Update ui/ui_core.py

ui/ui_core.py

@@ -1,46 +1,57 @@
 import sys
 import os
+import pandas as pd
+import pdfplumber
+import gradio as gr
 
 # ✅ Add src to Python path
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "src")))
-
 from txagent.txagent import TxAgent
-import pandas as pd
-import pdfplumber
-import gradio as gr
 
-def extract_all_text_from_csv(file_path):
+
+def extract_all_text_from_csv(file_path, progress=None, index=0, total=1):
     try:
-        df = pd.read_csv(file_path)
+        df = pd.read_csv(file_path, low_memory=False)
+        if progress:
+            progress((index + 1) / total, desc=f"Processed CSV: {os.path.basename(file_path)}")
         return df.to_string(index=False)
     except Exception as e:
         return f"Error parsing CSV: {e}"
 
-def extract_all_text_from_pdf(file_path):
+
+def extract_all_text_from_pdf(file_path, progress=None, index=0, total=1):
     extracted = []
     try:
         with pdfplumber.open(file_path) as pdf:
-            for page in pdf.pages:
+            num_pages = len(pdf.pages)
+            for i, page in enumerate(pdf.pages):
                 tables = page.extract_tables()
                 for table in tables:
                     for row in table:
                         if any(row):
                             extracted.append("\t".join([cell or "" for cell in row]))
+                if progress:
+                    progress((index + i / num_pages) / total, desc=f"Parsing PDF: {os.path.basename(file_path)} ({i+1}/{num_pages})")
         return "\n".join(extracted)
     except Exception as e:
         return f"Error parsing PDF: {e}"
 
+
 def create_ui(agent: TxAgent):
     with gr.Blocks(theme=gr.themes.Soft()) as demo:
         gr.Markdown("<h1 style='text-align: center;'>💊 TxAgent: Therapeutic Reasoning</h1>")
         chatbot = gr.Chatbot(label="TxAgent", height=600, type="messages")
 
-        file_upload = gr.File(label="Upload Medical File", file_types=[".pdf", ".txt", ".docx", ".jpg", ".png", ".csv"], file_count="multiple")
+        file_upload = gr.File(
+            label="Upload Medical File",
+            file_types=[".pdf", ".txt", ".docx", ".jpg", ".png", ".csv"],
+            file_count="multiple"
+        )
         message_input = gr.Textbox(placeholder="Ask a biomedical question or just upload the files...", show_label=False)
         send_button = gr.Button("Send", variant="primary")
         conversation_state = gr.State([])
 
-        def handle_chat(message, history, conversation, uploaded_files):
+        def handle_chat(message, history, conversation, uploaded_files, progress=gr.Progress()):
             context = (
                 "You are a clinical AI reviewing medical interview or form data. "
                 "Analyze the extracted content and reason step-by-step about what the doctor could have missed. "
@@ -49,14 +60,18 @@ def create_ui(agent: TxAgent):
 
             if uploaded_files:
                 extracted_text = ""
-                for file in uploaded_files:
+                total_files = len(uploaded_files)
+
+                for index, file in enumerate(uploaded_files):
                     path = file.name
                     if path.endswith(".csv"):
-                        extracted_text += extract_all_text_from_csv(path) + "\n"
+                        extracted_text += extract_all_text_from_csv(path, progress, index, total_files) + "\n"
                     elif path.endswith(".pdf"):
-                        extracted_text += extract_all_text_from_pdf(path) + "\n"
+                        extracted_text += extract_all_text_from_pdf(path, progress, index, total_files) + "\n"
                     else:
                         extracted_text += f"(Uploaded file: {os.path.basename(path)})\n"
+                        if progress:
+                            progress((index + 1) / total_files, desc=f"Skipping unsupported file: {os.path.basename(path)}")
 
                 message = f"{context}\n\n---\n{extracted_text.strip()}\n---\n\nNow reason what the doctor might have missed."