{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f1390152",
   "metadata": {},
   "source": [
    "# MRKL\n",
    "\n",
    "This notebook showcases using an agent to replicate the MRKL chain."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "39ea3638",
   "metadata": {},
   "source": [
    "This uses the example Chinook database.\n",
    "To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ac561cc4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import LLMMathChain, OpenAI, SerpAPIChain, SQLDatabase, SQLDatabaseChain\n",
    "from langchain.agents import initialize_agent, Tool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "07e96d99",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0)\n",
    "search = SerpAPIChain()\n",
    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
    "tools = [\n",
    "#     Tool(\n",
    "#         name = \"Search\",\n",
    "#         func=search.run,\n",
    "#         description=\"useful for when you need to answer questions about current events\"\n",
    "#     ),\n",
    "#     Tool(\n",
    "#         name=\"Calculator\",\n",
    "#         func=llm_math_chain.run,\n",
    "#         description=\"useful for when you need to answer questions about math\"\n",
    "#     ),\n",
    "    Tool(\n",
    "        name=\"FooBar DB\",\n",
    "        func=db_chain.run,\n",
    "        description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question\"\n",
    "    )\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a069c4b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "mrkl = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "356a1396",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "What was our total number of sales and total revenue in 2013?\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find out how many sales and how much revenue we had in 2013\n",
      "Action: FooBar DB\n",
      "Action Input: sales 2013\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "sales 2013\n",
      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT SUM(Total) FROM Invoice WHERE InvoiceDate BETWEEN '2013-01-01' AND '2013-12-31'\u001b[0m\n",
      "SQLResult: \u001b[33;1m\u001b[1;3m[(450.58000000000027,)]\u001b[0m\n",
      "Answer:\u001b[32;1m\u001b[1;3m 450.58\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3m 450.58\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find out how many sales and how much revenue we had in 2013\n",
      "Action: FooBar DB\n",
      "Action Input: revenue 2013\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "revenue 2013\n",
      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT SUM(Total) FROM Invoice WHERE strftime('%Y', InvoiceDate) = '2013'\u001b[0m\n",
      "SQLResult: \u001b[33;1m\u001b[1;3m[(450.58000000000027,)]\u001b[0m\n",
      "Answer:\u001b[32;1m\u001b[1;3m 450.58\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3m 450.58\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: We had 450.58 sales and 450.58 revenue in 2013\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'We had 450.58 sales and 450.58 revenue in 2013'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mrkl.run(\"What was our total number of sales and total revenue in 2013?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "4e9c9b23",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import ZeroShotAgent\n",
    "from langchain import PromptTemplate\n",
    "from langchain import LLMChain\n",
    "TEMPLATE = \"\"\"You are a data engineer answering questions using a SQL database.\n",
    "\n",
    "Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. If a previous query produced an error, do NOT try it again.\n",
    "\n",
    "Only use the following tables:\n",
    "\n",
    "{table_info}\n",
    "\n",
    "Use the following format:\n",
    "\n",
    "Question: the input question you must answer\n",
    "Thought: you should always think about what to do\n",
    "Action: SQLDB\n",
    "Action Input: the query to run against the SQL database\n",
    "Observation: the result of the action\n",
    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
    "Thought: I now know the final answer\n",
    "Final Answer: the final answer to the original input question\n",
    "\n",
    "Begin!\n",
    "\n",
    "Question: {{input}}\"\"\".format(**{\n",
    "            \"dialect\": db.dialect,\n",
    "            \"table_info\": db.table_info})\n",
    "prompt = PromptTemplate(template=TEMPLATE, input_variables=[\"input\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "a6fb1b4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
    "tools = [\n",
    "    Tool(\"SQLDB\", db.run, \"foo\")\n",
    "]\n",
    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "64578802",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "What was our total number of sales and total revenue in 2013?\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find the total number of sales and total revenue\n",
      "Action: SQLDB\n",
      "Action Input: SELECT SUM(Total) AS \"Total Sales\", SUM(Total) AS \"Total Revenue\" FROM Invoice WHERE InvoiceDate LIKE '2013%'\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m[(450.58000000000027, 450.58000000000027)]\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 450.58\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'450.58'"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"What was our total number of sales and total revenue in 2013?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e603cd7d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
      "Action: Search\n",
      "Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
      "Action: Search\n",
      "Action Input: \"Harry Styles age\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
      "Action: Calculator\n",
      "Action Input: 28^0.23\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "28^0.23\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```python\n",
      "print(28**0.23)\n",
      "```\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 2.1520202182226886\u001b[0m"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'2.1520202182226886'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mrkl.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a5c07010",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
      "Action: Search\n",
      "Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
      "Action: FooBar DB\n",
      "Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "Does Alanis Morissette exist in the FooBar database?\n",
      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
      "SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
      "Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
      "Action: FooBar DB\n",
      "Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "What albums by Alanis Morissette are in the FooBar database?\n",
      "SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
      "SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
      "Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mrkl.run(\"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d7c2e6ac",
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}