{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4a797514-61dc-4914-9d12-ce5c1a5287d9",
   "metadata": {},
   "source": [
    "# Function Calling with Llama 3 and LangChain"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4718a993-d052-4289-8b79-bb89f7b99023",
   "metadata": {},
   "source": [
    "The tech world is abuzz with the release of [Meta's Llama 3](https://llama.meta.com/llama3/), and Groq is excited to serve this powerful model at industry-leading speeds! Llama 3 [excels at function calling](https://twitter.com/RickLamers/status/1781444639079145722), making it an ideal choice for any function calling application. This cookbook will guide you through using Llama 3 in conjunction with [Groq's LangChain integration](https://python.langchain.com/docs/integrations/chat/groq/) to leverage Yahoo Finance's [yfinance API](https://pypi.org/project/yfinance/) for real-time stock market analysis. We'll demonstrate how to write functions to call the yfinance API from a user prompt, enabling the LLM to provide relevant, real-time information on the stock market, answering a range of questions from users"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "48234f2c-e41a-4c6c-a268-351d0d944682",
   "metadata": {},
   "source": [
    "### Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6e0fb2e5-db54-402d-a4fd-78239495f406",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_groq import ChatGroq\n",
    "import os\n",
    "import yfinance as yf\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9394c9a-0a8a-4882-81bd-76ea5f657f82",
   "metadata": {},
   "source": [
    "As mentioned in the introduction, we will be using Meta's Llama 3-70B model for function calling in this notebook. We are also using LangChain's ```ChatGroq``` function to define our LLM and integrate it with additional LangChain tooling. Note that you will need a Groq API Key to proceed and can create an account [here](https://console.groq.com/) to generate one for free."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c25157c7-2162-44f7-be8c-4f03d630f580",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = ChatGroq(groq_api_key = os.getenv('GROQ_API_KEY'),model = 'llama3-70b-8192')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0c91d792-cc1c-4956-9c18-3d44d1089e62",
   "metadata": {},
   "source": [
    "### Defining Tools"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ecba8a3e-6590-415f-a9ea-d14ac77f9e99",
   "metadata": {},
   "source": [
    "Now we will define two [LangChain tools](https://python.langchain.com/docs/modules/tools/) that leverage the yfinance API to answer user queries. Our goal is to enable the LLM to provide accurate and timely information on any stock, just like you'd get on [Yahoo Finance](https://finance.yahoo.com/quote/META/). We'll focus on two types of information: current data, such as price, volume, and beta, and historical prices. To achieve this, we'll create two tools: ```get_stock_info``` for current information and ```get_historical_price``` for historical prices."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0ec46bf-1374-4bf8-94e9-b450e2422e2d",
   "metadata": {},
   "source": [
    "Each tool includes a detailed description that helps the LLM determine which tool to use and which parameters to use. In ```get_stock_info```, we list all the keys available in data.info to ensure that Llama 3 selects the correct key verbatim. In ```get_historical_price```, we explicitly explain the purpose of start_date and end_date and provide guidance on how to fill them. In both functions, we've found that Llama 3 is capable of identifying the correct stock symbol given a company name without additional prompting."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7e5f4446-df38-4938-8ad0-1a54374c158a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.tools import tool\n",
    "\n",
    "@tool\n",
    "def get_stock_info(symbol, key):\n",
    "    '''Return the correct stock info value given the appropriate symbol and key. Infer valid key from the user prompt; it must be one of the following:\n",
    "\n",
    "    address1, city, state, zip, country, phone, website, industry, industryKey, industryDisp, sector, sectorKey, sectorDisp, longBusinessSummary, fullTimeEmployees, companyOfficers, auditRisk, boardRisk, compensationRisk, shareHolderRightsRisk, overallRisk, governanceEpochDate, compensationAsOfEpochDate, maxAge, priceHint, previousClose, open, dayLow, dayHigh, regularMarketPreviousClose, regularMarketOpen, regularMarketDayLow, regularMarketDayHigh, dividendRate, dividendYield, exDividendDate, beta, trailingPE, forwardPE, volume, regularMarketVolume, averageVolume, averageVolume10days, averageDailyVolume10Day, bid, ask, bidSize, askSize, marketCap, fiftyTwoWeekLow, fiftyTwoWeekHigh, priceToSalesTrailing12Months, fiftyDayAverage, twoHundredDayAverage, currency, enterpriseValue, profitMargins, floatShares, sharesOutstanding, sharesShort, sharesShortPriorMonth, sharesShortPreviousMonthDate, dateShortInterest, sharesPercentSharesOut, heldPercentInsiders, heldPercentInstitutions, shortRatio, shortPercentOfFloat, impliedSharesOutstanding, bookValue, priceToBook, lastFiscalYearEnd, nextFiscalYearEnd, mostRecentQuarter, earningsQuarterlyGrowth, netIncomeToCommon, trailingEps, forwardEps, pegRatio, enterpriseToRevenue, enterpriseToEbitda, 52WeekChange, SandP52WeekChange, lastDividendValue, lastDividendDate, exchange, quoteType, symbol, underlyingSymbol, shortName, longName, firstTradeDateEpochUtc, timeZoneFullName, timeZoneShortName, uuid, messageBoardId, gmtOffSetMilliseconds, currentPrice, targetHighPrice, targetLowPrice, targetMeanPrice, targetMedianPrice, recommendationMean, recommendationKey, numberOfAnalystOpinions, totalCash, totalCashPerShare, ebitda, totalDebt, quickRatio, currentRatio, totalRevenue, debtToEquity, revenuePerShare, returnOnAssets, returnOnEquity, freeCashflow, operatingCashflow, earningsGrowth, revenueGrowth, grossMargins, ebitdaMargins, operatingMargins, financialCurrency, trailingPegRatio\n",
    "    \n",
    "    If asked generically for 'stock price', use currentPrice\n",
    "    '''\n",
    "    data = yf.Ticker(symbol)\n",
    "    stock_info = data.info\n",
    "    return stock_info[key]\n",
    "\n",
    "\n",
    "@tool\n",
    "def get_historical_price(symbol, start_date, end_date):\n",
    "    \"\"\"\n",
    "    Fetches historical stock prices for a given symbol from 'start_date' to 'end_date'.\n",
    "    - symbol (str): Stock ticker symbol.\n",
    "    - end_date (date): Typically today unless a specific end date is provided. End date MUST be greater than start date\n",
    "    - start_date (date): Set explicitly, or calculated as 'end_date - date interval' (for example, if prompted 'over the past 6 months', date interval = 6 months so start_date would be 6 months earlier than today's date). Default to '1900-01-01' if vaguely asked for historical price. Start date must always be before the current date\n",
    "    \"\"\"\n",
    "\n",
    "    data = yf.Ticker(symbol)\n",
    "    hist = data.history(start=start_date, end=end_date)\n",
    "    hist = hist.reset_index()\n",
    "    hist[symbol] = hist['Close']\n",
    "    return hist[['Date', symbol]]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "077ba232-8485-4172-9291-ac4d592aec32",
   "metadata": {},
   "source": [
    "### Using our Tools"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b95ae71-cae9-49fb-8a0b-66385b79d9de",
   "metadata": {},
   "source": [
    "Now we will chain our tools together and bind them with our LLM so that they can be accessed:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7f062ce7-e23d-42b3-b9d6-493adb0c7bf1",
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = [get_stock_info, get_historical_price]\n",
    "llm_with_tools = llm.bind_tools(tools)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "53d8c970-cea9-42ec-8b52-50462dd48218",
   "metadata": {},
   "source": [
    "Let's test our function calling with a few simple prompts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8b5d16d2-6b5f-489d-b0d0-f62d65aee0b0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[{'name': 'get_stock_info', 'args': {'symbol': 'META', 'key': 'marketCap'}, 'id': 'call_3xm9'}]\n",
      "[{'name': 'get_stock_info', 'args': {'symbol': 'AAPL', 'key': 'volume'}, 'id': 'call_2p2z'}, {'name': 'get_stock_info', 'args': {'symbol': 'MSFT', 'key': 'volume'}, 'id': 'call_hvp4'}]\n"
     ]
    }
   ],
   "source": [
    "query1 = 'What is the market cap of Meta?'\n",
    "query2 = 'How does the volume of Apple compare to that of Microsoft?'\n",
    "\n",
    "print(llm_with_tools.invoke(query1).tool_calls)\n",
    "print(llm_with_tools.invoke(query2).tool_calls)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58a44315-b9d0-435b-a13d-369cef12aa4b",
   "metadata": {},
   "source": [
    "As you can see, in our first query we successfully called ```get_stock_info``` with parameters **META** and **marketCap**, which are valid stock symbols and keys, respectively. In our second query, the LLM correctly called ```get_stock_info``` twice for Apple and Microsoft."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "be4d79d9-6a4e-4b7e-9cca-1f3a21b5355e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[{'name': 'get_historical_price', 'args': {'symbol': '^GSPC', 'start_date': '2021-04-23', 'end_date': '2024-04-23'}, 'id': 'call_k06n'}]\n",
      "[{'name': 'get_historical_price', 'args': {'symbol': 'GOOGL', 'start_date': '2023-01-01', 'end_date': '2023-12-31'}, 'id': 'call_ca9y'}, {'name': 'get_historical_price', 'args': {'symbol': 'AMZN', 'start_date': '2023-01-01', 'end_date': '2023-12-31'}, 'id': 'call_h6q6'}]\n"
     ]
    }
   ],
   "source": [
    "query1 = 'Show the historical price of the S&P 500 over the past 3 years? (Today is 4/23/2024)'\n",
    "query2 = 'Compare the price of Google and Amazon throughout 2023'\n",
    "\n",
    "print(llm_with_tools.invoke(query1).tool_calls)\n",
    "print(llm_with_tools.invoke(query2).tool_calls)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ead6b037-6dad-4781-bb38-8214fa831233",
   "metadata": {},
   "source": [
    "Our tool calling LLM also correctly identified ```get_historical_price``` for historical price questions, and appropriately called it twice. Note that to perform any kind of lookback analysis, you'll need to provide the current date."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "104f013a-0279-4ead-bcec-db7cd23eecd3",
   "metadata": {},
   "source": [
    "### Putting it all together"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e7fb035-4332-4be2-a333-91cca36e8696",
   "metadata": {},
   "source": [
    "This function, ```plot_price_over_time```, is not called by the LLM but will plot historical price over time if ```get_historical_price``` is called:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ba207220-8e67-4799-bd32-576cd783132b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import plotly.graph_objects as go\n",
    "\n",
    "def plot_price_over_time(historical_price_dfs):\n",
    "\n",
    "    full_df = pd.DataFrame(columns = ['Date'])\n",
    "    for df in historical_price_dfs:\n",
    "        full_df = full_df.merge(df, on = 'Date', how = 'outer')\n",
    "\n",
    "    # Create a Plotly figure\n",
    "    fig = go.Figure()\n",
    "    \n",
    "    # Dynamically add a trace for each stock symbol in the DataFrame\n",
    "    for column in full_df.columns[1:]:  # Skip the first column since it's the date\n",
    "        fig.add_trace(go.Scatter(x=full_df['Date'], y=full_df[column], mode='lines+markers', name=column))\n",
    "    \n",
    "    \n",
    "    # Update the layout to add titles and format axis labels\n",
    "    fig.update_layout(\n",
    "        title='Stock Price Over Time: ' + ', '.join(full_df.columns.tolist()[1:]),\n",
    "        xaxis_title='Date',\n",
    "        yaxis_title='Stock Price (USD)',\n",
    "        yaxis_tickprefix='$',\n",
    "        yaxis_tickformat=',.2f',\n",
    "        xaxis=dict(\n",
    "            tickangle=-45,\n",
    "            nticks=20,\n",
    "            tickfont=dict(size=10),\n",
    "        ),\n",
    "        yaxis=dict(\n",
    "            showgrid=True,   # Enable y-axis grid lines\n",
    "            gridcolor='lightgrey',  # Set grid line color\n",
    "        ),\n",
    "        legend_title_text='Stock Symbol',\n",
    "        plot_bgcolor='white',  # Set plot background to white\n",
    "        paper_bgcolor='white',  # Set overall figure background to white\n",
    "        legend=dict(\n",
    "            bgcolor='white',  # Optional: Set legend background to white\n",
    "            bordercolor='black'\n",
    "        )\n",
    "    )\n",
    "    \n",
    "    # Show the figure - unfortunately dynamic charts are not supported on GitHub preview, so this just generates\n",
    "    # a static .png. If running locally, you can use fig.show(renderer='iframe') to output a dynamic plotly plot\n",
    "    fig.show('png')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd06265b-ceaf-4dca-b392-ceb3e10634f3",
   "metadata": {},
   "source": [
    "Finally, we will use LangChain to tie everything together. Our system prompt will provide the current date for context, and our function will execute each subsequent tool that's been called. It will also send the output back to the LLM so that it can respond to the user prompt with relevant information, and plot historical prices if that's what was asked for:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "f0312977-514a-4ecb-b1ed-29923c546704",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.messages import AIMessage, SystemMessage, HumanMessage, ToolMessage\n",
    "from datetime import date\n",
    "\n",
    "def call_functions(llm_with_tools, user_prompt):\n",
    "    system_prompt = 'You are a helpful finance assistant that analyzes stocks and stock prices. Today is {today}'.format(today = date.today())\n",
    "    \n",
    "    messages = [SystemMessage(system_prompt), HumanMessage(user_prompt)]\n",
    "    ai_msg = llm_with_tools.invoke(messages)\n",
    "    messages.append(ai_msg)\n",
    "    historical_price_dfs = []\n",
    "    symbols = []\n",
    "    for tool_call in ai_msg.tool_calls:\n",
    "        selected_tool = {\"get_stock_info\": get_stock_info, \"get_historical_price\": get_historical_price}[tool_call[\"name\"].lower()]\n",
    "        tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
    "        if tool_call['name'] == 'get_historical_price':\n",
    "            historical_price_dfs.append(tool_output)\n",
    "            symbols.append(tool_output.columns[1])\n",
    "        else:\n",
    "            messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
    "    \n",
    "    if len(historical_price_dfs) > 0:\n",
    "        plot_price_over_time(historical_price_dfs)\n",
    "        symbols = ' and '.join(symbols)\n",
    "        messages.append(ToolMessage('Tell the user that a historical stock price chart for {symbols} been generated.'.format(symbols=symbols), tool_call_id=0))\n",
    "\n",
    "    return llm_with_tools.invoke(messages).content\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e35c1d41-72c0-4ec7-b25a-e68eec646861",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The beta for Meta stock is 1.184.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_prompt = 'What is the beta for meta stock?'\n",
    "call_functions(llm_with_tools, user_prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "fff68338-24fa-454c-9a5e-8307c4341208",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'A historical stock price chart for GOOGL and AAPL and META has been generated.'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_prompt = \"Compare the stock price of Google, Apple and Meta over the past 6 months\"\n",
    "call_functions(llm_with_tools, user_prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d21b4491-7be4-46d9-af10-8dab353312bc",
   "metadata": {},
   "source": [
    "### Conclusion"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73573bc0-281a-419a-8465-9a1e179f7497",
   "metadata": {},
   "source": [
    "In this notebook, we've demonstrated how to harness the power of Groq API's function calling with Llama 3 and LangChain integration. Llama 3 is an impressive new model, and its capabilities are amplified when combined with Groq's exceptional LPU speed! To explore the interactive app that accompanies this notebook, please visit: https://llama3-function-calling.streamlit.app/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a911ee75-e50e-4310-b5ea-5e6aba5ee522",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}