History', 0)
+    title.alignment = WD_ALIGN_PARAGRAPH.CENTER
+    
+    # Add metadata
+    doc.add_paragraph(f'Session ID: {session_id}')
+    doc.add_paragraph(f'Export Date: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}')
+    doc.add_paragraph('')  # Empty line
+    
+    # Add separator
+    doc.add_paragraph('_' * 80)
+    doc.add_paragraph('')
+    
+    # Add messages
+    for msg in messages:
+        # Add role heading
+        role_para = doc.add_paragraph()
+        role_run = role_para.add_run(f"{msg['role']}:")
+        role_run.bold = True
+        role_run.font.size = Pt(12)
+        
+        if msg['role'] == 'User':
+            role_run.font.color.rgb = RGBColor(255, 107, 53)  # Orange color
+        else:
+            role_run.font.color.rgb = RGBColor(51, 51, 51)  # Dark gray
+        
+        # Add message content
+        content_para = doc.add_paragraph(msg['content'])
+        content_para.paragraph_format.left_indent = Inches(0.25)
+        
+        # Add spacing
+        doc.add_paragraph('')
+    
+    # Save to BytesIO
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    buffer.seek(0)
+    
+    return buffer
+
+
+def generate_pdf(session_id: str, messages: list) -> io.BytesIO:
+    """
+    Generate a PDF document from conversation history.
+    
+    Args:
+        session_id: Session identifier
+        messages: List of message dictionaries
+        
+    Returns:
+        BytesIO object containing the PDF document
+    """
+    buffer = io.BytesIO()
+    doc = SimpleDocTemplate(buffer, pagesize=letter,
+                           rightMargin=72, leftMargin=72,
+                           topMargin=72, bottomMargin=18)
+    
+    # Container for the 'Flowable' objects
+    elements = []
+    
+    # Define styles
+    styles = getSampleStyleSheet()
+    
+    # Title style
+    title_style = ParagraphStyle(
+        'CustomTitle',
+        parent=styles['Heading1'],
+        fontSize=24,
+        textColor=HexColor('#000000'),
+        spaceAfter=30,
+        alignment=TA_LEFT
+    )
+    
+    # Metadata style
+    meta_style = ParagraphStyle(
+        'MetaStyle',
+        parent=styles['Normal'],
+        fontSize=10,
+        textColor=HexColor('#666666'),
+        spaceAfter=6
+    )
+    
+    # User message style
+    user_style = ParagraphStyle(
+        'UserStyle',
+        parent=styles['Normal'],
+        fontSize=11,
+        textColor=HexColor('#FF6B35'),
+        fontName='Helvetica-Bold',
+        spaceAfter=6
+    )
+    
+    # Assistant message style
+    assistant_style = ParagraphStyle(
+        'AssistantStyle',
+        parent=styles['Normal'],
+        fontSize=11,
+        textColor=HexColor('#333333'),
+        fontName='Helvetica-Bold',
+        spaceAfter=6
+    )
+    
+    # Content style
+    content_style = ParagraphStyle(
+        'ContentStyle',
+        parent=styles['Normal'],
+        fontSize=10,
+        leftIndent=20,
+        spaceAfter=12
+    )
+    
+    # Add title
+    elements.append(Paragraph('Conversation History', title_style))
+    elements.append(Spacer(1, 12))
+    
+    # Add metadata
+    elements.append(Paragraph(f'Session ID: {session_id}', meta_style))
+    elements.append(Paragraph(f'Export Date: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}', meta_style))
+    elements.append(Spacer(1, 20))
+    
+    # Add separator line
+    elements.append(Paragraph('_' * 100, meta_style))
+    elements.append(Spacer(1, 12))
+    
+    # Add messages
+    for msg in messages:
+        # Add role
+        role_style = user_style if msg['role'] == 'User' else assistant_style
+        elements.append(Paragraph(f"{msg['role']}:", role_style))
+        
+        # Add content (escape HTML special characters)
+        content = msg['content'].replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')
+        elements.append(Paragraph(content, content_style))
+        elements.append(Spacer(1, 12))
+    
+    # Build PDF
+    doc.build(elements)
+    buffer.seek(0)
+    
+    return buffer
+
+
+@router.get("/export/{format}")
+async def export_conversation(format: str, session_id: str = "default"):
+    """
+    Export conversation history as Word (.docx) or PDF (.pdf) file.
+    
+    Args:
+        format: Export format ('docx' or 'pdf')
+        session_id: Session identifier (default: "default")
+        
+    Returns:
+        StreamingResponse with the generated document
+    """
+    # Validate format
+    if format.lower() not in ['docx', 'pdf']:
+        raise HTTPException(
+            status_code=400,
+            detail="Invalid format. Use 'docx' or 'pdf'"
+        )
+    
+    # Get conversation history
+    messages = get_conversation_history(session_id)
+    
+    if not messages:
+        raise HTTPException(
+            status_code=404,
+            detail="No conversation history found for this session"
+        )
+    
+    try:
+        # Generate document based on format
+        if format.lower() == 'docx':
+            buffer = generate_docx(session_id, messages)
+            media_type = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+            filename = f"conversation_{session_id}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
+        else:  # pdf
+            buffer = generate_pdf(session_id, messages)
+            media_type = "application/pdf"
+            filename = f"conversation_{session_id}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
+        
+        return StreamingResponse(
+            buffer,
+            media_type=media_type,
+            headers={
+                "Content-Disposition": f"attachment; filename={filename}"
+            }
+        )
+        
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error generating {format.upper()} document: {str(e)}"
+        )

logs/app.log

@@ -2810,3 +2810,219 @@ Medicatio...
 2025-10-14 19:13:14,886 - AgenticMedicalRAG - INFO - Successfully processed user input: what is my name...
 2025-10-14 19:13:24,367 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): hi what is my name...
 2025-10-14 19:13:26,466 - AgenticMedicalRAG - INFO - Successfully processed user input: hi what is my name...
+2025-10-15 11:55:21,110 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 11:55:22,611 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 11:55:22,612 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 11:55:22,612 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 11:55:22,613 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 11:55:34,494 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 11:55:34,495 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 11:55:34,496 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 11:55:34,496 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 11:55:34,496 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 11:55:35,068 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 11:55:35,089 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 11:55:35,089 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 11:55:35,445 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 11:55:35,445 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 11:55:35,446 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 11:55:35,446 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 11:55:35,446 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 11:56:29,506 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 11:56:30,251 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 11:56:30,252 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 11:56:30,253 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 11:56:30,253 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 11:56:37,823 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 11:56:37,824 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 11:56:37,824 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 11:56:37,825 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 11:56:37,825 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 11:56:37,896 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 11:56:37,912 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 11:56:37,913 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 11:56:38,314 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 11:56:38,315 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 11:56:38,316 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 11:56:38,316 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 11:56:38,316 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 11:56:39,646 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 11:56:39,646 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 11:56:39,646 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 12:03:09,903 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 12:03:10,683 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 12:03:10,684 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 12:03:10,685 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 12:03:10,686 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 12:03:18,456 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 12:03:18,456 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 12:03:18,456 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 12:03:18,456 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 12:03:18,456 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 12:03:18,562 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 12:03:18,588 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 12:03:18,589 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 12:03:18,983 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 12:03:18,983 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 12:03:18,984 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 12:03:18,984 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 12:03:18,984 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 12:03:20,251 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 12:03:20,251 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 12:03:20,252 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 12:04:12,798 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 12:04:23,412 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 12:04:24,235 - AgenticMedicalRAG - INFO - Medical answer validator initialized successfully
+2025-10-15 12:04:24,235 - AgenticMedicalRAG - INFO - GitHub storage initialized for MoazEldsouky/cloud-data-store
+2025-10-15 12:04:37,308 - AgenticMedicalRAG - INFO - Starting validation for interaction 36
+2025-10-15 12:04:52,405 - AgenticMedicalRAG - INFO - Assigned unique interaction ID: 36
+2025-10-15 12:04:56,153 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/evaluation_results.json to GitHub
+2025-10-15 12:04:56,154 - AgenticMedicalRAG - INFO - Evaluation saved to GitHub with ID: 36
+2025-10-15 12:04:56,154 - AgenticMedicalRAG - INFO - Background validation completed - Interaction ID: 36
+2025-10-15 12:04:56,155 - AgenticMedicalRAG - INFO - Validation scores - Overall: 90/100, Accuracy: 95/100, Coherence: 90/100, Relevance: 100/100
+2025-10-15 12:04:56,155 - AgenticMedicalRAG - INFO - Successfully processed user input: What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 12:04:56,159 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): What is the recommended first-line treatment for a...
+2025-10-15 12:05:03,904 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 12:05:05,234 - AgenticMedicalRAG - INFO - Starting validation for interaction 37
+2025-10-15 12:05:13,869 - AgenticMedicalRAG - INFO - Assigned unique interaction ID: 37
+2025-10-15 12:05:18,504 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/evaluation_results.json to GitHub
+2025-10-15 12:05:18,505 - AgenticMedicalRAG - INFO - Evaluation saved to GitHub with ID: 37
+2025-10-15 12:05:18,506 - AgenticMedicalRAG - INFO - Background validation completed - Interaction ID: 37
+2025-10-15 12:05:18,506 - AgenticMedicalRAG - INFO - Validation scores - Overall: 90/100, Accuracy: 95/100, Coherence: 90/100, Relevance: 88/100
+2025-10-15 12:05:18,506 - AgenticMedicalRAG - INFO - Successfully processed user input: What is the recommended first-line treatment for a...
+2025-10-15 12:06:42,357 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): i found that Afinitor has these side effects fever...
+2025-10-15 12:06:51,917 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/side_effects_reports.csv to GitHub
+2025-10-15 12:06:53,527 - AgenticMedicalRAG - INFO - Successfully processed user input: i found that Afinitor has these side effects fever...
+2025-10-15 13:53:10,922 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 13:53:14,459 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 13:53:14,460 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 13:53:14,461 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 13:53:14,461 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 13:53:37,561 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 13:53:37,561 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 13:53:37,562 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 13:53:37,562 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 13:53:37,562 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 13:53:38,204 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 13:53:38,256 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 13:53:38,257 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 13:53:38,599 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 13:53:38,599 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 13:53:38,600 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 13:53:38,600 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 13:53:38,600 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 13:53:40,070 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 13:53:40,071 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 13:53:40,071 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 15:15:32,001 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:21:28,032 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:25:20,165 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:26:11,107 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:28:26,020 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:31:26,481 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:31:27,943 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 15:31:27,944 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 15:31:27,945 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 15:31:27,945 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 15:31:37,240 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 15:31:37,240 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 15:31:37,240 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 15:31:37,241 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 15:31:37,241 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 15:31:37,355 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 15:31:37,381 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 15:31:37,381 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 15:31:37,816 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 15:31:37,816 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 15:31:37,816 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 15:31:37,817 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 15:31:37,817 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 15:31:39,116 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 15:31:39,117 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 15:31:39,117 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 15:43:17,615 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): hi...
+2025-10-15 15:43:20,246 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 15:43:20,246 - AgenticMedicalRAG - INFO - Skipping validation: insufficient context
+2025-10-15 15:43:20,247 - AgenticMedicalRAG - INFO - Successfully processed user input: hi...
+2025-10-15 15:43:38,087 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 15:43:47,023 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 15:43:48,038 - AgenticMedicalRAG - INFO - Medical answer validator initialized successfully
+2025-10-15 15:43:48,038 - AgenticMedicalRAG - INFO - GitHub storage initialized for MoazEldsouky/cloud-data-store
+2025-10-15 15:43:49,398 - AgenticMedicalRAG - INFO - Starting validation for interaction 38
+2025-10-15 15:44:05,399 - AgenticMedicalRAG - INFO - Assigned unique interaction ID: 38
+2025-10-15 15:44:09,466 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/evaluation_results.json to GitHub
+2025-10-15 15:44:09,467 - AgenticMedicalRAG - INFO - Evaluation saved to GitHub with ID: 38
+2025-10-15 15:44:09,468 - AgenticMedicalRAG - INFO - Background validation completed - Interaction ID: 38
+2025-10-15 15:44:09,468 - AgenticMedicalRAG - INFO - Validation scores - Overall: 90/100, Accuracy: 95/100, Coherence: 90/100, Relevance: 100/100
+2025-10-15 15:44:09,468 - AgenticMedicalRAG - INFO - Successfully processed user input: What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 15:48:15,410 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:48:19,805 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 15:48:19,807 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 15:48:19,807 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 15:48:19,808 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 15:48:32,796 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 15:48:34,304 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 15:48:34,305 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 15:48:34,306 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 15:48:34,307 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 15:48:56,261 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 15:48:56,262 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 15:48:56,263 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 15:48:56,263 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 15:48:56,263 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 15:48:56,812 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 15:48:56,857 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 15:48:56,857 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 15:48:57,268 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 15:48:57,268 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 15:48:57,268 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 15:48:57,269 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 15:48:57,269 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 15:48:58,999 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 15:48:59,000 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 15:48:59,000 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 16:00:25,963 - AgenticMedicalRAG - INFO - Configuration validation completed
+2025-10-15 16:00:27,014 - AgenticMedicalRAG - INFO - 🚀 Starting background initialization...
+2025-10-15 16:00:27,015 - AgenticMedicalRAG - INFO - 🔄 Background Init: Starting background initialization... (0%)
+2025-10-15 16:00:27,015 - AgenticMedicalRAG - INFO - 🔄 Background Init: Loading embedding model... (10%)
+2025-10-15 16:00:27,016 - AgenticMedicalRAG - INFO - Loading embedding model (first time)...
+2025-10-15 16:00:35,116 - AgenticMedicalRAG - INFO - Embedding model loaded successfully
+2025-10-15 16:00:35,117 - AgenticMedicalRAG - INFO - 🔄 Background Init: Embedding model loaded successfully (40%)
+2025-10-15 16:00:35,117 - AgenticMedicalRAG - INFO - 🔄 Background Init: Initializing retrievers and loading chunks... (50%)
+2025-10-15 16:00:35,117 - AgenticMedicalRAG - INFO - 🔄 Initializing retrievers (first time use)...
+2025-10-15 16:00:35,117 - AgenticMedicalRAG - INFO - 🔄 Processing new data and updating vector store if needed...
+2025-10-15 16:00:35,207 - AgenticMedicalRAG - INFO - 📦 Loading chunks cache for BM25 retriever...
+2025-10-15 16:00:35,225 - AgenticMedicalRAG - INFO - 🔍 Creating vector retriever...
+2025-10-15 16:00:35,225 - AgenticMedicalRAG - INFO - 📝 Creating BM25 retriever...
+2025-10-15 16:00:35,521 - AgenticMedicalRAG - INFO - 🔄 Creating hybrid retriever...
+2025-10-15 16:00:35,522 - AgenticMedicalRAG - INFO - ✅ Retrievers initialized successfully.
+2025-10-15 16:00:35,522 - AgenticMedicalRAG - INFO - 🔄 Background Init: Retrievers initialized successfully (90%)
+2025-10-15 16:00:35,522 - AgenticMedicalRAG - INFO - 🔄 Background Init: Warming up LLM... (95%)
+2025-10-15 16:00:35,522 - AgenticMedicalRAG - INFO - Initializing LLM (first time)...
+2025-10-15 16:00:36,475 - AgenticMedicalRAG - INFO - LLM initialized successfully
+2025-10-15 16:00:36,475 - AgenticMedicalRAG - INFO - 🔄 Background Init: All components initialized successfully (100%)
+2025-10-15 16:00:36,475 - AgenticMedicalRAG - INFO - ✅ Background initialization completed successfully
+2025-10-15 16:00:59,757 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): hi...
+2025-10-15 16:01:02,437 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 16:01:02,437 - AgenticMedicalRAG - INFO - Skipping validation: insufficient context
+2025-10-15 16:01:02,438 - AgenticMedicalRAG - INFO - Successfully processed user input: hi...
+2025-10-15 16:01:04,703 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 16:01:11,862 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 16:01:13,014 - AgenticMedicalRAG - INFO - Medical answer validator initialized successfully
+2025-10-15 16:01:13,015 - AgenticMedicalRAG - INFO - GitHub storage initialized for MoazEldsouky/cloud-data-store
+2025-10-15 16:01:13,844 - AgenticMedicalRAG - INFO - Starting validation for interaction 39
+2025-10-15 16:01:27,985 - AgenticMedicalRAG - INFO - Assigned unique interaction ID: 39
+2025-10-15 16:01:31,979 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/evaluation_results.json to GitHub
+2025-10-15 16:01:31,980 - AgenticMedicalRAG - INFO - Evaluation saved to GitHub with ID: 39
+2025-10-15 16:01:31,980 - AgenticMedicalRAG - INFO - Background validation completed - Interaction ID: 39
+2025-10-15 16:01:31,980 - AgenticMedicalRAG - INFO - Validation scores - Overall: 90/100, Accuracy: 95/100, Coherence: 90/100, Relevance: 88/100
+2025-10-15 16:01:31,981 - AgenticMedicalRAG - INFO - Successfully processed user input: What is the role of durvalumab in stage III NSCLC ...
+2025-10-15 17:12:17,907 - AgenticMedicalRAG - INFO - Processing user input (attempt 1): What first-line systemic therapy does ASCO recomme...
+2025-10-15 17:12:24,603 - AgenticMedicalRAG - INFO - Performing background validation for streaming response...
+2025-10-15 17:12:25,574 - AgenticMedicalRAG - INFO - Starting validation for interaction 40
+2025-10-15 17:12:34,757 - AgenticMedicalRAG - INFO - Assigned unique interaction ID: 40
+2025-10-15 17:12:39,210 - AgenticMedicalRAG - INFO - Successfully uploaded medical_data/evaluation_results.json to GitHub
+2025-10-15 17:12:39,211 - AgenticMedicalRAG - INFO - Evaluation saved to GitHub with ID: 40
+2025-10-15 17:12:39,212 - AgenticMedicalRAG - INFO - Background validation completed - Interaction ID: 40
+2025-10-15 17:12:39,212 - AgenticMedicalRAG - INFO - Validation scores - Overall: 90/100, Accuracy: 95/100, Coherence: 90/100, Relevance: 88/100
+2025-10-15 17:12:39,212 - AgenticMedicalRAG - INFO - Successfully processed user input: What first-line systemic therapy does ASCO recomme...

requirements.txt

@@ -31,3 +31,8 @@ rank-bm25==0.2.2
 numpy<2
 torch==2.2.2+cpu
 --extra-index-url https://download.pytorch.org/whl/cpu
+
+# Document generation
+python-docx==1.1.2
+reportlab==4.2.5
+