t81_559_class_07_1_agents.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "whjsJasuhstV"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/jeffheaton/app_generative_ai/blob/main/t81_559_class_04_1_langchain_chat.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "euOZxlIMhstX"
      },
      "source": [
        "# T81-559: Applications of Generative Artificial Intelligence\n",
        "**Module 7: LangChain: Agents**\n",
        "* Instructor: [Jeff Heaton](https://sites.wustl.edu/jeffheaton/), McKelvey School of Engineering, [Washington University in St. Louis](https://engineering.wustl.edu/Programs/Pages/default.aspx)\n",
        "* For more information visit the [class website](https://sites.wustl.edu/jeffheaton/t81-558/)."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "d4Yov72PhstY"
      },
      "source": [
        "# Module 7 Material\n",
        "\n",
        "* **Part 7.1: Structured Output Parser** [[Video]]() [[Notebook]](t81_559_class_07_1_agents.ipynb)\n",
        "* Part 7.2: Other Parsers (CSV, JSON, Pandas, Datetime)** [[Video]]() [[Notebook]](t81_559_class_05_2_parsers.ipynb)\n",
        "* Part 7.3: Pydantic Parser [[Video]]() [[Notebook]](t81_559_class_05_3_pydantic.ipynb)\n",
        "* Part 7.4: Custom Output Parser [[Video]]() [[Notebook]](t81_559_class_05_4_custom_parsers.ipynb)\n",
        "* Part 7.5: Output-Fixing Parser [[Video]]() [[Notebook]](t81_559_class_05_5_output_fixing_parsers.ipynb)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "AcAUP0c3hstY"
      },
      "source": [
        "# Google CoLab Instructions\n",
        "\n",
        "The following code ensures that Google CoLab is running and maps Google Drive if needed."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xsI496h5hstZ",
        "outputId": "588117ae-29ab-4b44-be6b-c0292cc60c3a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Note: using Google CoLab\n",
            "Collecting langchain\n",
            "  Downloading langchain-0.1.17-py3-none-any.whl (867 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m867.6/867.6 kB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain_openai\n",
            "  Downloading langchain_openai-0.1.6-py3-none-any.whl (34 kB)\n",
            "Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n",
            "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.29)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.5)\n",
            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)\n",
            "Collecting dataclasses-json<0.7,>=0.5.7 (from langchain)\n",
            "  Downloading dataclasses_json-0.6.5-py3-none-any.whl (28 kB)\n",
            "Collecting jsonpatch<2.0,>=1.33 (from langchain)\n",
            "  Downloading jsonpatch-1.33-py2.py3-none-any.whl (12 kB)\n",
            "Collecting langchain-community<0.1,>=0.0.36 (from langchain)\n",
            "  Downloading langchain_community-0.0.36-py3-none-any.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain-core<0.2.0,>=0.1.48 (from langchain)\n",
            "  Downloading langchain_core-0.1.50-py3-none-any.whl (302 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.8/302.8 kB\u001b[0m \u001b[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain-text-splitters<0.1,>=0.0.1 (from langchain)\n",
            "  Downloading langchain_text_splitters-0.0.1-py3-none-any.whl (21 kB)\n",
            "Collecting langsmith<0.2.0,>=0.1.17 (from langchain)\n",
            "  Downloading langsmith-0.1.53-py3-none-any.whl (116 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.4/116.4 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.25.2)\n",
            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.7.1)\n",
            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)\n",
            "Collecting openai<2.0.0,>=1.24.0 (from langchain_openai)\n",
            "  Downloading openai-1.25.1-py3-none-any.whl (312 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m312.9/312.9 kB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tiktoken<1,>=0.5.2 (from langchain_openai)\n",
            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m21.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.4)\n",
            "Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
            "  Downloading marshmallow-3.21.2-py3-none-any.whl (49 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.3/49.3 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting typing-inspect<1,>=0.4.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
            "  Downloading typing_inspect-0.9.0-py3-none-any.whl (8.8 kB)\n",
            "Collecting jsonpointer>=1.9 (from jsonpatch<2.0,>=1.33->langchain)\n",
            "  Downloading jsonpointer-2.4-py2.py3-none-any.whl (7.8 kB)\n",
            "Collecting packaging<24.0,>=23.2 (from langchain-core<0.2.0,>=0.1.48->langchain)\n",
            "  Downloading packaging-23.2-py3-none-any.whl (53 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.0/53.0 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting orjson<4.0.0,>=3.9.14 (from langsmith<0.2.0,>=0.1.17->langchain)\n",
            "  Downloading orjson-3.10.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (142 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m142.7/142.7 kB\u001b[0m \u001b[31m1.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.24.0->langchain_openai) (3.7.1)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai<2.0.0,>=1.24.0->langchain_openai) (1.7.0)\n",
            "Collecting httpx<1,>=0.23.0 (from openai<2.0.0,>=1.24.0->langchain_openai)\n",
            "  Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.24.0->langchain_openai) (1.3.1)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.24.0->langchain_openai) (4.66.2)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.24.0->langchain_openai) (4.11.0)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.2 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (2.18.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2024.2.2)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)\n",
            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken<1,>=0.5.2->langchain_openai) (2023.12.25)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai<2.0.0,>=1.24.0->langchain_openai) (1.2.1)\n",
            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai<2.0.0,>=1.24.0->langchain_openai)\n",
            "  Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai<2.0.0,>=1.24.0->langchain_openai)\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting mypy-extensions>=0.3.0 (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain)\n",
            "  Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)\n",
            "Installing collected packages: packaging, orjson, mypy-extensions, jsonpointer, h11, typing-inspect, tiktoken, marshmallow, jsonpatch, httpcore, langsmith, httpx, dataclasses-json, openai, langchain-core, langchain-text-splitters, langchain_openai, langchain-community, langchain\n",
            "  Attempting uninstall: packaging\n",
            "    Found existing installation: packaging 24.0\n",
            "    Uninstalling packaging-24.0:\n",
            "      Successfully uninstalled packaging-24.0\n",
            "Successfully installed dataclasses-json-0.6.5 h11-0.14.0 httpcore-1.0.5 httpx-0.27.0 jsonpatch-1.33 jsonpointer-2.4 langchain-0.1.17 langchain-community-0.0.36 langchain-core-0.1.50 langchain-text-splitters-0.0.1 langchain_openai-0.1.6 langsmith-0.1.53 marshmallow-3.21.2 mypy-extensions-1.0.0 openai-1.25.1 orjson-3.10.2 packaging-23.2 tiktoken-0.6.0 typing-inspect-0.9.0\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "\n",
        "try:\n",
        "    from google.colab import drive, userdata\n",
        "    COLAB = True\n",
        "    print(\"Note: using Google CoLab\")\n",
        "except:\n",
        "    print(\"Note: not using Google CoLab\")\n",
        "    COLAB = False\n",
        "\n",
        "# OpenAI Secrets\n",
        "if COLAB:\n",
        "    os.environ[\"OPENAI_API_KEY\"] = userdata.get('OPENAI_API_KEY')\n",
        "\n",
        "# Install needed libraries in CoLab\n",
        "if COLAB:\n",
        "    !pip install langchain langchain_openai,langchain_experimental,duckduckgo-search"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pC9A-LaYhsta"
      },
      "source": [
        "# 7.1: LangChain Agents\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "The following code uses an LLM to tell a joke. The pydantic parser ensures that the joke ends in a question mark. Such checking ensures that the somewhat random LLM produces output that aligns with our expectations."
      ],
      "metadata": {
        "id": "KUsS8qUHO2oc"
      }
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "Fl9oeUkBPsIu"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import Tool\n",
        "from langchain_experimental.utilities import PythonREPL\n",
        "\n",
        "python_repl = PythonREPL()\n",
        "\n",
        "python_repl.run(\"print(1+1)\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "id": "I53vfzsX3Kc1",
        "outputId": "d1d1df4e-ca8e-4126-c764-d43cb5b8e1fd"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:langchain_experimental.utilities.python:Python REPL can execute arbitrary code. Use with caution.\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'2\\n'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain_community.tools import DuckDuckGoSearchRun\n",
        "\n",
        "search = DuckDuckGoSearchRun()\n",
        "search.run(\"current version of OSX\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "Idy_UX7u3xky",
        "outputId": "b16bee11-ccb5-453f-c423-a2be0ccfaa91"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\"The first ancestor of the macOS family was Mac OS X Public Beta released in 2000, followed by a public release of Mac OS X 10.0 in 2001. Let's recount the stories of all Mac OS X versions, up to the current macOS (or check out our ultimate infographic.) 1. Mac OS X 10.0 (Cheetah) March 24, 2001: Aqua interface is born with Mac OS X Cheetah ... macOS 13 Ventura. Introduced at WWDC 2022, macOS Ventura is the current version of macOS, the operating system that runs on the Mac. macOS Ventura is a significant update that introduces a new ... macOS 14 Sonoma: Release date. Apple macOS 14 Sonoma was released on September 26 as a free update for all supported Macs. (Image credit: Apple) Of course, any new MacBook or desktop Mac you buy ... The newest version of macOS, aka macOS 14, aka Sonoma (named after the Californian wine region), is now available. Among the new features Sonoma brings to Macs are changes to widgets, a new Game ... Current Version. The current version of macOS Sonoma is macOS 14.4.1, released on March 25. macOS Sonoma 14.4.1 is a bug fix update that addresses an issue with USB hubs connected to external ...\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install duckduckgo-search"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tSR6oKLm6mPB",
        "outputId": "f34f02fa-c735-4ece-eea8-81356a338c10"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting duckduckgo-search\n",
            "  Downloading duckduckgo_search-5.3.0-py3-none-any.whl (21 kB)\n",
            "Requirement already satisfied: click>=8.1.7 in /usr/local/lib/python3.10/dist-packages (from duckduckgo-search) (8.1.7)\n",
            "Collecting curl-cffi>=0.6.2 (from duckduckgo-search)\n",
            "  Downloading curl_cffi-0.6.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m33.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: orjson>=3.10.0 in /usr/local/lib/python3.10/dist-packages (from duckduckgo-search) (3.10.2)\n",
            "Requirement already satisfied: cffi>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from curl-cffi>=0.6.2->duckduckgo-search) (1.16.0)\n",
            "Requirement already satisfied: certifi>=2024.2.2 in /usr/local/lib/python3.10/dist-packages (from curl-cffi>=0.6.2->duckduckgo-search) (2024.2.2)\n",
            "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.12.0->curl-cffi>=0.6.2->duckduckgo-search) (2.22)\n",
            "Installing collected packages: curl-cffi, duckduckgo-search\n",
            "Successfully installed curl-cffi-0.6.3 duckduckgo-search-5.3.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.pydantic_v1 import BaseModel, Field\n",
        "from langchain.tools import BaseTool, StructuredTool, tool\n",
        "\n",
        "@tool\n",
        "def multiply(a: int, b: int) -> int:\n",
        "    \"\"\"Multiply two numbers.\"\"\"\n",
        "    return a * b\n",
        "\n",
        "print(multiply.name)\n",
        "print(multiply.description)\n",
        "print(multiply.args)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jTVRr16T-49B",
        "outputId": "7d80b10e-9b80-49be-ea7d-c685bd11915c"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "multiply\n",
            "multiply(a: int, b: int) -> int - Multiply two numbers.\n",
            "{'a': {'title': 'A', 'type': 'integer'}, 'b': {'title': 'B', 'type': 'integer'}}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import initialize_agent, AgentType\n",
        "from langchain_openai import ChatOpenAI\n",
        "\n",
        "MODEL = 'gpt-3.5-turbo'\n",
        "TEMPERATURE = 0.2\n",
        "\n",
        "llm = ChatOpenAI(\n",
        "  model=MODEL,\n",
        "  temperature=TEMPERATURE,\n",
        "  max_tokens= 256)\n",
        "\n",
        "tools = [multiply]\n",
        "agent_chain = initialize_agent(tools,\n",
        "                               llm,\n",
        "                               agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
        "                               verbose=True)\n",
        "\n",
        "\n",
        "agent_chain(\"What is 2 multiplied by 3?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S0EKUEjIPROW",
        "outputId": "631ae4fb-4323-4500-dc1a-138be1216487"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I can use the multiply tool to find the product of 2 and 3. \n",
            "\n",
            "Action:\n",
            "```\n",
            "{\n",
            "  \"action\": \"multiply\",\n",
            "  \"action_input\": {\"a\": 2, \"b\": 3}\n",
            "}\n",
            "```  \n",
            "\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m6\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3mI have calculated that 2 multiplied by 3 equals 6.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input': 'What is 2 multiplied by 3?',\n",
              " 'output': 'I have calculated that 2 multiplied by 3 equals 6.'}"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "https://python.langchain.com/docs/integrations/chat/"
      ],
      "metadata": {
        "id": "dB4TbGF4VBG7"
      }
    }
  ],
  "metadata": {
    "anaconda-cloud": {},
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3.11 (genai)",
      "language": "python",
      "name": "pytorch"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.11.8"
    },
    "varInspector": {
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "delete_cmd_postfix": "",
          "delete_cmd_prefix": "del ",
          "library": "var_list.py",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "delete_cmd_postfix": ") ",
          "delete_cmd_prefix": "rm(",
          "library": "var_list.r",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ],
      "window_display": false
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}