05_NLP/02. LangChain_Example.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "Based on a notebook that is copyrighted by © 2023 Patrick Loeber"
      ],
      "metadata": {
        "id": "DOycdBmh0FBf"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# LangChain\n",
        "\n",
        "LangChain is a framework for developing applications powered by language models.\n",
        "\n",
        "- GitHub: https://github.com/hwchase17/langchain\n",
        "- Docs: https://python.langchain.com/en/latest/index.html\n",
        "\n",
        "### Overview:\n",
        "- Installation\n",
        "- LLMs\n",
        "- Prompt Templates\n",
        "- Chains\n",
        "- Agents and Tools\n",
        "- Memory\n",
        "- Document Loaders\n",
        "- Indexes"
      ],
      "metadata": {
        "id": "nTDgRy0jKDkP"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 0. Installation"
      ],
      "metadata": {
        "id": "5WGtOYYTKfz3"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "bcrn7QRyQXGj",
        "outputId": "147f96ad-e6bd-40f4-e07c-ad8ea5d932f0",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting langchain\n",
            "  Downloading langchain-0.1.0-py3-none-any.whl (797 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m798.0/798.0 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement 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) (2.0.24)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.1)\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",
            "Collecting dataclasses-json<0.7,>=0.5.7 (from langchain)\n",
            "  Downloading dataclasses_json-0.6.3-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,>=0.0.9 (from langchain)\n",
            "  Downloading langchain_community-0.0.11-py3-none-any.whl (1.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m45.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain-core<0.2,>=0.1.7 (from langchain)\n",
            "  Downloading langchain_core-0.1.10-py3-none-any.whl (216 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m216.6/216.6 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langsmith<0.1.0,>=0.0.77 (from langchain)\n",
            "  Downloading langsmith-0.0.80-py3-none-any.whl (48 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.3/48.3 kB\u001b[0m \u001b[31m3.4 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) (1.23.5)\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) (23.2.0)\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) (1.9.4)\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: 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",
            "Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
            "  Downloading marshmallow-3.20.2-py3-none-any.whl (49 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m3.7 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",
            "Requirement already satisfied: anyio<5,>=3 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1.7->langchain) (3.7.1)\n",
            "Requirement already satisfied: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1.7->langchain) (23.2)\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: 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) (3.6)\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) (2023.11.17)\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: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1.7->langchain) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1.7->langchain) (1.2.0)\n",
            "Collecting 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: mypy-extensions, marshmallow, jsonpointer, typing-inspect, langsmith, jsonpatch, langchain-core, dataclasses-json, langchain-community, langchain\n",
            "Successfully installed dataclasses-json-0.6.3 jsonpatch-1.33 jsonpointer-2.4 langchain-0.1.0 langchain-community-0.0.11 langchain-core-0.1.10 langsmith-0.0.80 marshmallow-3.20.2 mypy-extensions-1.0.0 typing-inspect-0.9.0\n"
          ]
        }
      ],
      "source": [
        "!pip install langchain"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 1. LLMs\n",
        "\n",
        "A generic interface for all LLMs. See all LLM providers: https://python.langchain.com/docs/integrations/llms/"
      ],
      "metadata": {
        "id": "NkGGSdmtta6s"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install openai"
      ],
      "metadata": {
        "id": "H_dfy6G_aBtY",
        "outputId": "6e2da8ad-4afc-4bb1-a518-af85f718c2f1",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting openai\n",
            "  Downloading openai-1.7.2-py3-none-any.whl (212 kB)\n",
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/212.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.0/212.1 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━\u001b[0m \u001b[32m204.8/212.1 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.1/212.1 kB\u001b[0m \u001b[31m2.3 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) (3.7.1)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n",
            "Collecting httpx<1,>=0.23.0 (from openai)\n",
            "  Downloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (1.10.13)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.0)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.1)\n",
            "Collecting typing-extensions<5,>=4.7 (from openai)\n",
            "  Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n",
            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.6)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2023.11.17)\n",
            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n",
            "  Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m6.5 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)\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[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: typing-extensions, h11, httpcore, httpx, openai\n",
            "  Attempting uninstall: typing-extensions\n",
            "    Found existing installation: typing_extensions 4.5.0\n",
            "    Uninstalling typing_extensions-4.5.0:\n",
            "      Successfully uninstalled typing_extensions-4.5.0\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "llmx 0.0.15a0 requires cohere, which is not installed.\n",
            "llmx 0.0.15a0 requires tiktoken, which is not installed.\n",
            "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed h11-0.14.0 httpcore-1.0.2 httpx-0.26.0 openai-1.7.2 typing-extensions-4.9.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "os.environ[\"OPENAI_API_KEY\"] =\"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\""
      ],
      "metadata": {
        "id": "RlxEmS1CaM5v"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.llms import OpenAI\n",
        "\n",
        "llm = OpenAI(temperature=0.9)  # model_name=\"text-davinci-003\"\n",
        "text = \"What would be a good company name for a company that makes colorful socks?\"\n",
        "print(llm(text))"
      ],
      "metadata": {
        "id": "pY09s9cmZ6nQ",
        "outputId": "bc145ed1-77fe-4bac-9ade-a590e892e65e",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain_community.llms.openai.OpenAI` was deprecated in langchain-community 0.1.0 and will be removed in 0.2.0. Use langchain_openai.OpenAI instead.\n",
            "  warn_deprecated(\n",
            "/usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.7 and will be removed in 0.2.0. Use invoke instead.\n",
            "  warn_deprecated(\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\"Rainbow Toes\" or \"Vibrant Socks Co.\"\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install huggingface_hub"
      ],
      "metadata": {
        "id": "idkq_aVyaceF",
        "outputId": "dbf2635d-590c-4eb8-9fc3-f4cf3104f20f",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.20.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.9.0)\n",
            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.11.17)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "os.environ[\"HUGGINGFACEHUB_API_TOKEN\"] = \"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\""
      ],
      "metadata": {
        "id": "i4DKOWjyaRmO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import HuggingFaceHub"
      ],
      "metadata": {
        "id": "QmtH72oCaU32"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# https://huggingface.co/google/flan-t5-xl\n",
        "llm = HuggingFaceHub(repo_id=\"google/flan-t5-xxl\", model_kwargs={\"temperature\":0.1, \"max_length\":64})\n",
        "\n",
        "llm(\"translate English to German: How old are you?\")"
      ],
      "metadata": {
        "id": "8uK5TtJPc49I",
        "outputId": "f3fe7f75-4144-4e09-97a2-093c1cdb7970",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 90
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'InferenceApi' (from 'huggingface_hub.inference_api') is deprecated and will be removed from version '1.0'. `InferenceApi` client is deprecated in favor of the more feature-complete `InferenceClient`. Check out this guide to learn how to convert your script to use it: https://huggingface.co/docs/huggingface_hub/guides/inference#legacy-inferenceapi-client.\n",
            "  warnings.warn(warning_message, FutureWarning)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'Wie alt sind Sie?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 2. Prompt Templates\n",
        "\n",
        "LangChain faciliates prompt management and optimization.\n",
        "\n",
        "Normally when you use an LLM in an application, you are not sending user input directly to the LLM. Instead, you need to take the user input and construct a prompt, and only then send that to the LLM."
      ],
      "metadata": {
        "id": "3O-7dO1htdO4"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "llm(\"Can Barack Obama have a conversation with George Washington?\")"
      ],
      "metadata": {
        "id": "_FDS9IDRapOt",
        "outputId": "05e80024-22eb-4e6d-a119-8a207d42d1f2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'yes'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "prompt = \"\"\"Question: Can Barack Obama have a conversation with George Washington?\n",
        "\n",
        "Let's think step by step.\n",
        "\n",
        "Answer: \"\"\"\n",
        "llm(prompt)"
      ],
      "metadata": {
        "id": "lB4W8dM1tPAY",
        "outputId": "80de7494-78fc-4031-c3c8-007512ca8eb8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'George Washington died in 1799. Barack Obama was born in 1961. The answer: no.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import PromptTemplate\n",
        "\n",
        "template = \"\"\"Question: {question}\n",
        "\n",
        "Let's think step by step.\n",
        "\n",
        "Answer: \"\"\"\n",
        "\n",
        "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
      ],
      "metadata": {
        "id": "UU1VyMMvtsCE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "formatted_prompt = prompt.format(question=\"Can Barack Obama have a conversation with George Washington?\")"
      ],
      "metadata": {
        "id": "-Yzpc_0aHHeE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "formatted_prompt"
      ],
      "metadata": {
        "id": "5u313VGDalqT",
        "outputId": "b762069c-1eb6-4dfb-893e-2d9fe6a01a76",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\"Question: Can Barack Obama have a conversation with George Washington?\\n\\nLet's think step by step.\\n\\nAnswer: \""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "llm(formatted_prompt)"
      ],
      "metadata": {
        "id": "on8ubh3kt7oD",
        "outputId": "807d300b-c649-4408-ae5b-db99e4db3b25",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'George Washington died in 1799. Barack Obama was born in 1961. The answer: no.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 3. Chains\n",
        "\n",
        "Combine LLMs and Prompts in multi-step workflows"
      ],
      "metadata": {
        "id": "1zw1KlSeuUOY"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import LLMChain\n",
        "\n",
        "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
        "\n",
        "question = \"Can Barack Obama have a conversation with George Washington?\"\n",
        "\n",
        "print(llm_chain.run(question))"
      ],
      "metadata": {
        "id": "eE6n-jbAuOxt",
        "outputId": "cc5705af-8d4a-4a6b-8874-29ef57fab63f",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "George Washington died in 1799. Barack Obama was born in 1961. The answer: no.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
            "  warn_deprecated(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 4. Agents and Tools\n",
        "\n",
        "Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done.\n",
        "\n",
        "\n",
        "When used correctly agents can be extremely powerful. In order to load agents, you should understand the following concepts:\n",
        "\n",
        "- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains.\n",
        "- LLM: The language model powering the agent.\n",
        "- Agent: The agent to use.\n",
        "\n",
        "Tools: https://python.langchain.com/en/latest/modules/agents/tools.html\n",
        "\n",
        "Agent Types: https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html"
      ],
      "metadata": {
        "id": "Zp-UlOK0bMVQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import load_tools\n",
        "from langchain.agents import initialize_agent"
      ],
      "metadata": {
        "id": "79JcjhFXwv0J"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install wikipedia"
      ],
      "metadata": {
        "id": "dOSpaurEb1MR",
        "outputId": "28ae99fc-9121-4588-f08a-f5ced3950474",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting wikipedia\n",
            "  Downloading wikipedia-1.4.0.tar.gz (27 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from wikipedia) (4.11.2)\n",
            "Requirement already satisfied: requests<3.0.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from wikipedia) (2.31.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.0.0->wikipedia) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.0.0->wikipedia) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.0.0->wikipedia) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.0.0->wikipedia) (2023.11.17)\n",
            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->wikipedia) (2.5)\n",
            "Building wheels for collected packages: wikipedia\n",
            "  Building wheel for wikipedia (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for wikipedia: filename=wikipedia-1.4.0-py3-none-any.whl size=11678 sha256=0b6cb35f02a0410ecbc74d4572731cd1e21c68d0cfc9af7d70b1d3cd999ffd21\n",
            "  Stored in directory: /root/.cache/pip/wheels/5e/b6/c5/93f3dec388ae76edc830cb42901bb0232504dfc0df02fc50de\n",
            "Successfully built wikipedia\n",
            "Installing collected packages: wikipedia\n",
            "Successfully installed wikipedia-1.4.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.llms import OpenAI\n",
        "llm = OpenAI(temperature=0)\n",
        "tools = load_tools([\"wikipedia\", \"llm-math\"], llm=llm)"
      ],
      "metadata": {
        "id": "RgV4kny1bgy1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
      ],
      "metadata": {
        "id": "iQUOsWLrbjKv",
        "outputId": "afeaca49-b99e-49de-d49d-25661bf058ce",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `initialize_agent` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n",
            "  warn_deprecated(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"In what year was the film Departed with Leopnardo Dicaprio released? What is this year raised to the 0.43 power?\")"
      ],
      "metadata": {
        "id": "M8Rob2Wsb_l9",
        "outputId": "ecf17097-6de8-4257-f211-793610644e72",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        }
      },
      "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 should use Wikipedia to find the release year of the film and then use a calculator to raise it to the 0.43 power.\n",
            "Action: Wikipedia\n",
            "Action Input: Departed\u001b[0m"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/wikipedia/wikipedia.py:389: GuessedAtParserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system (\"lxml\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n",
            "\n",
            "The code that caused this warning is on line 389 of the file /usr/local/lib/python3.10/dist-packages/wikipedia/wikipedia.py. To get rid of this warning, pass the additional argument 'features=\"lxml\"' to the BeautifulSoup constructor.\n",
            "\n",
            "  lis = BeautifulSoup(html).find_all('li')\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Observation: \u001b[36;1m\u001b[1;3mPage: The Departed\n",
            "Summary: The Departed is a 2006 American crime thriller film directed by Martin Scorsese and written by William Monahan. It is both a remake of the 2002 Hong Kong film Infernal Affairs and also loosely based on the real-life Boston Winter Hill Gang; the character Colin Sullivan is based on the corrupt FBI agent John Connolly, while the character Frank Costello is based on Irish-American gangster and crime boss Whitey Bulger. The film stars Leonardo DiCaprio, Matt Damon, Jack Nicholson, and Mark Wahlberg, with Martin Sheen, Ray Winstone, Vera Farmiga, Alec Baldwin, Anthony Anderson and James Badge Dale in supporting roles.\n",
            "The film takes place in Boston and the surrounding metro area, primarily in the South Boston neighborhood. Irish Mob boss Frank Costello (Nicholson) plants Colin Sullivan (Damon) as a spy within the Massachusetts State Police; simultaneously, the police assign undercover state trooper Billy Costigan (DiCaprio) to infiltrate Costello's mob crew. When both sides realize the situation, Sullivan and Costigan each attempt to discover the other's identity before they are found out.\n",
            "The Departed was a critical and commercial success, receiving acclaim for its direction, performances (particularly of DiCaprio, Nicholson, and Wahlberg), screenplay, and editing.\n",
            "It won several accolades, including four Oscars at the 79th Academy Awards: for Best Picture, Best Director, Best Adapted Screenplay, and Best Film Editing. It became Scorsese's first and, to date, only personal Oscar win; Wahlberg was also nominated for Best Supporting Actor. The film also received six nominations at the 64th Golden Globe Awards, six nominations at the 60th British Academy Film Awards, and two nominations at the 13th Screen Actors Guild Awards. DiCaprio was nominated for Golden Globe Award for Best Actor – Motion Picture Drama (also nominated that year in the same category for Blood Diamond), BAFTA Award for Best Actor in a Leading Role and Screen Actors Guild Award for Outstanding Performance by a Male Actor in a Supporting Role for his performance.\n",
            "\n",
            "\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m Now I have the release year, I can use a calculator to raise it to the 0.43 power.\n",
            "Action: Calculator\n",
            "Action Input: 2006 ^ 0.43\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3mAnswer: 26.30281917656938\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
            "Final Answer: 26.30281917656938\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'26.30281917656938'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 5. Memory\n",
        "\n",
        "Add State to Chains and Agents.\n",
        "\n",
        "Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory."
      ],
      "metadata": {
        "id": "8AuQNfhYm48A"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import OpenAI, ConversationChain\n",
        "\n",
        "llm = OpenAI(temperature=0)\n",
        "conversation = ConversationChain(llm=llm, verbose=True)\n",
        "\n",
        "conversation.predict(input=\"Hi there!\")"
      ],
      "metadata": {
        "id": "Ujwj29G2cDPN",
        "outputId": "31201856-a655-4094-a2ac-e872461915d8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 264
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
            "\n",
            "Current conversation:\n",
            "\n",
            "Human: Hi there!\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hello! It's nice to meet you. I am an AI created by OpenAI. I am constantly learning and improving my abilities through machine learning algorithms. How can I assist you today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Can we talk about AI?\")"
      ],
      "metadata": {
        "id": "XkKv8n7ZnB2e",
        "outputId": "bb05c6e6-9bdb-4bd0-a6fb-ada489ad9718",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
            "\n",
            "Current conversation:\n",
            "Human: Hi there!\n",
            "AI:  Hello! It's nice to meet you. I am an AI created by OpenAI. I am constantly learning and improving my abilities through machine learning algorithms. How can I assist you today?\n",
            "Human: Can we talk about AI?\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Absolutely! I am an AI, so I am always happy to talk about my own kind. What specifically would you like to know about AI?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"I'm interested in Reinforcement Learning.\")"
      ],
      "metadata": {
        "id": "r4P3zWCmoDST",
        "outputId": "0b0687e9-5310-4a11-d5e8-28d66aa27ca0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 350
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
            "\n",
            "Current conversation:\n",
            "Human: Hi there!\n",
            "AI:  Hello! It's nice to meet you. I am an AI created by OpenAI. I am constantly learning and improving my abilities through machine learning algorithms. How can I assist you today?\n",
            "Human: Can we talk about AI?\n",
            "AI:  Absolutely! I am an AI, so I am always happy to talk about my own kind. What specifically would you like to know about AI?\n",
            "Human: I'm interested in Reinforcement Learning.\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Reinforcement Learning is a type of machine learning that involves training an AI agent through trial and error. The agent receives rewards or punishments based on its actions, and uses this feedback to learn how to achieve a specific goal. It is often used in tasks that involve decision making and long-term planning, such as playing games or controlling robots. Is there anything else you would like to know about Reinforcement Learning?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 6. Document Loaders\n",
        "\n",
        "Combining language models with your own text data is a powerful way to differentiate them. The first step in doing this is to load the data into “documents” - a fancy way of say some pieces of text. This module is aimed at making this easy.\n",
        "\n",
        "https://python.langchain.com/en/latest/modules/indexes/document_loaders.html"
      ],
      "metadata": {
        "id": "9wMttXM-CuPK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.document_loaders import NotionDirectoryLoader\n",
        "\n",
        "loader = NotionDirectoryLoader(\"Notion_DB\")\n",
        "\n",
        "docs = loader.load()"
      ],
      "metadata": {
        "id": "iAiISOcboPKR"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 7. Indexes\n",
        "\n",
        "Indexes refer to ways to structure documents so that LLMs can best interact with them. This module contains utility functions for working with documents\n",
        "\n",
        "- Embeddings: An embedding is a numerical representation of a piece of information, for example, text, documents, images, audio, etc.\n",
        "- Text Splitters: When you want to deal with long pieces of text, it is necessary to split up that text into chunks.\n",
        "- Vectorstores: Vector databases store and index vector embeddings from NLP models to understand the meaning and context of strings of text, sentences, and whole documents for more accurate and relevant search results."
      ],
      "metadata": {
        "id": "Q_zcj8MLDGfQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "\n",
        "filename = \"README.md\"\n",
        "\n",
        "url = \"https://raw.githubusercontent.com/PXLAIRobotics/PG.AI-TA-2324-HandsOn/main/\" + filename\n",
        "res = requests.get(url)\n",
        "with open(filename, \"w\") as f:\n",
        "  f.write(res.text)"
      ],
      "metadata": {
        "id": "qLU79cyCozYl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Document Loader\n",
        "from langchain.document_loaders import TextLoader\n",
        "loader = TextLoader('./' + filename)\n",
        "documents = loader.load()"
      ],
      "metadata": {
        "id": "XGyZXiJZBsov"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Text Splitter\n",
        "from langchain.text_splitter import CharacterTextSplitter\n",
        "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
        "docs = text_splitter.split_documents(documents)"
      ],
      "metadata": {
        "id": "OklI0xTvp2KE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install sentence_transformers"
      ],
      "metadata": {
        "id": "skvXSMXHCxyq",
        "outputId": "121005fe-fff1-4387-b164-18f082b4532a",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting sentence_transformers\n",
            "  Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n",
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/86.0 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m30.7/86.0 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.0/86.0 kB\u001b[0m \u001b[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: transformers<5.0.0,>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (4.35.2)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (4.66.1)\n",
            "Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (2.1.0+cu121)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (0.16.0+cu121)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (1.23.5)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (1.2.2)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (1.11.4)\n",
            "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (3.8.1)\n",
            "Collecting sentencepiece (from sentence_transformers)\n",
            "  Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m18.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: huggingface-hub>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (0.20.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (3.13.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (2023.6.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (2.31.0)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (6.0.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (4.9.0)\n",
            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (23.2)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (3.2.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (3.1.2)\n",
            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (2.1.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (2023.6.3)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (0.15.0)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (0.4.1)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk->sentence_transformers) (8.1.7)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk->sentence_transformers) (1.3.2)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence_transformers) (3.2.0)\n",
            "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision->sentence_transformers) (9.4.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.6.0->sentence_transformers) (2.1.3)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (2023.11.17)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.6.0->sentence_transformers) (1.3.0)\n",
            "Building wheels for collected packages: sentence_transformers\n",
            "  Building wheel for sentence_transformers (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sentence_transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125923 sha256=c1a0907ca8f288ae310a1f149c3a1ae078c6b6e1916246d0513f8d61202a737f\n",
            "  Stored in directory: /root/.cache/pip/wheels/62/f2/10/1e606fd5f02395388f74e7462910fe851042f97238cbbd902f\n",
            "Successfully built sentence_transformers\n",
            "Installing collected packages: sentencepiece, sentence_transformers\n",
            "Successfully installed sentence_transformers-2.2.2 sentencepiece-0.1.99\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Embeddings\n",
        "from langchain.embeddings import HuggingFaceEmbeddings\n",
        "embeddings = HuggingFaceEmbeddings()\n",
        "\n",
        "text = \"This is a test document.\"\n",
        "query_result = embeddings.embed_query(text)\n",
        "doc_result = embeddings.embed_documents([text])"
      ],
      "metadata": {
        "id": "V1yCdAhSCi64"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install faiss-cpu"
      ],
      "metadata": {
        "id": "8R3pT55b-uBJ",
        "outputId": "9bdb91f8-c394-4103-b90a-1dce536d3cca",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting faiss-cpu\n",
            "  Downloading faiss_cpu-1.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.6/17.6 MB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: faiss-cpu\n",
            "Successfully installed faiss-cpu-1.7.4\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Vectorstore: https://python.langchain.com/en/latest/modules/indexes/vectorstores.html\n",
        "from langchain.vectorstores import FAISS\n",
        "\n",
        "db = FAISS.from_documents(docs, embeddings)\n",
        "\n",
        "query = \"Number of neurons\"\n",
        "docs = db.similarity_search(query)"
      ],
      "metadata": {
        "id": "W7sRydnlC7rb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(docs[0].page_content)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CB7lvDWzDHZy",
        "outputId": "fed07eb6-cead-47b2-d4b0-0bfe08f14f8d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "**Multiclass classification**\n",
            "* Number of neurons in the output layer: `<num_classes>`\n",
            "* Activation function in the output layer: `softmax`\n",
            "* Loss function: `categorical_crossentropy` (n log loss)\n",
            "\n",
            "#### Regression\n",
            "* Number of neurons in the output layer: `1`\n",
            "* Activation function in the output layer: `linear`\n",
            "* Loss function: `mse` or `mae`\n",
            "\n",
            "#### Complex outputs (i.e. YOLO)\n",
            "* Number of neurons in the output layer: `<to_define>`\n",
            "* Activation function in the output layer: `<to_define>`\n",
            "* Activation function in the output layer: `<to_define>`\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "db.save_local(\"faiss_index\")\n",
        "new_db = FAISS.load_local(\"faiss_index\", embeddings)\n",
        "docs = new_db.similarity_search(query)\n",
        "print(docs[0].page_content)"
      ],
      "metadata": {
        "id": "nu-AmhDLEK0h",
        "outputId": "8153544c-8057-4771-861e-a45f60340fd9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "**Multiclass classification**\n",
            "* Number of neurons in the output layer: `<num_classes>`\n",
            "* Activation function in the output layer: `softmax`\n",
            "* Loss function: `categorical_crossentropy` (n log loss)\n",
            "\n",
            "#### Regression\n",
            "* Number of neurons in the output layer: `1`\n",
            "* Activation function in the output layer: `linear`\n",
            "* Loss function: `mse` or `mae`\n",
            "\n",
            "#### Complex outputs (i.e. YOLO)\n",
            "* Number of neurons in the output layer: `<to_define>`\n",
            "* Activation function in the output layer: `<to_define>`\n",
            "* Activation function in the output layer: `<to_define>`\n"
          ]
        }
      ]
    }
  ]
}