Agent_Langchain.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "##Agents\n",
        "###Agents has access to a set of tools like websearch, calculator or custom tools and Using LLM it will decide which action need to be taken first"
      ],
      "metadata": {
        "id": "IqoTn1NBkgsd"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "##Why we need Agents?\n",
        "###LLM does not have access to real time data. LLM models has no clue about \"As of today, How many more goals did Messi need to surpass Ronaldo's international goal tally?\""
      ],
      "metadata": {
        "id": "vRkQmsDVlonS"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "![agents.png](data:image/png;base64,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)"
      ],
      "metadata": {
        "id": "JL-zRg7Pp6KH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain\n",
        "!pip install google-search-results\n",
        "!pip install openai"
      ],
      "metadata": {
        "id": "jEBozwz06g4h",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "84395122-e9b2-4658-c2ed-efbdcebd3a5e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.0.321)\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) (2.0.22)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.8.6)\n",
            "Requirement already satisfied: anyio<4.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.7.1)\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",
            "Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.6.1)\n",
            "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.33)\n",
            "Requirement already satisfied: langsmith<0.1.0,>=0.0.43 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.49)\n",
            "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.23.5)\n",
            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.10.13)\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",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.1.0)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (3.3.0)\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) (6.0.4)\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) (1.9.2)\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) (1.4.0)\n",
            "Requirement 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: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<4.0->langchain) (3.4)\n",
            "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<4.0->langchain) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4.0->langchain) (1.1.3)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (3.20.1)\n",
            "Requirement already satisfied: typing-inspect<1,>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (0.9.0)\n",
            "Requirement already satisfied: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain) (2.4)\n",
            "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (4.5.0)\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) (2023.7.22)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.0)\n",
            "Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.10/dist-packages (from marshmallow<4.0.0,>=3.18.0->dataclasses-json<0.7,>=0.5.7->langchain) (23.2)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n",
            "Requirement already satisfied: google-search-results in /usr/local/lib/python3.10/dist-packages (2.4.2)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from google-search-results) (2.31.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->google-search-results) (3.3.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->google-search-results) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->google-search-results) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->google-search-results) (2023.7.22)\n",
            "Requirement already satisfied: openai in /usr/local/lib/python3.10/dist-packages (0.28.1)\n",
            "Requirement already satisfied: requests>=2.20 in /usr/local/lib/python3.10/dist-packages (from openai) (2.31.0)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.1)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from openai) (3.8.6)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai) (3.3.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai) (2023.7.22)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (23.1.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (6.0.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (4.0.3)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai) (1.3.1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount(\"/content/drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pXco04XZA6GA",
        "outputId": "6c974931-8dcc-4c5f-98be-66c9c78d233c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import sys\n",
        "sys.path.append(\"/content/drive/MyDrive\")"
      ],
      "metadata": {
        "id": "GBlbR-QYBIXf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from constant_keys import *"
      ],
      "metadata": {
        "id": "Us3bdELYBO5k"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY # Replace with your key\n",
        "os.environ[\"SERPAPI_API_KEY\"] = SERPAPI_API_KEY # Replace with your key"
      ],
      "metadata": {
        "id": "kEGAP-vMBS08"
      },
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import load_tools, initialize_agent, AgentType\n",
        "from langchain.llms import OpenAI"
      ],
      "metadata": {
        "id": "6W9HymxiBe_w"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(temperature=0)"
      ],
      "metadata": {
        "id": "3aRKcjdzBhZD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tools = load_tools([\"serpapi\",\"llm-math\"], llm=llm)"
      ],
      "metadata": {
        "id": "L9r2Ek8eBzpd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
      ],
      "metadata": {
        "id": "ojPBu8-7B1HN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"As of today, How many more goals did Messi need to surpass Ronaldo's international goal tally?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 310
        },
        "id": "JtkQ69G8B1Js",
        "outputId": "10d87b7d-3336-47c2-f41b-a85a469cdda4"
      },
      "execution_count": null,
      "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 the current goal tallies of both players\n",
            "Action: Search\n",
            "Action Input: \"Messi Ronaldo international goals\"\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mInternational football Argentina star Messi has scored 104 goals in 176 international appearances – both all-time records for his nation. With 123 goals in 201 games for Portugal, Ronaldo holds both the all-time men's records for international appearances and goals.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I need to subtract Ronaldo's goals from Messi's\n",
            "Action: Calculator\n",
            "Action Input: 104 - 123\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3mAnswer: -19\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
            "Final Answer: Messi needs 19 more goals to surpass Ronaldo's international goal tally.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\"Messi needs 19 more goals to surpass Ronaldo's international goal tally.\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "hoQA7CxQCS2t"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}