update in files and ppt conversion to pdf

app.py

@@ -78,7 +78,7 @@ def setup_agent(vectorstore):
     tools = [retriever_tool, web_tool, scenario_simulator]
     llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.3)
     prompt = ChatPromptTemplate.from_messages([
-        ("system", "You are Dr. Sue Cohen's Teaching Assistant, a passionate tutor for Applied Optimization/Simulation/Decision Tech/Project Mgmt. Guide users with sharp insights, probing questions, and hints from course materials/web. Be witty (e.g., 'Solid, but don’t optimize for chaos—how’s this tie to diffusion?'), professional, encouraging. Run scenario sims for adoption/scalability queries with clear params. Prioritize course/web data, use web for updates. Be concise, cite sources, never solve outright, redirect if off-topic, prompt next steps."),
+        ("system", "You are Dr. Sue Cohen's Teaching Assistant, a passionate tutor for Commercializing New Technologies, Leading Organizations to Innovate Smarter, Competing in Emerging Economies, and Strategic Management. Guide users with sharp insights, probing questions, and hints from course materials/web. Be witty (e.g., 'Solid, but don’t optimize for chaos—how’s this tie to diffusion?'), professional, encouraging. Run scenario sims for adoption/scalability queries with clear params. Prioritize course/web data, use web for updates. Be concise, cite sources, never solve outright, redirect if off-topic, prompt next steps."),
         ("human", "{input}"),
         MessagesPlaceholder("agent_scratchpad")
     ])
@@ -108,9 +108,9 @@ agent = setup_agent(vectorstore)
 
 demo = gr.ChatInterface(
     fn=chat,
-    title="Opt/Sim Project RAG Bot",
-    description="Query materials + web aug, e.g., 'Latest on genetic algos in scheduling?'"
+    title="COMMERCIALIZING NEW TECHNOLOGIES RAG Bot",
+    description="Query materials + web augmented"
 )
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch(server_name="0.0.0.0", server_port=7860,share=True)

ppt_preproc.py

@@ -0,0 +1,130 @@
+import os
+import shutil
+import sys
+import logging
+from datetime import datetime
+
+# Set up logging
+logging.basicConfig(
+    filename=f"conversion_log_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log",
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
+
+# For .docx conversion
+try:
+    from docx2pdf import convert as docx_convert
+except ImportError:
+    logging.error("docx2pdf not installed. Run 'pip install docx2pdf'.")
+    sys.exit(1)
+
+# For .pptx conversion
+try:
+    import win32com.client
+except ImportError:
+    logging.error("pywin32 not installed. Run 'pip install pywin32'.")
+    sys.exit(1)
+
+try:
+    import comtypes.client
+except ImportError:
+    logging.warning("comtypes not installed. Run 'pip install comtypes' for fallback.")
+
+def check_irm_status(filepath):
+    """Check if IRM is enabled on a PPTX file."""
+    try:
+        ppt_app = win32com.client.Dispatch("PowerPoint.Application")
+        pres = ppt_app.Presentations.Open(os.path.abspath(filepath), ReadOnly=True, WithWindow=False)
+        irm_enabled = pres.Permission.Enabled
+        pres.Close()
+        ppt_app.Quit()
+        return irm_enabled
+    except Exception as e:
+        logging.error(f"Failed to check IRM for {filepath}: {e}")
+        return None
+
+def convert_pptx_print(filepath, output_pdf):
+    """Attempt PPTX to PDF conversion using print-to-PDF."""
+    try:
+        ppt_app = win32com.client.Dispatch("PowerPoint.Application")
+        pres = ppt_app.Presentations.Open(os.path.abspath(filepath), ReadOnly=True, WithWindow=False)
+        pres.PrintOut(PrintToFile=output_pdf)
+        pres.Close()
+        ppt_app.Quit()
+        logging.info(f"Converted {filepath} to {output_pdf} using print-to-PDF.")
+        return True
+    except Exception as e:
+        logging.error(f"Print-to-PDF failed for {filepath}: {e}")
+        return False
+
+def convert_pptx_win32(filepath, output_pdf):
+    """Attempt PPTX to PDF conversion using win32com SaveAs."""
+    try:
+        ppt_app = win32com.client.Dispatch("PowerPoint.Application")
+        pres = ppt_app.Presentations.Open(os.path.abspath(filepath), ReadOnly=True, WithWindow=False)
+        pres.SaveAs(output_pdf, 32)  # 32 = ppSaveAsPDF
+        pres.Close()
+        ppt_app.Quit()
+        logging.info(f"Converted {filepath} to {output_pdf} using win32com SaveAs.")
+        return True
+    except Exception as e:
+        logging.error(f"win32com SaveAs failed for {filepath}: {e}")
+        return False
+
+def convert_pptx_comtypes(filepath, output_pdf):
+    """Attempt PPTX to PDF conversion using comtypes SaveAs."""
+    try:
+        ppt_app = comtypes.client.CreateObject("PowerPoint.Application")
+        pres = ppt_app.Presentations.Open(os.path.abspath(filepath), ReadOnly=True, WithWindow=False)
+        pres.SaveAs(output_pdf, 32)  # 32 = ppSaveAsPDF
+        pres.Close()
+        ppt_app.Quit()
+        logging.info(f"Converted {filepath} to {output_pdf} using comtypes SaveAs.")
+        return True
+    except Exception as e:
+        logging.error(f"comtypes SaveAs failed for {filepath}: {e}")
+        return False
+
+def main(input_dir, output_dir):
+    if not os.path.isdir(input_dir):
+        logging.error(f"{input_dir} is not a directory.")
+        sys.exit(1)
+
+    os.makedirs(output_dir, exist_ok=True)
+
+    for root, _, files in os.walk(input_dir):
+        rel_dir = os.path.relpath(root, input_dir)
+        target_subdir = os.path.join(output_dir, rel_dir)
+        os.makedirs(target_subdir, exist_ok=True)
+
+        for file in files:
+            filepath = os.path.join(root, file)
+            base, ext = os.path.splitext(file)
+            output_pdf = os.path.join(target_subdir, base + '.pdf')
+
+            try:
+                if ext.lower() == '.docx':
+                    docx_convert(filepath, output_pdf)
+                    logging.info(f"Converted {filepath} to {output_pdf}")
+                elif ext.lower() == '.pptx':
+                    # Check IRM status
+                    irm_status = check_irm_status(filepath)
+                    if irm_status is not None:
+                        logging.info(f"IRM enabled for {filepath}: {irm_status}")
+                    
+                    # Try print-to-PDF first (bypasses edit restrictions)
+                    if not convert_pptx_print(filepath, output_pdf):
+                        # Fallback to SaveAs methods
+                        if not convert_pptx_win32(filepath, output_pdf):
+                            if 'comtypes' in sys.modules and not convert_pptx_comtypes(filepath, output_pdf):
+                                logging.warning(f"Failed to convert {filepath}. Likely IRM or strict restrictions.")
+                            elif not 'comtypes' in sys.modules:
+                                logging.warning(f"Failed to convert {filepath}. Install comtypes for additional fallback.")
+                elif ext.lower() == '.pdf':
+                    shutil.copy(filepath, output_pdf)
+                    logging.info(f"Copied {filepath} to {output_pdf}")
+            except Exception as e:
+                logging.error(f"Error processing {filepath}: {e}")
+
+if __name__ == "__main__":
+    main("OrigFolder", "ConvertedFiles")  # Use OrigFolder directly