Update app.py

app.py

@@ -1,8 +1,7 @@
 import os
 import nltk
-import asyncio
 
-# Use a directory within the user's home director
+# Use a directory within the user's home directory
 nltk_data_dir = os.path.expanduser("~/.nltk_data")
 os.makedirs(nltk_data_dir, exist_ok=True)
 nltk.data.path.append(nltk_data_dir)
@@ -101,106 +100,71 @@ question_prompt = (
     "Unless retrievable from the documents, don't ask questions which cannot be compared to previous periods."
 )
 
-import asyncio
-
-async def send_heartbeat(interval=300):
-    while True:
-        await asyncio.sleep(interval)  # Send heartbeat every 5 minutes
-        await cl.Message(content="Still waiting for your input...").send()
-
 @cl.on_chat_start
 async def on_chat_start():
-    # Start the heartbeat task
-    heartbeat_task = asyncio.create_task(send_heartbeat())
-
-    try:
-        # Set a timeout for the user input
-        ticker_response = await asyncio.wait_for(
-            cl.AskUserMessage(
-                content="Please enter the ticker symbol for the company you want to analyze:"
-            ).send(),
-            timeout=300  # Timeout after 300 seconds (5 minutes)
-        )
-
-        # Cancel the heartbeat once the user provides input
-        heartbeat_task.cancel()
-
-        # Check if ticker_response is None or doesn't contain 'content'
-        if ticker_response is None or 'content' not in ticker_response:
-            await cl.Message(content="No input received. Please restart and enter a valid ticker symbol.").send()
-            return
+    ticker_response = await cl.AskUserMessage(
+        content="Please enter the ticker symbol for the company you want to analyze:"
+    ).send()
 
-        ticker_symbol = ticker_response['content'].strip().upper()
-        if not ticker_symbol:
-            await cl.Message(content="No valid ticker symbol provided. Please restart and enter a valid ticker symbol.").send()
-            return
+    ticker_symbol = ticker_response['content'].upper()
 
-        msg = cl.Message(content=f"Retrieving financial data for {ticker_symbol}...")
-        await msg.send()
+    msg = cl.Message(content=f"Retrieving financial data for {ticker_symbol}...")
+    await msg.send()
 
-        try:
-            # Get the data for the company
-            company = yf.Ticker(ticker_symbol)
-
-            # Extract company information
-            company_info = company.info
-
-            # Extract analyst price targets
-            analysts_target = company.analyst_price_targets
+    try:
+        # Get the data for the company
+        company = yf.Ticker(ticker_symbol)
 
-            # Retrieve the Quarterly Financial Statements
-            quarterly_income_statement = company.quarterly_financials
-            quarterly_balance_sheet = company.quarterly_balance_sheet
-            quarterly_cash_flow = company.quarterly_cashflow
+        # Extract company information
+        company_info = company.info
 
-            # Generate the formatted financial summary
-            financial_summary = format_financial_data(
-                company_info, analysts_target, quarterly_income_statement,
-                quarterly_balance_sheet, quarterly_cash_flow
-            )
+        # Extract analyst price targets
+        analysts_target = company.analyst_price_targets
 
-            # Create a Document object with the financial summary
-            document = Document(text=financial_summary, metadata={"company": ticker_symbol})
+        # Retrieve the Quarterly Financial Statements
+        quarterly_income_statement = company.quarterly_financials
+        quarterly_balance_sheet = company.quarterly_balance_sheet
+        quarterly_cash_flow = company.quarterly_cashflow
 
-            # Create index
-            index = VectorStoreIndex.from_documents(
-                [document], service_context=service_context
-            )
+        # Generate the formatted financial summary
+        financial_summary = format_financial_data(
+            company_info, analysts_target, quarterly_income_statement,
+            quarterly_balance_sheet, quarterly_cash_flow
+        )
 
-            # Store the index in the user session
-            cl.user_session.set("index", index)
+        # Create a Document object with the financial summary
+        document = Document(text=financial_summary, metadata={"company": ticker_symbol})
 
-            # Generate summary
-            query_engine = index.as_query_engine()
-            summary_response = await cl.make_async(query_engine.query)(summary_prompt)
-            await cl.Message(content=f"**Summary:**\n{summary_response}").send()
+        # Create index
+        index = VectorStoreIndex.from_documents(
+            [document], service_context=service_context
+        )
 
-            # Generate questions
-            questions_response = await cl.make_async(query_engine.query)(question_prompt)
-            questions_format = str(questions_response).split('\n')
-            relevant_questions = [question.strip() for question in questions_format if question.strip() and question.strip()[0].isdigit()]
+        # Store the index in the user session
+        cl.user_session.set("index", index)
 
-            # Answer generated questions
-            await cl.Message(content="Generated questions and answers:").send()
-            for question in relevant_questions:
-                response = await cl.make_async(query_engine.query)(question)
-                await cl.Message(content=f"**{question}**\n{response}").send()
+        # Generate summary
+        query_engine = index.as_query_engine()
+        summary_response = await cl.make_async(query_engine.query)(summary_prompt)
+        await cl.Message(content=f"**Summary:**\n{summary_response}").send()
 
-            msg.content = "Processing done. You can now ask more questions about the financial data!"
-            await msg.update()
+        # Generate questions
+        questions_response = await cl.make_async(query_engine.query)(question_prompt)
+        questions_format = str(questions_response).split('\n')
+        relevant_questions = [question.strip() for question in questions_format if question.strip() and question.strip()[0].isdigit()]
 
-        except Exception as e:
-            await cl.Message(content=f"An error occurred during processing: {str(e)}").send()
+        # Answer generated questions
+        await cl.Message(content="Generated questions and answers:").send()
+        for question in relevant_questions:
+            response = await cl.make_async(query_engine.query)(question)
+            await cl.Message(content=f"**{question}**\n{response}").send()
 
-    except asyncio.TimeoutError:
-        # Handle timeout if no input is provided within 5 minutes
-        heartbeat_task.cancel()
-        await cl.Message(content="Session timed out due to inactivity. Please restart and enter a ticker symbol.").send()
+        msg.content = "Processing done. You can now ask more questions about the financial data!"
+        await msg.update()
 
     except Exception as e:
-        heartbeat_task.cancel()
-        await cl.Message(content=f"An error occurred: {str(e)}").send()
-
+        await cl.Message(content=f"An error occurred during processing: {str(e)}").send()
+        
 @cl.on_message
 async def main(message: cl.Message):
     index = cl.user_session.get("index")