import os import time import uuid from typing import List, Tuple, Optional, Dict, Union import google.generativeai as genai import gradio as gr from PIL import Image from langchain.chat_models import ChatOpenAI from langchain.prompts import ChatPromptTemplate from langchain.chains import LLMChain, SequentialChain from textwrap import dedent import google.generativeai as genai import yfinance as yf from pypfopt.discrete_allocation import DiscreteAllocation, get_latest_prices from pypfopt import EfficientFrontier from pypfopt import risk_models from pypfopt import expected_returns from pypfopt import plotting import copy import numpy as np import pandas as pd import plotly.express as px import matplotlib.pyplot as plt from datetime import datetime import datetime # Tool import from crewai.tools.gemini_tools import GeminiSearchTools from langchain.tools.yahoo_finance_news import YahooFinanceNewsTool from crewai.tools.browser_tools import BrowserTools from crewai.tools.sec_tools import SECTools # Google Langchain from langchain_google_genai import GoogleGenerativeAI #Crew imports from crewai import Agent, Task, Crew, Process # Retrieve API Key from Environment Variable GOOGLE_AI_STUDIO = os.environ.get('GOOGLE_API_KEY') # Ensure the API key is available if not GOOGLE_AI_STUDIO: raise ValueError("API key not found. Please set the GOOGLE_AI_STUDIO2 environment variable.") STEP1_TITLE = """

Custom GPT Portfolio Generator

""" STEP2_TITLE = """

Create a Financial OutLook Report of Your Portfolio

""" STEP3_TITLE = """

Optimize Your Portfolio to Maximize Return

""" portfolios_output = """ Creating a Conservative Portfolio Title: Steady and Secure: A Conservative Portfolio Approach Introduction: In the world of investments, a conservative portfolio is akin to a steady ship in turbulent seas. It's designed for those who seek stability over high risks, focusing on preserving capital and generating regular income. This approach is particularly appealing to retirees or those nearing retirement, who prioritize safeguarding their wealth over aggressive growth. Rational for Selection of Each Stock: Coca-Cola (KO): A classic example of stability and consistent dividend payout, Coca-Cola's global brand strength makes it a reliable choice for conservative investors. Procter & Gamble (PG): Known for its wide range of consumer products, PG offers consistent performance and a strong history of dividend payments. Johnson & Johnson (JNJ): A leader in healthcare, JNJ's diversified portfolio and strong financials offer low volatility and dependable dividends. Verizon Communications (VZ): As a telecom giant, Verizon provides essential services, ensuring steady demand and reliable dividends. Pfizer (PFE): A pharmaceutical stalwart, Pfizer offers a blend of stability and moderate growth, backed by a solid dividend history. McDonald's (MCD): A global fast-food leader, McDonald’s demonstrates resilient performance and steady dividends, even in economic downturns. Walmart (WMT): The retail giant's consistent performance and dividend history make it a stable choice for conservative portfolios. 3M (MMM): Known for its innovation and diversified product line, 3M offers stability and a long history of dividend growth. The Southern Company (SO): As a utility company, SO provides essential services, leading to consistent demand and steady dividends. Duke Energy (DUK): Another utility company, Duke Energy's focus on essential services ensures stable revenues and dividends. Conclusion: This conservative portfolio is built on the bedrock of stability, resilience, and regular income. It's tailored for investors who prioritize capital preservation and steady income over high-risk, high-reward strategies. Portfolio Tickers: KO, PG, JNJ, VZ, PFE, MCD, WMT, MMM, SO, DUK Creating a Growth Portfolio Title: Nurturing Wealth: A Growth-Oriented Portfolio Strategy Introduction: For the investor with an eye on the future and a stomach for some risk, a growth portfolio is the way to go. This strategy is ideal for those aiming for long-term capital appreciation. It typically includes stocks of companies with significant growth potential, such as those in technology, healthcare, and renewable energy sectors. Rational for Selection of Each Stock: Apple Inc. (AAPL): A leader in technology, Apple's continuous innovation and strong market presence make it a prime candidate for growth. Amazon.com Inc. (AMZN): With its ever-expanding business and dominance in e-commerce and cloud computing, Amazon is poised for sustained growth. Tesla Inc. (TSLA): At the forefront of the electric vehicle revolution, Tesla's growth potential in a transforming auto industry is substantial. NVIDIA Corporation (NVDA): A key player in the gaming and AI sectors, NVIDIA's cutting-edge technology positions it for strong growth. Alphabet Inc. (GOOGL): Google's parent company, with its diverse range of rapidly growing businesses, is a staple in any growth portfolio. Microsoft Corporation (MSFT): A tech giant with consistent growth in cloud computing and software, Microsoft is a robust choice for growth. Netflix, Inc. (NFLX): As a leader in streaming media, Netflix's ongoing global expansion and content creation suggest significant growth potential. Visa Inc. (V): With the increasing shift to digital payments, Visa's global network positions it well for growth in fintech. Mastercard Incorporated (MA): Similar to Visa, Mastercard's role in the growing digital payment sector offers strong growth prospects. Salesforce.com, Inc. (CRM): As a leader in cloud-based customer relationship management software, Salesforce is well-positioned for growth in the digital transformation of businesses. Conclusion: This growth portfolio is designed for the long-term investor who seeks capital appreciation and is comfortable with higher risk. It leverages the potential of market leaders and innovators across various sectors, setting the stage for significant growth over time. Portfolio Tickers: AAPL, AMZN, TSLA, NVDA, GOOGL, MSFT, NFLX, V, MA, CRM Creating a Balanced Portfolio Title: Harmonizing Growth and Stability: The Balanced Portfolio Introduction: A balanced portfolio is the middle ground in investment strategy, blending the growth potential of stocks with the stability of bonds and other income-generating assets. This approach aims to moderate risk while still offering opportunities for capital appreciation and income. It's well-suited for investors who desire a mix of growth and income with a moderate risk profile. Rational for Selection of Each Stock: Apple Inc. (AAPL): As a tech giant with a solid track record, Apple offers both growth potential and relative stability, a perfect fit for a balanced portfolio. JPMorgan Chase & Co. (JPM): A leading financial institution, JPMorgan brings stability and potential for capital appreciation, along with steady dividends. Johnson & Johnson (JNJ): A diversified healthcare company, JNJ offers stability and consistent dividends, making it a reliable choice for balanced investing. Procter & Gamble (PG): With a wide array of consumer products, PG is known for its stability and consistent dividend payouts. The Coca-Cola Company (KO): A global beverage leader, Coca-Cola provides steady income through dividends, along with potential for moderate growth. Microsoft Corporation (MSFT): A blend of growth and stability, Microsoft's strong financials and innovative edge make it a balanced choice. Pfizer Inc. (PFE): In the healthcare sector, Pfizer offers a combination of stability, dividend income, and potential growth. Verizon Communications Inc. (VZ): As a telecom giant, Verizon provides stable dividends and operates in a relatively stable industry. 3M Company (MMM): Known for its diversified industrial products, 3M offers a balance of stability and growth potential. Walmart Inc. (WMT): The retail giant's consistent performance and defensive nature in economic downturns make it a balanced choice. Conclusion: This balanced portfolio is carefully crafted to provide a blend of stability and growth. It's an ideal choice for investors seeking a diversified approach, with a mix of reliable income and potential for capital appreciation. Portfolio Tickers: AAPL, JPM, JNJ, PG, KO, MSFT, PFE, VZ, MMM, WMT Creating an Aggressive Portfolio Title: Pursuit of High Returns: An Aggressive Portfolio Strategy Introduction: The aggressive portfolio is designed for the investor who is willing to embrace high risk in pursuit of high returns. This strategy often involves investing in high-growth stocks, emerging market securities, and innovative sectors. It's most suitable for investors with a long-term horizon and a high tolerance for market volatility. Rational for Selection of Each Stock: Tesla, Inc. (TSLA): A leader in the electric vehicle industry, Tesla represents high growth potential in the evolving automotive sector. Amazon.com, Inc. (AMZN): Amazon's continuous expansion into new markets and technologies positions it for aggressive growth. NVIDIA Corporation (NVDA): With its leading role in AI and gaming, NVIDIA is poised for significant growth in high-tech sectors. Alphabet Inc. (GOOGL): The parent company of Google, Alphabet has diverse and rapidly growing business segments, making it a strong candidate for aggressive growth. Shopify Inc. (SHOP): As an e-commerce platform, Shopify has high growth potential in the expanding online retail space. Square, Inc. (SQ): Operating in the fintech space, Square's innovative payment solutions position it for aggressive growth. Moderna, Inc. (MRNA): A biotech company with a focus on mRNA technology, Moderna has high growth potential in the healthcare sector. Zoom Video Communications, Inc. (ZM): A leader in remote communication solutions, Zoom has the potential for aggressive growth in the evolving workplace. Snowflake Inc. (SNOW): A cloud computing company, Snowflake's innovative data platform positions it for high growth in the tech sector. Peloton Interactive, Inc. (PTON): In the fitness technology space, Peloton's innovative business model offers high growth potential. Conclusion: This aggressive portfolio is tailored for those seeking exponential growth and who are comfortable with high levels of risk. It leverages the potential of companies in rapidly growing industries and innovative sectors, making it suitable for long-term, risk-tolerant investors. Portfolio Tickers: TSLA, AMZN, NVDA, GOOGL, SHOP, SQ, MRNA, ZM, SNOW, PTON Summary of Portfolio Strategies Overview: In this comprehensive investment guide, we explored four distinct portfolio strategies, each tailored to different investor profiles and risk tolerances. From the steady and secure conservative approach to the high-risk, high-reward aggressive strategy, these portfolios offer a range of options for investors with varying objectives and time horizons. Summary of Each Portfolio: Conservative Portfolio: Focused on stability and income generation, this portfolio includes stocks like KO, PG, and JNJ. Ideal for risk-averse investors, especially those nearing retirement, it emphasizes capital preservation and steady dividend income. Growth Portfolio: Targeting long-term capital appreciation, this portfolio features companies like AAPL, AMZN, and TSLA. Suited for investors with a longer horizon and higher risk tolerance, it focuses on stocks with significant growth potential. Balanced Portfolio: Aiming for a middle-ground approach, this portfolio includes a mix of stable and growth-oriented stocks like AAPL, JPM, and MSFT. It's designed for investors seeking both income and moderate capital appreciation, with a diversified risk profile. Aggressive Portfolio: Geared towards maximum growth, this strategy includes high-growth stocks like TSLA, NVDA, and GOOGL. Suitable for investors with a high risk tolerance and a long-term investment horizon, it focuses on sectors with high potential for rapid growth. Conclusion: These tailored portfolios offer a range of investment strategies to suit different investor needs. Whether prioritizing income and stability or seeking aggressive growth, each portfolio is constructed with a specific investment goal and risk tolerance in mind. """ # LangChain function for company analysis # For furture upgrade def company_analysis(api_key: str, company_name: str) -> dict: os.environ['OPENAI_API_KEY'] = api_key # Set the OpenAI API key as an environment variable llm = ChatOpenAI() ''' # Identify the email's language template1 = "Return the language this email is written in:\n{email}.\nONLY return the language it was written in." prompt1 = ChatPromptTemplate.from_template(template1) chain_1 = LLMChain(llm=llm, prompt=prompt1, output_key="language") # Translate the email to English template2 = "Translate this email from {language} to English. Here is the email:\n" + email prompt2 = ChatPromptTemplate.from_template(template2) chain_2 = LLMChain(llm=llm, prompt=prompt2, output_key="translated_email") # Provide a summary in English template3 = "Create a short summary of this email:\n{translated_email}" prompt3 = ChatPromptTemplate.from_template(template3) chain_3 = LLMChain(llm=llm, prompt=prompt3, output_key="summary") # Provide a reply in English template4 = "Reply to the sender of the email giving a plausible reply based on the {summary} and a promise to address issues" prompt4 = ChatPromptTemplate.from_template(template4) chain_4 = LLMChain(llm=llm, prompt=prompt4, output_key="reply") # Provide a translation back to the original language template5 = "Translate the {reply} back to the original {language} of the email." prompt5 = ChatPromptTemplate.from_template(template5) chain_5 = LLMChain(llm=llm, prompt=prompt5, output_key="translated_reply") seq_chain = SequentialChain(chains=[chain_1, chain_2, chain_3, chain_4, chain_5], input_variables=['email'], output_variables=['language', 'translated_email', 'summary', 'reply', 'translated_reply'], verbose=True) ''' return seq_chain(email) print("google-generativeai:", genai.__version__) GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY") TITLE1 = """

Company Analysis

""" TITLE2 = """

Investment Strategy

""" TITLE3 = """

Profit Prophet

""" SUBTITLE = """

Strategy Agent built with Gemini Pro and Gemini Pro Vision API

""" GETKEY = """
Get an API key GOOGLE API KEY.
""" AVATAR_IMAGES = ( None, "https://media.roboflow.com/spaces/gemini-icon.png" ) movie_script_analysis = "" IMAGE_CACHE_DIRECTORY = "/tmp" IMAGE_WIDTH = 512 CHAT_HISTORY = List[Tuple[Optional[Union[Tuple[str], str]], Optional[str]]] def preprocess_stop_sequences(stop_sequences: str) -> Optional[List[str]]: if not stop_sequences: return None return [sequence.strip() for sequence in stop_sequences.split(",")] def preprocess_image(image: Image.Image) -> Optional[Image.Image]: image_height = int(image.height * IMAGE_WIDTH / image.width) return image.resize((IMAGE_WIDTH, image_height)) def cache_pil_image(image: Image.Image) -> str: image_filename = f"{uuid.uuid4()}.jpeg" os.makedirs(IMAGE_CACHE_DIRECTORY, exist_ok=True) image_path = os.path.join(IMAGE_CACHE_DIRECTORY, image_filename) image.save(image_path, "JPEG") return image_path def preprocess_chat_history( history: CHAT_HISTORY ) -> List[Dict[str, Union[str, List[str]]]]: messages = [] for user_message, model_message in history: if isinstance(user_message, tuple): pass elif user_message is not None: messages.append({'role': 'user', 'parts': [user_message]}) if model_message is not None: messages.append({'role': 'model', 'parts': [model_message]}) return messages def upload(files: Optional[List[str]], chatbot: CHAT_HISTORY) -> CHAT_HISTORY: for file in files: image = Image.open(file).convert('RGB') image = preprocess_image(image) image_path = cache_pil_image(image) chatbot.append(((image_path,), None)) return chatbot def user(text_prompt: str, chatbot: CHAT_HISTORY): if text_prompt: chatbot.append((text_prompt, None)) return "", chatbot def bot( google_key: str, files: Optional[List[str]], temperature: float, max_output_tokens: int, stop_sequences: str, top_k: int, top_p: float, chatbot: CHAT_HISTORY ): if len(chatbot) == 0: return chatbot google_key = google_key if google_key else GOOGLE_API_KEY if not google_key: raise ValueError( "GOOGLE_API_KEY is not set. " "Please follow the instructions in the README to set it up.") genai.configure(api_key=google_key) generation_config = genai.types.GenerationConfig( temperature=temperature, max_output_tokens=max_output_tokens, stop_sequences=preprocess_stop_sequences(stop_sequences=stop_sequences), top_k=top_k, top_p=top_p) if files: text_prompt = [chatbot[-1][0]] \ if chatbot[-1][0] and isinstance(chatbot[-1][0], str) \ else [] image_prompt = [Image.open(file).convert('RGB') for file in files] model = genai.GenerativeModel('gemini-pro-vision') response = model.generate_content( text_prompt + image_prompt, stream=True, generation_config=generation_config) else: messages = preprocess_chat_history(chatbot) model = genai.GenerativeModel('gemini-pro') response = model.generate_content( messages, stream=True, generation_config=generation_config) # streaming effect chatbot[-1][1] = "" for chunk in response: for i in range(0, len(chunk.text), 10): section = chunk.text[i:i + 10] chatbot[-1][1] += section time.sleep(0.01) yield chatbot google_key_component = gr.Textbox( label="GOOGLE API KEY", value="", type="password", placeholder="...", info="You have to provide your own GOOGLE_API_KEY for this app to function properly", visible=GOOGLE_API_KEY is None ) chatbot_component = gr.Chatbot( label='Gemini Pro Vision', bubble_full_width=False, avatar_images=AVATAR_IMAGES, scale=2, height=400 ) text_prompt_component = gr.Textbox(value=movie_script_analysis, show_label=False, autofocus=True, scale=8, lines=8 ) upload_button_component = gr.UploadButton( label="Upload Images", file_count="multiple", file_types=["image"], scale=1 ) run_button_component = gr.Button(value="Run", variant="primary", scale=1) run_button_analysis = gr.Button(value="Run", variant="primary", scale=1) temperature_component = gr.Slider( minimum=0, maximum=1.0, value=0.4, step=0.05, label="Temperature", info=( "Temperature controls the degree of randomness in token selection. Lower " "temperatures are good for prompts that expect a true or correct response, " "while higher temperatures can lead to more diverse or unexpected results. " )) max_output_tokens_component = gr.Slider( minimum=1, maximum=2048, value=1024, step=1, label="Token limit", info=( "Token limit determines the maximum amount of text output from one prompt. A " "token is approximately four characters. The default value is 2048." )) stop_sequences_component = gr.Textbox( label="Add stop sequence", value="", type="text", placeholder="STOP, END", info=( "A stop sequence is a series of characters (including spaces) that stops " "response generation if the model encounters it. The sequence is not included " "as part of the response. You can add up to five stop sequences." )) top_k_component = gr.Slider( minimum=1, maximum=40, value=32, step=1, label="Top-K", info=( "Top-k changes how the model selects tokens for output. A top-k of 1 means the " "selected token is the most probable among all tokens in the model’s " "vocabulary (also called greedy decoding), while a top-k of 3 means that the " "next token is selected from among the 3 most probable tokens (using " "temperature)." )) top_p_component = gr.Slider( minimum=0, maximum=1, value=1, step=0.01, label="Top-P", info=( "Top-p changes how the model selects tokens for output. Tokens are selected " "from most probable to least until the sum of their probabilities equals the " "top-p value. For example, if tokens A, B, and C have a probability of .3, .2, " "and .1 and the top-p value is .5, then the model will select either A or B as " "the next token (using temperature). " )) user_inputs = [ text_prompt_component, chatbot_component ] bot_inputs = [ google_key_component, upload_button_component, temperature_component, max_output_tokens_component, stop_sequences_component, top_k_component, top_p_component, chatbot_component ] # Gmix ++++++++++++++++++++++++++++++++++++++++++++++++ #Crew imports from crewai import Agent, Task, Crew, Process # Set gemini_llm gemini_llm = GoogleGenerativeAI(model="gemini-pro", google_api_key=GOOGLE_AI_STUDIO) def crewai_process(research_topic): # Define your agents with roles and goals researcher = Agent( role='Senior Research Analyst', goal=f'Uncover cutting-edge developments in {research_topic}', backstory="""You are a Senior Research Analyst at a leading think tank. Your expertise lies in identifying emerging trends. You have a knack for dissecting complex data and presenting actionable insights.""", verbose=True, allow_delegation=False, llm = gemini_llm, tools=[ GeminiSearchTools.gemini_search ] ) writer = Agent( role='Tech Content Strategist', goal='Craft compelling content on tech advancements', backstory="""You are a renowned Tech Social Media Content Writer and Strategist, known for your insightful and engaging articles on technology and innovation. With a deep understanding of the tech industry and how people are impacted by it, you transform complex concepts into compelling narratives.""", verbose=True, allow_delegation=True, llm = gemini_llm # Add tools and other optional parameters as needed ) # Create tasks for your agents task1 = Task( description=f"""Conduct a comprehensive analysis of the latest advancements in {research_topic}. Compile your findings in a detailed report. Your final answer MUST be a full analysis report""", agent=researcher ) task2 = Task( description="""Using the insights from the researcher's report, develop an engaging blog post that highlights the most significant advancements. Your post should be informative yet accessible, catering to a tech-savvy audience. Aim for a narrative that captures the essence of these breakthroughs and their implications for the future. Your final answer MUST be the full blog post of at least 3 paragraphs.""", agent=writer ) # Instantiate your crew with a sequential process crew = Crew( agents=[researcher, writer], tasks=[task1, task2], verbose=2, process=Process.sequential ) # Get your crew to work! result = crew.kickoff() return result # Portfolio Analysis +++++++++++++++++++++++++++++++++++ def plot_cum_returns(data, title): daily_cum_returns = 1 + data.dropna().pct_change() daily_cum_returns = daily_cum_returns.cumprod()*100 fig = px.line(daily_cum_returns, title=title) return fig def plot_efficient_frontier_and_max_sharpe(mu, S): # Optimize portfolio for max Sharpe ratio and plot it out with efficient frontier curve ef = EfficientFrontier(mu, S) fig, ax = plt.subplots(figsize=(6,4)) ef_max_sharpe = copy.deepcopy(ef) plotting.plot_efficient_frontier(ef, ax=ax, show_assets=False) # Find the max sharpe portfolio ef_max_sharpe.max_sharpe(risk_free_rate=0.02) ret_tangent, std_tangent, _ = ef_max_sharpe.portfolio_performance() ax.scatter(std_tangent, ret_tangent, marker="*", s=100, c="r", label="Max Sharpe") # Generate random portfolios with random weights n_samples = 1000 w = np.random.dirichlet(np.ones(ef.n_assets), n_samples) rets = w.dot(ef.expected_returns) stds = np.sqrt(np.diag(w @ ef.cov_matrix @ w.T)) sharpes = rets / stds ax.scatter(stds, rets, marker=".", c=sharpes, cmap="viridis_r") # Output ax.legend() return fig def output_results(start_date, end_date, tickers_string): tickers = tickers_string.split(',') # Get Stock Prices stocks_df = yf.download(tickers, start=start_date, end=end_date)['Adj Close'] # Plot Individual Stock Prices fig_indiv_prices = px.line(stocks_df, title='Price of Individual Stocks') # Plot Individual Cumulative Returns fig_cum_returns = plot_cum_returns(stocks_df, 'Cumulative Returns of Individual Stocks Starting with $100') # Calculatge and Plot Correlation Matrix between Stocks corr_df = stocks_df.corr().round(2) fig_corr = px.imshow(corr_df, text_auto=True, title = 'Correlation between Stocks') # Calculate expected returns and sample covariance matrix for portfolio optimization later mu = expected_returns.mean_historical_return(stocks_df) S = risk_models.sample_cov(stocks_df) # Plot efficient frontier curve fig_efficient_frontier = plot_efficient_frontier_and_max_sharpe(mu, S) # Get optimized weights ef = EfficientFrontier(mu, S) ef.max_sharpe(risk_free_rate=0.04) weights = ef.clean_weights() expected_annual_return, annual_volatility, sharpe_ratio = ef.portfolio_performance() expected_annual_return, annual_volatility, sharpe_ratio = '{}%'.format((expected_annual_return*100).round(2)), \ '{}%'.format((annual_volatility*100).round(2)), \ '{}%'.format((sharpe_ratio*100).round(2)) weights_df = pd.DataFrame.from_dict(weights, orient = 'index') weights_df = weights_df.reset_index() weights_df.columns = ['Tickers', 'Weights'] # Calculate returns of portfolio with optimized weights stocks_df['Optimized Portfolio'] = 0 for ticker, weight in weights.items(): stocks_df['Optimized Portfolio'] += stocks_df[ticker]*weight # Plot Cumulative Returns of Optimized Portfolio fig_cum_returns_optimized = plot_cum_returns(stocks_df['Optimized Portfolio'], 'Cumulative Returns of Optimized Portfolio Starting with $100') return fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns ticker_string_conservative = gr.Textbox("KO,PG,JNJ,VZ,PFE,MCD,WMT,MMM,SO,DUK") ticker_string_growth = gr.Textbox("AAPL,AMZN,TSLA,NVDA,GOOGL,MSFT,NFLX,V,MA,CRM") ticker_string_balanced = gr.Textbox("AAPL,JPM,JNJ,PG,KO,MSFT,PFE,VZ,MMM,WMT") ticker_string_agressive = gr.Textbox("TSLA,AMZN,NVDA,GOOGL,SHOP,SQ,MRNA,ZM,SNOW,PTON") # Interface ============================================= with gr.Blocks() as demo: with gr.Tab("Step 1: Portfolio Generator"): gr.HTML(STEP1_TITLE) with gr.Row(): with gr.Column(scale=1): gr.Image(value="resources/robot1.jpg") with gr.Column(scale=5): gr.Textbox(value = portfolios_output, label="Generated Portfolios Example (Conservative, Growth, Balanced, & Agressive)", lines=40, interactive=False ) with gr.Tab("Step 2: Optimize Portfolio"): gr.HTML(STEP3_TITLE) with gr.Blocks() as app: with gr.Row(): start_date = gr.Textbox("2013-01-01", label="Start Date") end_date = gr.Textbox(datetime.datetime.now().date(), label="End Date") with gr.Row(): gr.HTML("

Suggested Portfolios (Adjust as Needed)

") with gr.Row(): btn1 = gr.Button("Conservative") ticker_string_conservative = gr.Textbox("KO,PG,JNJ,VZ,PFE,MCD,WMT,MMM,SO,DUK", label='Conservative') btn2 = gr.Button("Growth") ticker_string_growth = gr.Textbox("AAPL,AMZN,TSLA,NVDA,GOOGL,MSFT,NFLX,V,MA,CRM", label='Growth') with gr.Row(): btn3 = gr.Button("Balanced") ticker_string_balanced = gr.Textbox("AAPL,JPM,JNJ,PG,KO,MSFT,PFE,VZ,MMM,WMT", label='Balanced') btn4 = gr.Button("Agressive") ticker_string_agressive = gr.Textbox("TSLA,AMZN,NVDA,GOOGL,SHOP,SQ,MRNA,ZM,SNOW,PTON", label='Agressive') ''' with gr.Row(): gr.HTML("

Adjusted Portfolio

") with gr.Row(): ticker_string = gr.Textbox("AAPL,AMZN,TSLA,NVDA,GOOGL,MSFT,NFLX,V,MA,CRM", label='Adjusted') with gr.Row(): btn = gr.Button("Get Optimized Portfolio") ''' with gr.Row(): gr.HTML("

Optimizied Portfolio Metrics

") with gr.Row(): expected_annual_return = gr.Text(label="Expected Annual Return") annual_volatility = gr.Text(label="Annual Volatility") sharpe_ratio = gr.Text(label="Sharpe Ratio") ''' btn.click(fn=output_results, inputs=[start_date, end_date, ticker_string], outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) ''' btn1.click(fn=output_results, inputs=[start_date, end_date, ticker_string_conservative], outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) btn2.click(fn=output_results, inputs=[start_date, end_date, ticker_string_growth], outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) btn3.click(fn=output_results, inputs=[start_date, end_date, ticker_string_balanced], outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) btn4.click(fn=output_results, inputs=[start_date, end_date, ticker_string_agressive], outputs=[fig_cum_returns_optimized, weights_df, fig_efficient_frontier, fig_corr, \ expected_annual_return, annual_volatility, sharpe_ratio, fig_indiv_prices, fig_cum_returns]) with gr.Tab("Step 3: Portfolio Analysis"): gr.HTML(STEP2_TITLE) run_button_crewai = gr.Button(value="Run", variant="primary", scale=1) run_button_crewai.click( fn=crewai_process, inputs=gr.Textbox(lines=2, placeholder="Enter Research Topic Here..."), outputs=gr.Textbox(label="Portfolio Analysis") ) with gr.Row(): fig_cum_returns_optimized = gr.Plot(label="Cumulative Returns of Optimized Portfolio (Starting Price of $100)") weights_df = gr.DataFrame(label="Optimized Weights of Each Ticker") with gr.Row(): fig_efficient_frontier = gr.Plot(label="Efficient Frontier") fig_corr = gr.Plot(label="Correlation between Stocks") with gr.Row(): fig_indiv_prices = gr.Plot(label="Price of Individual Stocks") fig_cum_returns = gr.Plot(label="Cumulative Returns of Individual Stocks Starting with $100") # For future upgrade ''' with gr.Tab("Company Analysis"): gr.HTML(TITLE1) run_button_analysis.click( fn=company_analysis, inputs=[ gr.Textbox(label="Enter your OpenAI API Key:", type="password"), gr.Textbox(label="Enter the Company Name:") ], outputs=[ gr.Textbox(label="Language"), gr.Textbox(label="Summary"), gr.Textbox(label="Translated Email"), gr.Textbox(label="Reply in English"), gr.Textbox(label="Reply in Original Language") ] ) with gr.Tab("Investment Strategy"): gr.HTML(TITLE2) gr.HTML(SUBTITLE) gr.HTML(GETKEY) with gr.Column(): google_key_component.render() chatbot_component.render() with gr.Row(): text_prompt_component.render() upload_button_component.render() run_button_component.render() with gr.Accordion("Parameters", open=False): temperature_component.render() max_output_tokens_component.render() stop_sequences_component.render() with gr.Accordion("Advanced", open=False): top_k_component.render() top_p_component.render() run_button_component.click( fn=user, inputs=user_inputs, outputs=[text_prompt_component, chatbot_component], queue=False ).then( fn=bot, inputs=bot_inputs, outputs=[chatbot_component], ) text_prompt_component.submit( fn=user, inputs=user_inputs, outputs=[text_prompt_component, chatbot_component], queue=False ).then( fn=bot, inputs=bot_inputs, outputs=[chatbot_component], ) upload_button_component.upload( fn=upload, inputs=[upload_button_component, chatbot_component], outputs=[chatbot_component], queue=False ) with gr.Tab("Profit Prophet"): gr.HTML(TITLE3) with gr.Row(): with gr.Column(scale=1): gr.Image(value = "resources/holder.png") with gr.Column(scale=1): gr.Image(value = "resources/holder.png") ''' demo.queue(max_size=99).launch(debug=False, show_error=True)