Update app.py

app.py

@@ -1,83 +1,45 @@
 import yfinance as yf
 import gradio as gr
-import chatgroq  # Import Chatgroq API client
 from langchain.chains import LLMChain
-from langchain.memory import ConversationBufferMemory
 from langchain.prompts import PromptTemplate
+from langchain.llms import LlamaCpp
 
-# Initialize memory for conversation
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+# Define Llama model (you must provide the path to your Llama model)
+llama_model = LlamaCpp(model_path="path_to_your_llama_model.bin")
 
-# Define the prompt template for stock analysis
-prompt = """
-You are a stock market analyst. The user is asking for stock analysis.
-Here are the details of the stock:
-- Name: {stock_name}
-- Price: {stock_price}
-- Sector: {sector}
-- P/E Ratio: {pe_ratio}
+# Set up Langchain LLM
+llm_chain = LLMChain(llm=llama_model)
 
-Analyze the stock performance and provide a brief summary and advice to the user.
+# Define the prompt template for querying the LLM about stock details
+prompt_template = """
+You are a stock market assistant. Please provide detailed information about the stock.
+The stock symbol is: {stock_symbol}.
 """
-
-# 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
-    }
-
-# Function to generate stock analysis based on the conversation context
-def stock_analysis(ticker, user_query=""):
-    # Get API key from environment (no need to pass manually)
-    api_key = os.getenv("CHATGROQ_API_KEY")  # Ensure Hugging Face secret is set
+stock_prompt = PromptTemplate(input_variables=["stock_symbol"], template=prompt_template)
+
+# Function to get stock data from Yahoo Finance
+def get_stock_data(stock_symbol):
+    stock = yf.Ticker(stock_symbol)
+    stock_info = stock.info  # Get company info
+    stock_price = stock_info['currentPrice']  # Get current stock price
+    company_name = stock_info.get('shortName', 'N/A')
+    sector = stock_info.get('sector', 'N/A')
+    market_cap = stock_info.get('marketCap', 'N/A')
+
+    # Generate a response using Langchain LLM
+    stock_details = llm_chain.run(stock_prompt.format(stock_symbol=stock_symbol))
     
-    if not api_key:
-        return "API key is required for Chatgroq."
-
-    # Initialize Chatgroq model with the API key
-    chatgroq_model = chatgroq.ChatGroqModel(api_key)
+    return f"Company: {company_name}\nSector: {sector}\nMarket Cap: {market_cap}\nStock Price: ${stock_price}\n\nDetailed Information: {stock_details}"
 
-    # Set the stock data in the prompt template
-    stock_data = get_stock_data(ticker)
-    prompt_input = {
-        'stock_name': stock_data['stock_name'],
-        'stock_price': stock_data['stock_price'],
-        'sector': stock_data['sector'],
-        'pe_ratio': stock_data['pe_ratio']
-    }
-
-    # Create LLM chain with Chatgroq model and prompt
-    chain = LLMChain(llm=chatgroq_model, prompt=PromptTemplate.from_template(prompt), memory=memory)
-    
-    # Get analysis from Chatgroq-based agent
-    analysis = chain.run(input=prompt_input)
-    
-    # Generate advice if there is a user query
-    if user_query:
-        return stock_data, analysis + "\n" + "Advice: " + user_query
-    return stock_data, analysis
+# Gradio Interface
+def stock_market_agent(stock_symbol):
+    return get_stock_data(stock_symbol)
 
-# 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"),
-    ]
-)
+# Set up Gradio UI
+iface = gr.Interface(fn=stock_market_agent,
+                     inputs=gr.Textbox(label="Enter Stock Symbol (e.g., AAPL)"),
+                     outputs="text",
+                     title="Stock Market Agent",
+                     description="Get real-time stock prices and company information from Yahoo Finance.")
 
-if __name__ == '__main__':
-    iface.launch()
+iface.launch()