Update app.py

app.py

@@ -5,9 +5,10 @@ from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.llms.groq import Groq
 from llama_index.core import ServiceContext
 from llama_index.core.node_parser import SentenceSplitter
-from PyPDF2 import PdfReader
-import tempfile
 from dotenv import load_dotenv
+import yfinance as yf
+import pandas as pd
+
 load_dotenv()
 
 # Fetch the API key from environment variables
@@ -24,90 +25,106 @@ service_context = ServiceContext.from_defaults(
     node_parser=SentenceSplitter(chunk_size=1000, chunk_overlap=200)
 )
 
+def format_financial_data(company_info, analysts_target, income_statement, balance_sheet, cash_flow):
+    summary = f"# {company_info.get('longName', '')} Financial Summary\n"
+    
+    # Company Overview
+    summary += f"\n## Company Overview\n"
+    business_summary = company_info.get('longBusinessSummary', '')
+    summary += f"{business_summary}\n"
+
+    # Analyst Price Targets
+    if analysts_target is not None and not analysts_target.empty:
+        current_price = company_info.get('currentPrice', 'N/A')
+        target_mean_price = analysts_target['targetMeanPrice'].iloc[-1]
+        target_high_price = analysts_target['targetHighPrice'].iloc[-1]
+        target_low_price = analysts_target['targetLowPrice'].iloc[-1]
+        number_of_analysts = analysts_target['numberOfAnalysts'].iloc[-1]
+        
+        summary += f"\n## Analyst Price Targets\n"
+        summary += f"- **Current Price**: ${current_price}\n"
+        summary += f"- **Mean Target Price**: ${target_mean_price}\n"
+        summary += f"- **High Target Price**: ${target_high_price}\n"
+        summary += f"- **Low Target Price**: ${target_low_price}\n"
+        summary += f"- **Number of Analysts**: {number_of_analysts}\n"
+
+    # Function to format financial tables
+    def format_financial_table(df, title):
+        summary = f"\n## {title}\n\n"
+        df = df.copy()
+        df.columns = [col.strftime('%Y-%m-%d') if hasattr(col, 'strftime') else col for col in df.columns]
+        df.index = df.index.str.replace(r'([a-z])([A-Z])', r'\1 \2', regex=True)  # Add spaces between words
+        df = df.apply(lambda x: x.apply(lambda y: f"${y:,.0f}" if pd.notnull(y) and isinstance(y, (int, float)) else y))
+        summary += df.to_markdown()
+        return summary
+
+    # Format the quarterly income statement
+    if income_statement is not None and not income_statement.empty:
+        summary += format_financial_table(income_statement, "Quarterly Income Statement")
+
+    # Format the quarterly balance sheet
+    if balance_sheet is not None and not balance_sheet.empty:
+        summary += format_financial_table(balance_sheet, "Quarterly Balance Sheet")
+
+    # Format the quarterly cash flow statement
+    if cash_flow is not None and not cash_flow.empty:
+        summary += format_financial_table(cash_flow, "Quarterly Cash Flow Statement")
+    
+    return summary
+
 summary_prompt = (
-    "You are a world-class financial analyst with extensive experience analyzing quarterly reports. "
-    "Give me a comprehensive summary of the earnings report. Focus on the Strategic Insights and Key Financial Figures. "
+    "You are a world-class financial analyst with extensive experience analyzing financial data. "
+    "Give me a comprehensive summary of the financial data. Focus on the Strategic Insights and Key Financial Figures. "
     "Answer in extensive bullet points please."
 )
 
 question_prompt = (
-    "You are a financial analyst with extensive experience analyzing quarterly reports. "
-    "Read the earnings call transcript and earnings presentation report and generate 10 questions focusing on the strategic insights and financial figures. "
+    "You are a financial analyst with extensive experience analyzing financial data. "
+    "Read the financial summary and generate 10 questions focusing on the strategic insights and financial figures. "
     "Ask questions that require precise answers and provide strategic insight into the company's financial and strategic performance, such as revenue growth, market trends, profit margins, and more. "
     "Only ask questions that can be answered using the provided document, without making any assumptions or inferences beyond the text. "
     "Please format the questions as a list with a simple '1. Question 1', '2. Question 2', etc. structure. "
     "Unless retrievable from the documents, don't ask questions which cannot be compared to previous periods."
 )
 
-def read_file_content(file):
-    if file.name.lower().endswith('.pdf'):
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
-            temp_file.write(file.content)
-            temp_file_path = temp_file.name
-        
-        try:
-            pdf_reader = PdfReader(temp_file_path)
-            text = ""
-            for page in pdf_reader.pages:
-                text += page.extract_text()
-        finally:
-            os.unlink(temp_file_path)
-    elif file.name.lower().endswith('.txt'):
-        text = file.content.decode('utf-8')
-    else:
-        raise ValueError("Unsupported file type")
-    
-    return text
-
 @cl.on_chat_start
 async def on_chat_start():
-    # Ask if the user wants to upload files or paste text
-    choice_response = await cl.AskUserMessage(
-        content="Would you like to upload files or paste text? (Type 'upload' or 'paste')"
+    ticker_response = await cl.AskUserMessage(
+        content="Please enter the ticker symbol for the company you want to analyze:"
     ).send()
 
-    choice_msg = choice_response['content'].lower()
-    documents = []
+    ticker_symbol = ticker_response['content'].upper()
 
-    if choice_msg == "upload":
-        files = await cl.AskFileMessage(
-            content="Please upload PDF or TXT files to begin!",
-            accept=["application/pdf", "text/plain"],
-            max_files=5,
-            max_size_mb=20,
-        ).send()
-
-        if not files:
-            await cl.Message(content="No files were uploaded. Please try again.").send()
-            return
+    msg = cl.Message(content=f"Retrieving financial data for {ticker_symbol}...")
+    await msg.send()
 
-        for file in files:
-            text = read_file_content(file)
-            documents.append(Document(text=text, metadata={"filename": file.name}))
+    try:
+        # Get the data for the company
+        company = yf.Ticker(ticker_symbol)
 
-    elif choice_msg == "paste":
-        pasted_response = await cl.AskUserMessage(
-            content="Please paste your document text here:"
-        ).send()
+        # Extract company information
+        company_info = company.info
 
-        pasted_text = pasted_response['content']
-        if not pasted_text:
-            await cl.Message(content="No text was pasted. Please try again.").send()
-            return
+        # Extract analyst price targets
+        analysts_target = company.analyst_price_target
 
-        documents.append(Document(text=pasted_text, metadata={"source": "pasted_text"}))
+        # Retrieve the Quarterly Financial Statements
+        quarterly_income_statement = company.quarterly_financials
+        quarterly_balance_sheet = company.quarterly_balance_sheet
+        quarterly_cash_flow = company.quarterly_cashflow
 
-    else:
-        await cl.Message(content="Invalid choice. Please start over and type either 'upload' or 'paste'.").send()
-        return
+        # Generate the formatted financial summary
+        financial_summary = format_financial_data(
+            company_info, analysts_target, quarterly_income_statement,
+            quarterly_balance_sheet, quarterly_cash_flow
+        )
 
-    msg = cl.Message(content="Processing input... Will take a few minutes")
-    await msg.send()
+        # Create a Document object with the financial summary
+        document = Document(text=financial_summary, metadata={"company": ticker_symbol})
 
-    try:
         # Create index
         index = VectorStoreIndex.from_documents(
-            documents, service_context=service_context
+            [document], service_context=service_context
         )
 
         # Store the index in the user session
@@ -129,7 +146,7 @@ async def on_chat_start():
             response = await cl.make_async(query_engine.query)(question)
             await cl.Message(content=f"**{question}**\n{response}").send()
 
-        msg.content = "Processing done. You can now ask more questions!"
+        msg.content = "Processing done. You can now ask more questions about the financial data!"
         await msg.update()
 
     except Exception as e:
@@ -140,7 +157,7 @@ async def main(message: cl.Message):
     index = cl.user_session.get("index")
     
     if index is None:
-        await cl.Message(content="Please upload files first before asking questions.").send()
+        await cl.Message(content="Please provide a ticker symbol first before asking questions.").send()
         return
 
     query_engine = index.as_query_engine()
@@ -151,4 +168,4 @@ async def main(message: cl.Message):
     for token in str(response):
         await response_message.stream_token(token=token)
     
-    await response_message.send()  
+    await response_message.send()