Update app.py

app.py

@@ -3,7 +3,7 @@ import os
 import pandas as pd
 import json
 import gradio as gr
-from typing import List, Tuple, Union, Generator
+from typing import List, Tuple, Union, Generator, BinaryIO
 import hashlib
 import shutil
 import re
@@ -25,7 +25,7 @@ for d in [model_cache_dir, tool_cache_dir, file_cache_dir, report_dir]:
 os.environ["HF_HOME"] = model_cache_dir
 os.environ["TRANSFORMERS_CACHE"] = model_cache_dir
 
-sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "src")))
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "src"))
 from txagent.txagent import TxAgent
 
 MAX_MODEL_TOKENS = 32768
@@ -42,17 +42,30 @@ def clean_response(text: str) -> str:
 def estimate_tokens(text: str) -> int:
     return len(text) // 3.5 + 1
 
-def extract_text_from_excel(file_obj: Union[str, os.PathLike, 'file']) -> str:
+def extract_text_from_excel(file_obj: Union[str, os.PathLike, BinaryIO]) -> str:
+    """Extract text from Excel file which can be a path, file-like object, or Gradio file object."""
     all_text = []
     try:
-        xls = pd.ExcelFile(file_obj)
+        # Handle Gradio file object which has .name attribute
+        if hasattr(file_obj, 'name'):
+            file_path = file_obj.name
+        else:
+            file_path = file_obj
+            
+        xls = pd.ExcelFile(file_path)
     except Exception as e:
         raise ValueError(f"❌ Error reading Excel file: {e}")
+    
     for sheet_name in xls.sheet_names:
-        df = xls.parse(sheet_name).astype(str).fillna("")
-        rows = df.apply(lambda row: " | ".join([cell for cell in row if cell.strip()]), axis=1)
-        sheet_text = [f"[{sheet_name}] {line}" for line in rows if line.strip()]
-        all_text.extend(sheet_text)
+        try:
+            df = xls.parse(sheet_name).astype(str).fillna("")
+            rows = df.apply(lambda row: " | ".join([cell for cell in row if cell.strip()]), axis=1)
+            sheet_text = [f"[{sheet_name}] {line}" for line in rows if line.strip()]
+            all_text.extend(sheet_text)
+        except Exception as e:
+            print(f"Warning: Could not parse sheet {sheet_name}: {e}")
+            continue
+            
     return "\n".join(all_text)
 
 def split_text_into_chunks(text: str, max_tokens: int = MAX_CHUNK_TOKENS, max_chunks: int = 30) -> List[str]:
@@ -95,7 +108,16 @@ Respond in well-structured bullet points with medical reasoning.
 def init_agent():
     tool_path = os.path.join(tool_cache_dir, "new_tool.json")
     if not os.path.exists(tool_path):
-        shutil.copy(os.path.abspath("data/new_tool.json"), tool_path)
+        # Create default tool file if it doesn't exist
+        default_tool = {
+            "name": "new_tool",
+            "description": "Default tool configuration",
+            "version": "1.0",
+            "tools": []
+        }
+        with open(tool_path, 'w') as f:
+            json.dump(default_tool, f)
+            
     agent = TxAgent(
         model_name="mims-harvard/TxAgent-T1-Llama-3.1-8B",
         rag_model_name="mims-harvard/ToolRAG-T1-GTE-Qwen2-1.5B",
@@ -108,20 +130,14 @@ def init_agent():
     agent.init_model()
     return agent
 
-def stream_report(agent, input_file: Union[str, 'file'], full_output: str) -> Generator[Tuple[str, Union[str, None], str], None, None]:
+def stream_report(agent, input_file: Union[str, BinaryIO], full_output: str) -> Generator[Tuple[str, Union[str, None], str], None, None]:
     accumulated_text = ""
     try:
         if input_file is None:
             yield "❌ Please upload a valid Excel file.", None, ""
             return
 
-        if hasattr(input_file, "read"):
-            text = extract_text_from_excel(input_file)
-        elif isinstance(input_file, str) and os.path.exists(input_file):
-            text = extract_text_from_excel(input_file)
-        else:
-            raise ValueError("❌ Invalid or missing file.")
-
+        text = extract_text_from_excel(input_file)
         chunks = split_text_into_chunks(text)
 
         for i, chunk in enumerate(chunks):
@@ -221,7 +237,13 @@ if __name__ == "__main__":
     try:
         agent = init_agent()
         demo = create_ui(agent)
-        demo.launch(server_name="0.0.0.0", server_port=7860, allowed_paths=["/data/hf_cache/reports"], share=True)
+        demo.launch(
+            server_name="0.0.0.0", 
+            server_port=7860, 
+            allowed_paths=["/data/hf_cache/reports"], 
+            share=True,
+            show_error=True
+        )
     except Exception as e:
-        print(f"Error: {str(e)}")
-        sys.exit(1)
+        print(f"Error: {str(e)}", file=sys.stderr)
+        sys.exit(1)