import streamlit as st import os import getpass from langchain import PromptTemplate from langchain import hub from langchain.docstore.document import Document from langchain.document_loaders import WebBaseLoader from langchain.schema import StrOutputParser from langchain.schema.prompt_template import format_document from langchain.schema.runnable import RunnablePassthrough import google.generativeai as genai from langchain_google_genai import GoogleGenerativeAIEmbeddings from langchain_google_genai import ChatGoogleGenerativeAI from langchain.chains.llm import LLMChain from langchain.chains import StuffDocumentsChain from langchain_core.messages import HumanMessage import requests from tradingview_ta import TA_Handler, Interval import yfinance as yf from datetime import datetime, timedelta from newsapi import NewsApiClient st.set_page_config(layout="wide") GOOGLE_API_KEY=os.environ['GOOGLE_API_KEY'] st.title('Stock Market Insights') st.sidebar.image("https://myndroot.com/wp-content/uploads/2023/12/Gemini-Dext.jpg",width =100) st.sidebar.markdown("The App uses **Google Gemini API** for Text and Vision along with 🦜️🔗 LangChain") st.sidebar.info("Know more about [NSE Tickers](https://www.google.com/search?q=nse+tickers+list&sca_esv=a6c39f4d03c5324c&sca_upv=1&rlz=1C1GCEB_enIN1011IN1011&sxsrf=ADLYWILQPbew-0SrvUUWpI8Y29_uOOgbvA%3A1716470016765&ei=AEFPZp-zLvzHp84P_ZWtuA0&oq=NSE+Tickers+&gs_lp=Egxnd3Mtd2l6LXNlcnAiDE5TRSBUaWNrZXJzICoCCAAyBRAAGIAEMggQABgWGAoYHjIGEAAYFhgeMgYQABgWGB4yBhAAGBYYHjIGEAAYFhgeMgYQABgWGB4yBhAAGBYYHjILEAAYgAQYhgMYigUyCxAAGIAEGIYDGIoFSIIbUL0PWL0PcAF4AZABAJgB8QKgAfECqgEDMy0xuAEByAEA-AEBmAICoAKKA8ICChAAGLADGNYEGEeYAwCIBgGQBgiSBwUxLjMtMaAHtQU&sclient=gws-wiz-serp)") st.sidebar.info("Know more about [Charts](https://chart-img.com/)") ticker_user = st.text_input("Enter Ticker for NSE Stocks","") gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001") llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro",google_api_key = GOOGLE_API_KEY) llm_vis = ChatGoogleGenerativeAI(model="gemini-pro-vision",google_api_key = GOOGLE_API_KEY) def get_tradingview_analysis(symbol, exchange, screener, interval): try: stock = TA_Handler( symbol=symbol, screener=screener, exchange=exchange, interval=interval, ) analysis_summary = stock.get_analysis() return analysis_summary except Exception as e: return {"error": str(e)} if ticker_user!="": url1 = f"https://www.google.com/finance/quote/{ticker_user}:NSE?hl=en" url2 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/" url3 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/news/" url4 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/minds/" loader = WebBaseLoader([url1,url2,url3,url4]) docs = loader.load() st.divider() # llm_prompt_template = """You are an expert Stock Market Trader for stock market insights based on fundamental, analytical, profit based and company financials. # Based on the context below # {context}, Summarize the stock based on Historical data based on fundamental, price, news, sentiment , any red flags and suggest rating of the Stock in a 1 to 10 Scale""" llm_prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, and detailed company financials. Using your expertise, please analyze the stock based on the provided context below. Context: {context} Task: Summarize the stock based on its historical and current data. Evaluate the stock on the following parameters: 1. Company Fundamentals: Assess the stock's intrinsic value, growth potential, and financial health. 2. Current & Future Price Trends: Analyze historical price movements and current price trends. 3. News and Sentiment: Review recent news articles, press releases, and social media sentiment. 4. Red Flags: Identify any potential risks or warning signs. 5. Provide a rating for the stock on a scale of 1 to 10. 6. Advise if the stock is a good buy for the next 2 weeks. 7. Suggest at what price we need to buy and hold or sell PROVIDE THE DETAILS based on just the FACTS present in the document PROVIDE THE DETAILS IN an JSON Object """ # st.sidebar.subheader('Prompt') # user_prompt = st.sidebar.text_area("Enter Prompt",llm_prompt_template) #https://huggingface.co/spaces/pradeepodela/Stock-Analyser/blob/main/app.py interval = Interval.INTERVAL_1_DAY analysis_summary = get_tradingview_analysis( symbol=ticker_user, exchange="NSE", screener="india", interval=interval, ) st.title("Analysis Summary") st.dataframe(analysis_summary.summary) query = f"{ticker_user} stock" details = { "symbol": ticker_user, "exchange": "NSE", "screener": "india", "interval": interval, } st.title("Details") st.dataframe(details) st.title("Oscillator Analysis") st.dataframe(analysis_summary.oscillators) st.title("Moving Averages") st.dataframe(analysis_summary.moving_averages) st.title("Summary") st.dataframe(analysis_summary.summary) st.title("Indicators") st.dataframe(analysis_summary.indicators) url = "https://api.chart-img.com/v2/tradingview/advanced-chart" api_key = "l0iUFRSeqC9z7nDPTd1hnafPh2RrdcEy6rl6tNqV" headers = { "x-api-key": api_key, "content-type": "application/json" } data = { "height": 400, "theme": "light", "interval": "1D", "session": "extended", "symbol": f"NSE:{ticker_user}" } response = requests.post(url, headers=headers, json=data) if response.status_code == 200: with open("chart_t1.jpg", "wb") as f: f.write(response.content) st.image("chart_t1.jpg", caption='') llm_prompt = PromptTemplate.from_template(llm_prompt_template) llm_chain = LLMChain(llm=llm,prompt=llm_prompt) stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="context") res = stuff_chain.invoke(docs) #create the humanmassage propmt templete with the image file # hmessage = HumanMessage( # content=[ # { # "type": "text", # "text": "Based on the Image, suggest a BUY and SELL Strategy along with Risk based approach using Stop loss/Target price. PROVIDE THE DETAILS based on just the FACTS present and PROVIDE THE DETAILS IN an JSON Object", # }, # {"type": "image_url", "image_url": "chart_t1.jpg"}, # ] # ) # message = llm_vis.invoke([hmessage]) # st.write(message.content) st.write(res["output_text"]) # print("Image saved as chart-img-02.png") else: st.warning(f"Failed to retrieve image. Status code: {response.status_code}") st.warning("Response:", response.text)