Update app.py

app.py

@@ -2,7 +2,6 @@ import os
 import gradio as gr
 import openai
 from langdetect import detect
-from fpdf import FPDF  # To generate PDF
 import json
 
 # Set up OpenAI API with your custom endpoint
@@ -85,27 +84,6 @@ def format_response(data):
 
     return formatted_response.strip()
 
-# Function to generate PDF based on investment data
-def generate_pdf(company_name, investment_data):
-    pdf = FPDF()
-    pdf.set_auto_page_break(auto=True, margin=15)
-    pdf.add_page()
-
-    # Title
-    pdf.set_font("Arial", 'B', 16)
-    pdf.cell(200, 10, f"Investment Report for {company_name}", ln=True, align="C")
-
-    # Adding investment data
-    pdf.set_font("Arial", size=12)
-    pdf.ln(10)
-    pdf.multi_cell(0, 10, f"Investment Data:\n\n{investment_data}")
-
-    # Save PDF to file
-    pdf_output = f"{company_name}_investment_report.pdf"
-    pdf.output(pdf_output)
-
-    return pdf_output
-
 # Function to handle the interaction and queries
 def market_analysis_agent(user_input, history=[]):
     try:
@@ -120,13 +98,7 @@ def market_analysis_agent(user_input, history=[]):
             return history, history
         
         # Handle private market queries with datasets
-        if "create a pdf" in user_input.lower() and "investment" in user_input.lower():
-            company_name = "Razorpay"  # Example; in real scenario, extract from user input
-            investment_data = "Investment data for Razorpay will go here."  # Replace with actual data retrieval logic
-            pdf_output = generate_pdf(company_name, investment_data)
-            return history, gr.File(pdf_output)  # Returning the generated PDF file
-
-        elif "company" in user_input.lower():
+        if "company" in user_input.lower():
             response = company_profile
         elif "financials" in user_input.lower():
             response = financials