gpt_search.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/willdphan/gpt-search/blob/main/gpt_search.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain\n",
        "!pip install openai\n",
        "!pip install google-search-results"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2F2F9Puqn1Ku",
        "outputId": "2ae532c5-6187-4b79-e515-52a92aeda0d1"
      },
      "id": "2F2F9Puqn1Ku",
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: langchain in /usr/local/lib/python3.9/dist-packages (0.0.134)\n",
            "Requirement already satisfied: dataclasses-json<0.6.0,>=0.5.7 in /usr/local/lib/python3.9/dist-packages (from langchain) (0.5.7)\n",
            "Requirement already satisfied: PyYAML>=5.4.1 in /usr/local/lib/python3.9/dist-packages (from langchain) (6.0)\n",
            "Requirement already satisfied: SQLAlchemy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.4.47)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.9/dist-packages (from langchain) (3.8.4)\n",
            "Requirement already satisfied: pydantic<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.10.7)\n",
            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.27.1)\n",
            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (4.0.2)\n",
            "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.22.4)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (8.2.2)\n",
            "Requirement already satisfied: openapi-schema-pydantic<2.0,>=1.2 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.2.4)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (22.2.0)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (2.0.12)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.3)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.8.2)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
            "Requirement already satisfied: typing-inspect>=0.4.0 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (0.8.0)\n",
            "Requirement already satisfied: marshmallow-enum<2.0.0,>=1.5.1 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (1.5.1)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.3.0 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (3.19.0)\n",
            "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic<2,>=1->langchain) (4.5.0)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (2022.12.7)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (3.4)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.9/dist-packages (from SQLAlchemy<2,>=1->langchain) (2.0.2)\n",
            "Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.9/dist-packages (from marshmallow<4.0.0,>=3.3.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (23.0)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.9/dist-packages (from typing-inspect>=0.4.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (1.0.0)\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: openai in /usr/local/lib/python3.9/dist-packages (0.27.4)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.9/dist-packages (from openai) (3.8.4)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from openai) (4.65.0)\n",
            "Requirement already satisfied: requests>=2.20 in /usr/local/lib/python3.9/dist-packages (from openai) (2.27.1)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (3.4)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2022.12.7)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2.0.12)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (4.0.2)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (22.2.0)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.8.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.3.3)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.3.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (6.0.4)\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: google-search-results in /usr/local/lib/python3.9/dist-packages (2.4.2)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from google-search-results) (2.27.1)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->google-search-results) (2.0.12)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->google-search-results) (3.4)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->google-search-results) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->google-search-results) (2022.12.7)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "7f247903",
      "metadata": {
        "id": "7f247903"
      },
      "outputs": [],
      "source": [
        "from langchain.agents import load_tools\n",
        "from langchain.agents import initialize_agent\n",
        "from langchain.llms import OpenAI"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "83032dcf",
      "metadata": {
        "id": "83032dcf"
      },
      "source": [
        "### SERP API"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "0c90ba74",
      "metadata": {
        "id": "0c90ba74"
      },
      "outputs": [],
      "source": [
        "from langchain.agents import load_tools\n",
        "\n",
        "import os\n",
        "os.environ['OPENAI_API_KEY'] = \"...\"\n",
        "os.environ['SERPAPI_API_KEY'] = \"...\""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "id": "d0f2fd44",
      "metadata": {
        "id": "d0f2fd44"
      },
      "outputs": [],
      "source": [
        "llm = OpenAI(temperature=0)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "id": "f26a0dd5",
      "metadata": {
        "id": "f26a0dd5"
      },
      "outputs": [],
      "source": [
        "tool_names = [\"serpapi\"]\n",
        "tools = load_tools(tool_names)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "e8a35518",
      "metadata": {
        "id": "e8a35518"
      },
      "outputs": [],
      "source": [
        "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "id": "829a2d67",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 226
        },
        "id": "829a2d67",
        "outputId": "5af191f0-d18c-44bb-ed39-49c4f473609b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m LangChain is a blockchain-based language learning platform\n",
            "Action: Search\n",
            "Action Input: \"LangChain blockchain language learning\"\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mOne new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m LangChain provides a unique way to learn languages\n",
            "Final Answer: LangChain provides a unique way to learn languages by using blockchain technology and language models to evaluate progress.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'LangChain provides a unique way to learn languages by using blockchain technology and language models to evaluate progress.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 7
        }
      ],
      "source": [
        "agent.run(\"Why use LangChain\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "id": "b4cc45f6",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 226
        },
        "id": "b4cc45f6",
        "outputId": "34b4de9c-bb0c-4b2a-bf9f-19437fe222ba"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m I need to find out who the current president is.\n",
            "Action: Search\n",
            "Action Input: \"current president\"\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mJoe Biden\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
            "Final Answer: Joe Biden is the current president.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'Joe Biden is the current president.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ],
      "source": [
        "# Input should be a search query.\n",
        "agent.run(\"Who is the current president?\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "1869cabc",
      "metadata": {
        "id": "1869cabc"
      },
      "source": [
        "### Wolfram Alpha"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "id": "0fd02098",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0fd02098",
        "outputId": "e6dab7ce-11ff-4a92-bf56-9be8c59896f5"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: wolframalpha in /usr/local/lib/python3.9/dist-packages (5.0.0)\n",
            "Requirement already satisfied: more-itertools in /usr/local/lib/python3.9/dist-packages (from wolframalpha) (9.1.0)\n",
            "Requirement already satisfied: xmltodict in /usr/local/lib/python3.9/dist-packages (from wolframalpha) (0.13.0)\n",
            "Requirement already satisfied: jaraco.context in /usr/local/lib/python3.9/dist-packages (from wolframalpha) (4.3.0)\n"
          ]
        }
      ],
      "source": [
        "from langchain.agents import load_tools\n",
        "\n",
        "import os\n",
        "!pip install wolframalpha\n",
        "os.environ['OPENAI_API_KEY'] = \"...\"\n",
        "os.environ['WOLFRAM_ALPHA_APPID'] = \"...\""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "id": "7a96dfdd",
      "metadata": {
        "id": "7a96dfdd"
      },
      "outputs": [],
      "source": [
        "llm = OpenAI(temperature=0)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "id": "1ba4200b",
      "metadata": {
        "id": "1ba4200b"
      },
      "outputs": [],
      "source": [
        "tool_names = [\"wolfram-alpha\"]\n",
        "tools = load_tools(tool_names)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "id": "4716e3a8",
      "metadata": {
        "id": "4716e3a8"
      },
      "outputs": [],
      "source": [
        "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "id": "89e0d255",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "89e0d255",
        "outputId": "306f3066-5eee-4aaf-df31-319883d60d61"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m I should research this animal.\n",
            "Action: Wolfram Alpha\n",
            "Action Input: \"beluga whale\"\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mAssumption: beluga (animal) \n",
            "Answer: kingdom | Animalia (animals)\n",
            "phylum | Chordata (chordates)\n",
            "class | Mammalia (mammals)\n",
            "order | Cetacea (whales, dolphins and porpoises)\n",
            "family | Monodontidae (narwhals, belugas)\n",
            "genus | Delphinapterus (beluga)\n",
            "species | Delphinapterus leucas (beluga)\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
            "Final Answer: The beluga whale is a species of whale in the family Monodontidae, genus Delphinapterus, and species Delphinapterus leucas.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The beluga whale is a species of whale in the family Monodontidae, genus Delphinapterus, and species Delphinapterus leucas.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 13
        }
      ],
      "source": [
        "# Input should be a search query.\n",
        "\n",
        "agent.run(\"What is the a beluga whale?\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "id": "86c98c29",
      "metadata": {
        "id": "86c98c29"
      },
      "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": "3.9.13"
    },
    "colab": {
      "provenance": [],
      "include_colab_link": true
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}