Create app.py

app.py

@@ -0,0 +1,78 @@
+import yfinance as yf
+import gradio as gr
+import llama_index as ll
+import chatgroq
+
+# Initialize Llama model (assuming you have a pre-trained model from llama)
+llama_model = ll.LlamaModel('your_llama_model_path')  # Replace with your Llama model path
+
+# Initialize Chatgroq (Configure accordingly based on your API or setup)
+chatgroq_model = chatgroq.ChatGroqModel('your_chatgroq_model_id')  # Replace with your Chatgroq ID
+
+# Function to fetch stock data from Yahoo Finance
+def get_stock_data(ticker):
+    stock = yf.Ticker(ticker)
+    stock_info = stock.info
+    stock_price = stock_info.get('currentPrice', 'N/A')
+    stock_name = stock_info.get('shortName', 'N/A')
+    stock_sector = stock_info.get('sector', 'N/A')
+    stock_pe_ratio = stock_info.get('trailingPE', 'N/A')
+    return {
+        'stock_name': stock_name,
+        'stock_price': stock_price,
+        'sector': stock_sector,
+        'pe_ratio': stock_pe_ratio
+    }
+
+# Llama-based reasoning function to respond as a stock analyst
+def generate_analysis(stock_data):
+    prompt = f"""
+    You are a stock market analyst. 
+    Here are the details of the stock:
+    Name: {stock_data['stock_name']}
+    Price: {stock_data['stock_price']}
+    Sector: {stock_data['sector']}
+    P/E Ratio: {stock_data['pe_ratio']}
+    
+    Analyze the stock performance and provide a brief summary and advice to the user.
+    """
+    response = llama_model.generate_response(prompt)
+    return response
+
+# Chatgroq-based reasoning to understand context and provide advice
+def generate_advice_based_on_context(stock_data, user_query):
+    context = f"The stock price of {stock_data['stock_name']} is {stock_data['stock_price']}."
+    advice_prompt = f"User wants to know about the stock performance. {context} {user_query}"
+    advice = chatgroq_model.get_advice(advice_prompt)
+    return advice
+
+# Gradio Interface function
+def stock_analysis(ticker, user_query=""):
+    stock_data = get_stock_data(ticker)
+    analysis = generate_analysis(stock_data)
+    
+    # Generate user-specific advice (if any query is provided)
+    if user_query:
+        advice = generate_advice_based_on_context(stock_data, user_query)
+        return stock_data, analysis, advice
+    
+    return stock_data, analysis
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=stock_analysis,
+    inputs=[
+        gr.Textbox(label="Stock Ticker", placeholder="Enter stock ticker (e.g., AAPL)"),
+        gr.Textbox(label="User Query", placeholder="Ask about the stock (optional)", optional=True)
+    ],
+    outputs=[
+        gr.JSON(label="Stock Data"),
+        gr.Textbox(label="Analysis"),
+        gr.Textbox(label="Advice", optional=True)
+    ],
+    live=True
+)
+
+# Run the Gradio app
+if __name__ == '__main__':
+    iface.launch()