langchain/docs/modules/agents/agents/examples/conversational_agent.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4658d71a",
   "metadata": {},
   "source": [
    "# Conversation Agent\n",
    "\n",
    "This notebook walks through using an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\n",
    "\n",
    "This is accomplished with a specific type of agent (`conversational-react-description`) which expects to be used with a memory component."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f65308ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import Tool\n",
    "from langchain.agents import AgentType\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain import OpenAI\n",
    "from langchain.utilities import GoogleSearchAPIWrapper\n",
    "from langchain.agents import initialize_agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5fb14d6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "search = GoogleSearchAPIWrapper()\n",
    "tools = [\n",
    "    Tool(\n",
    "        name = \"Current Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events or the current state of the world\"\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "dddc34c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "memory = ConversationBufferMemory(memory_key=\"chat_history\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cafe9bc1",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm=OpenAI(temperature=0)\n",
    "agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dc70b454",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: Do I need to use a tool? No\n",
      "AI: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Hi Bob, nice to meet you! How can I help you today?'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"hi, i am bob\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3dcf7953",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: Do I need to use a tool? No\n",
      "AI: Your name is Bob!\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Your name is Bob!'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"what's my name?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "aa05f566",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: Do I need to use a tool? No\n",
      "AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "c5d8b7ea",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: Do I need to use a tool? Yes\n",
      "Action: Current Search\n",
      "Action Input: Who won the World Cup in 1978\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
      "AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"The last letter in your name is 'b'. Argentina won the World Cup in 1978.\""
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f608889b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Thought: Do I need to use a tool? Yes\n",
      "Action: Current Search\n",
      "Action Input: Current temperature in Pomfret\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
      "AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"whats the current temperature in pomfret?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0084efd6",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}