app.py

import streamlit as st
import yfinance as yf
import requests
import pandas as pd
from langchain.agents import initialize_agent, AgentType
from langchain.tools import Tool
from langchain_huggingface import HuggingFacePipeline
import os
from dotenv import load_dotenv
from transformers import AutoModelForCausalLM, AutoTokenizer,pipeline
import torch

load_dotenv()
NEWSAPI_KEY = os.getenv("NEWSAPI_KEY")
access_token = os.getenv("API_KEY")

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token = access_token)
model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-2b-it",
    torch_dtype=torch.bfloat16,
    token = access_token
)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def validate_ticker(ticker):
    # Ensure ticker is uppercase and length is reasonable (1-5 characters)
    return ticker.strip().upper()


def fetch_stock_data(ticker):
    ticker = validate_ticker(ticker)  # Validate and clean input
    stock = yf.Ticker(ticker)
    hist = stock.history(period="1mo")
    return hist.tail(5)

def fetch_stock_news(ticker, NEWSAPI_KEY):
    api_url = f"https://newsapi.org/v2/everything?q={ticker}&apiKey={NEWSAPI_KEY}"
    response = requests.get(api_url)
    if response.status_code == 200:
        articles = response.json().get('articles', [])
        return [{"title": article['title'], "description": article['description']} for article in articles[:5]]
    else:
        return [{"error": "Unable to fetch news."}]

def calculate_moving_average(ticker, window=5):
    stock = yf.Ticker(ticker)
    hist = stock.history(period="1mo")
    hist[f"{window}-day MA"] = hist["Close"].rolling(window=window).mean()
    return hist[["Close", f"{window}-day MA"]].tail(5)

llm = HuggingFacePipeline(pipeline=pipe)

stock_data_tool = Tool(
    name="Stock Data Fetcher",
    func=fetch_stock_data,
    description="Fetch recent stock data for a valid stock ticker (e.g., AAPL for Apple)."
)

stock_news_tool = Tool(
    name="Stock News Fetcher",
    func=lambda ticker: fetch_stock_news(ticker, NEWSAPI_KEY),
    description="Fetch recent news articles about a stock ticker."
)

moving_average_tool = Tool(
    name="Moving Average Calculator",
    func=calculate_moving_average,
    description="Calculate the moving average of a stock over a 5-day window."
)

tools = [stock_data_tool, stock_news_tool, moving_average_tool]

agent = initialize_agent(
    tools=tools,
    llm=llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
    handle_parsing_errors=True  # Enables automatic handling of parsing issues
)

print(fetch_stock_data("AAPL"))
print(fetch_stock_news("AAPL", NEWSAPI_KEY))
print(calculate_moving_average("AAPL"))


st.title("Trading Helper Agent")

query = st.text_input("Enter your query:")

if st.button("Submit"):
    if query:
        st.write("Debug: User Query ->", query)
        with st.spinner("Processing..."):
            try:
                response = agent.run(query)
                st.write("Debug: Agent Response ->", response)
                st.success("Response:")
                st.write(response)
            except Exception as e:
                st.error(f"An error occurred: {e}")
                # Log the full LLM output for debugging
                if hasattr(e, "output"):
                    st.write("Raw Output:", e.output)
    else:
        st.warning("Please enter a query.")