Update app.py

app.py

@@ -96,41 +96,43 @@ def create_visualizations(df):
         
     return figures[0] if figures else None
 
+def analyze_chat_history(chat_history_text):
+    """Analyze chat history and return DataFrame, plot, and summary."""
+    if not chat_history_text.strip():
+        return None, None, "No chat history provided."
+    
+    df = create_researcher_df(chat_history_text)
+    
+    if df.empty:
+        return None, None, "No data could be extracted from the chat history."
+    
+    # Generate analysis summary
+    summary = f"Analysis of {len(df)} researchers:\n"
+    if 'affiliation' in df.columns:
+        summary += f"- Institutions represented: {df['affiliation'].nunique()}\n"
+    
+    field_counts = analyze_research_fields(df)
+    if not field_counts.empty:
+        top_fields = field_counts.nlargest(3)
+        summary += "- Top research fields:\n"
+        for field, count in top_fields.items():
+            summary += f"  • {field}: {count} researchers\n"
+    
+    # Create visualization
+    fig = create_visualizations(df)
+    
+    return df, fig, summary
+
 def process_message(
     message,
     chat_history,
     system_message,
     max_tokens,
     temperature,
-    top_p,
-    chat_history_text
+    top_p
 ):
-    """Process message and return response with analysis."""
+    """Process message and return response."""
     try:
-        # Process chat history if provided
-        if chat_history_text:
-            df = create_researcher_df(chat_history_text)
-            
-            # Generate analysis summary
-            summary = f"Analysis of {len(df)} researchers:\n"
-            if 'affiliation' in df.columns:
-                summary += f"- Institutions represented: {df['affiliation'].nunique()}\n"
-            
-            field_counts = analyze_research_fields(df)
-            if not field_counts.empty:
-                top_fields = field_counts.nlargest(3)
-                summary += "- Top research fields:\n"
-                for field, count in top_fields.items():
-                    summary += f"  • {field}: {count} researchers\n"
-            
-            # Create visualization
-            fig = create_visualizations(df)
-            
-            # Add analysis to message
-            message += f"\n\nCommunity Analysis:\n{summary}"
-        else:
-            fig = None
-
         # Generate response using the LLM
         messages = [{"role": "system", "content": system_message}]
         for user_msg, bot_msg in chat_history:
@@ -148,27 +150,45 @@ def process_message(
         bot_message = response.choices[0].message.content
         chat_history.append((message, bot_message))
         
-        return chat_history, fig, chat_history
+        return chat_history
 
     except Exception as e:
         error_message = f"Error: {str(e)}"
         chat_history.append((message, error_message))
-        return chat_history, None, chat_history
+        return chat_history
 
 with gr.Blocks(title="CohortBot") as demo:
-    chatbot = gr.Chatbot(label="Chat History")
-    msg = gr.Textbox(label="Message", placeholder="Type your message here...")
-    system_msg = gr.Textbox(value="You are a friendly Research Community Chatbot.", label="System message")
-    max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
-    temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
-    top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
-    chat_history_text = gr.Textbox(label="Chat History for Analysis", lines=10)
-    plot = gr.Plot(label="Community Analysis")
+    with gr.Row():
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(label="Chat History")
+            msg = gr.Textbox(label="Message", placeholder="Type your message here...")
+            with gr.Row():
+                system_msg = gr.Textbox(value="You are a friendly Research Community Chatbot.", label="System message")
+            with gr.Row():
+                max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+                temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+                top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
+        
+        with gr.Column(scale=1):
+            chat_history_text = gr.Textbox(label="Chat History for Analysis", lines=10)
+            analyze_btn = gr.Button("Analyze Chat History", variant="primary")
+            with gr.Row():
+                analysis_text = gr.Textbox(label="Analysis Summary", lines=4)
+            with gr.Row():
+                researcher_table = gr.Dataframe(label="Extracted Researcher Data")
+            with gr.Row():
+                plot = gr.Plot(label="Community Analysis")
     
     msg.submit(
         process_message,
-        [msg, chatbot, system_msg, max_tokens, temperature, top_p, chat_history_text],
-        [chatbot, plot, chatbot]
+        [msg, chatbot, system_msg, max_tokens, temperature, top_p],
+        [chatbot]
+    )
+    
+    analyze_btn.click(
+        analyze_chat_history,
+        inputs=[chat_history_text],
+        outputs=[researcher_table, plot, analysis_text]
     )
 
 if __name__ == "__main__":