Update app.py

app.py

@@ -3,13 +3,14 @@ import os
 import pandas as pd
 import json
 import gradio as gr
-from typing import List
+from typing import List, Tuple
 import hashlib
 import shutil
 import re
 from datetime import datetime
 import time
 
+# Configuration and setup
 persistent_dir = "/data/hf_cache"
 os.makedirs(persistent_dir, exist_ok=True)
 
@@ -36,13 +37,10 @@ def file_hash(path: str) -> str:
 
 def clean_response(text: str) -> str:
     try:
-        # First try to encode/decode to handle any surrogate pairs
         text = text.encode('utf-8', 'surrogatepass').decode('utf-8')
-    except UnicodeEncodeError:
-        # Fallback to replace strategy if there are invalid characters
+    except UnicodeError:
         text = text.encode('utf-8', 'replace').decode('utf-8')
     
-    # Additional cleaning
     text = re.sub(r"\[.*?\]|\bNone\b", "", text, flags=re.DOTALL)
     text = re.sub(r"\n{3,}", "\n\n", text)
     text = re.sub(r"[^\n#\-\*\w\s\.,:\(\)]+", "", text)
@@ -59,7 +57,6 @@ def parse_excel_to_prompts(file_path: str) -> List[str]:
             records = []
             for _, row in group.iterrows():
                 record = f"- {row['Form Name']}: {row['Form Item']} = {row['Item Response']} ({row['Interview Date']} by {row['Interviewer']})\n{row['Description']}"
-                # Clean each record to prevent encoding issues
                 records.append(clean_response(record))
             
             record_text = "\n".join(records)
@@ -94,73 +91,105 @@ def init_agent():
     target_tool_path = os.path.join(tool_cache_dir, "new_tool.json")
     
     if not os.path.exists(target_tool_path):
-        try:
-            shutil.copy(default_tool_path, target_tool_path)
-        except Exception as e:
-            raise RuntimeError(f"Failed to copy tool file: {str(e)}")
+        shutil.copy(default_tool_path, target_tool_path)
     
-    try:
-        agent = TxAgent(
-            model_name="mims-harvard/TxAgent-T1-Llama-3.1-8B",
-            rag_model_name="mims-harvard/ToolRAG-T1-GTE-Qwen2-1.5B",
-            tool_files_dict={"new_tool": target_tool_path},
-            force_finish=True,
-            enable_checker=True,
-            step_rag_num=4,
-            seed=100,
-            additional_default_tools=[],
-        )
-        agent.init_model()
-        return agent
-    except Exception as e:
-        raise RuntimeError(f"Failed to initialize agent: {str(e)}")
+    agent = TxAgent(
+        model_name="mims-harvard/TxAgent-T1-Llama-3.1-8B",
+        rag_model_name="mims-harvard/ToolRAG-T1-GTE-Qwen2-1.5B",
+        tool_files_dict={"new_tool": target_tool_path},
+        force_finish=True,
+        enable_checker=True,
+        step_rag_num=4,
+        seed=100,
+        additional_default_tools=[],
+    )
+    agent.init_model()
+    return agent
 
 def create_ui(agent):
-    with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    with gr.Blocks(theme=gr.themes.Soft(), title="Clinical Oversight Assistant") as demo:
         gr.Markdown("# 🏥 Clinical Oversight Assistant (Excel Optimized)")
         
-        with gr.Row():
-            with gr.Column(scale=1):
-                file_upload = gr.File(
-                    label="Upload Excel File",
-                    file_types=[".xlsx"], 
-                    file_count="single",
-                    interactive=True
-                )
-                msg_input = gr.Textbox(
-                    label="Additional Instructions",
-                    placeholder="Add any specific analysis requests...",
-                    lines=3
-                )
-                send_btn = gr.Button("Analyze", variant="primary")
+        with gr.Tabs():
+            with gr.TabItem("Analysis"):
+                with gr.Row():
+                    # Left column - Inputs
+                    with gr.Column(scale=1):
+                        file_upload = gr.File(
+                            label="Upload Excel File",
+                            file_types=[".xlsx"], 
+                            file_count="single",
+                            interactive=True
+                        )
+                        msg_input = gr.Textbox(
+                            label="Additional Instructions",
+                            placeholder="Add any specific analysis requests...",
+                            lines=3
+                        )
+                        with gr.Row():
+                            clear_btn = gr.Button("Clear", variant="secondary")
+                            send_btn = gr.Button("Analyze", variant="primary")
+                    
+                    # Right column - Outputs
+                    with gr.Column(scale=2):
+                        chatbot = gr.Chatbot(
+                            label="Analysis Results",
+                            height=600,
+                            bubble_full_width=False,
+                            show_copy_button=True
+                        )
+                        download_output = gr.File(
+                            label="Download Full Report",
+                            interactive=False
+                        )
+            
+            with gr.TabItem("Instructions"):
+                gr.Markdown("""
+                ## How to Use This Tool
                 
-            with gr.Column(scale=2):
-                chatbot = gr.Chatbot(
-                    label="Analysis Results",
-                    height=600,
-                    bubble_full_width=False,
-                    show_copy_button=True
-                )
-                download_output = gr.File(
-                    label="Download Full Report",
-                    interactive=False
-                )
+                1. **Upload Excel File**: Select your patient records Excel file
+                2. **Add Instructions** (Optional): Provide any specific analysis requests
+                3. **Click Analyze**: The system will process each patient record
+                4. **Review Results**: Analysis appears in the chat window
+                5. **Download Report**: Get a full text report of all findings
+                
+                ### Excel File Requirements
+                Your Excel file must contain these columns:
+                - Booking Number
+                - Form Name
+                - Form Item
+                - Item Response
+                - Interview Date
+                - Interviewer
+                - Description
+                
+                ### Analysis Includes
+                - Missed diagnoses
+                - Medication conflicts
+                - Incomplete assessments
+                - Urgent follow-up needs
+                """)
         
-        def analyze(message: str, history: List[dict], file) -> tuple:
+        def format_message(role: str, content: str) -> Tuple[str, str]:
+            """Format messages for the chatbot in (user, bot) format"""
+            if role == "user":
+                return (content, None)
+            else:
+                return (None, content)
+        
+        def analyze(message: str, chat_history: List[Tuple[str, str]], file) -> Tuple[List[Tuple[str, str]], str]:
             if not file:
                 raise gr.Error("Please upload an Excel file first")
             
             try:
-                # Initial processing message
-                history.append({"role": "user", "content": message})
-                history.append({"role": "assistant", "content": "⏳ Processing Excel data..."})
-                yield history, None
+                # Initialize chat history with user message
+                new_history = chat_history + [format_message("user", message)]
+                new_history.append(format_message("assistant", "⏳ Processing Excel data..."))
+                yield new_history, None
                 
-                # Parse Excel file
                 prompts = parse_excel_to_prompts(file.name)
                 full_output = ""
                 
-                # Process each booking
                 for idx, prompt in enumerate(prompts, 1):
                     chunk_output = ""
                     try:
@@ -181,65 +210,59 @@ def create_ui(agent):
                             elif isinstance(result, str):
                                 cleaned = clean_response(result)
                                 chunk_output += cleaned + "\n"
-                                
-                            # Yield intermediate results
+                            
                             if chunk_output:
                                 output = f"--- Booking {idx} ---\n{chunk_output.strip()}\n"
-                                history[-1] = {"role": "assistant", "content": output}
-                                yield history, None
+                                new_history[-1] = format_message("assistant", output)
+                                yield new_history, None
                                 
                     except Exception as e:
                         error_msg = f"⚠️ Error processing booking {idx}: {str(e)}"
-                        history.append({"role": "assistant", "content": error_msg})
-                        yield history, None
+                        new_history.append(format_message("assistant", error_msg))
+                        yield new_history, None
                         continue
                         
                     if chunk_output:
                         output = f"--- Booking {idx} ---\n{chunk_output.strip()}\n"
-                        history.append({"role": "assistant", "content": output})
+                        new_history.append(format_message("assistant", output))
                         full_output += output + "\n"
-                        yield history, None
+                        yield new_history, None
                 
                 # Save report
                 file_hash_value = file_hash(file.name)
                 report_path = os.path.join(report_dir, f"{file_hash_value}_report.txt")
                 with open(report_path, "w", encoding="utf-8") as f:
                     f.write(full_output)
-                    
-                yield history, report_path if os.path.exists(report_path) else None
+                
+                yield new_history, report_path if os.path.exists(report_path) else None
                 
             except Exception as e:
-                history.append({"role": "assistant", "content": f"❌ Error: {str(e)}"})
-                yield history, None
+                new_history.append(format_message("assistant", f"❌ Error: {str(e)}"))
+                yield new_history, None
                 raise gr.Error(f"Analysis failed: {str(e)}")
-
+        
+        def clear_chat():
+            return [], None
+        
         # Event handlers
         send_btn.click(
             analyze,
-            inputs=[msg_input, gr.State([]), file_upload],
+            inputs=[msg_input, chatbot, file_upload],
             outputs=[chatbot, download_output],
             api_name="analyze"
         )
         
         msg_input.submit(
             analyze,
-            inputs=[msg_input, gr.State([]), file_upload],
+            inputs=[msg_input, chatbot, file_upload],
             outputs=[chatbot, download_output]
         )
         
-        # Additional UI elements
-        with gr.Accordion("Instructions", open=False):
-            gr.Markdown("""
-            **How to use:**
-            1. Upload an Excel file containing patient records
-            2. Optionally add specific analysis instructions
-            3. Click 'Analyze' to process the data
-            4. Review results and download the full report
-            
-            **Excel Format Requirements:**
-            - Must contain columns: Booking Number, Form Name, Form Item, Item Response, Interview Date, Interviewer, Description
-            - Each row represents one patient record item
-            """)
+        clear_btn.click(
+            clear_chat,
+            inputs=[],
+            outputs=[chatbot, download_output]
+        )
     
     return demo
 
@@ -248,7 +271,6 @@ if __name__ == "__main__":
         agent = init_agent()
         demo = create_ui(agent)
         
-        # Launch with error handling
         demo.queue(
             api_open=False,
             max_size=20
@@ -257,7 +279,7 @@ if __name__ == "__main__":
             server_port=7860,
             show_error=True,
             allowed_paths=[report_dir],
-            share=False  # Changed to False to avoid the warning
+            share=False
         )
     except Exception as e:
         print(f"Failed to launch application: {str(e)}")