{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# **RAG UsingWeaviate**\n",
        "\n",
        "## **Roman Empire Question Answering System**\n",
        "### **Overview**\n",
        "This project is a question answering system focused on providing answers related to the Roman Empire. It utilizes various technologies such as Weaviate for document storage and similarity search, OpenAI for language models and embeddings, and Langchain for creating the question answering pipeline.\n",
        "![warkflow.jpg](data:image/jpeg;base64,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)\n",
        "\n",
        "**Setup Instructions:**\n",
        "- Install All the required libraries and dependencies.\n",
        "- Define your Weaviate and OpenAI credentials.\n",
        "- load the documents using the `load_documents` function.\n",
        "- spltit the documents into small chunks using the `text_splitter` function.\n",
        "- load the embeddings using the `load_embeddings` function.\n",
        "- Select the embedding model to create the embeddings.\n",
        "- create a vector store using weaviate.\n",
        "- store the data in weaviate vectorstore.\n",
        "- Finally, create a question answering pipeline to interact with the data."
      ],
      "metadata": {
        "id": "mZLVPpSPDMD8"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Creating Vectorstore"
      ],
      "metadata": {
        "id": "xvm6BXxUiK2F"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# install dependencies\n",
        "!pip install weaviate-client\n",
        "!pip install langchain\n",
        "!pip install openai\n",
        "!pip install pypdf\n",
        "!pip install -U langchain-community\n",
        "!pip install sentence_transformers\n",
        "!pip install unstructured\n",
        "!pip install \"unstructured[pdf]\""
      ],
      "metadata": {
        "id": "cg6XDu3VYNW3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "outputId": "3f6b845a-adf2-4f7b-b4ae-432daa1e3ed4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: weaviate-client in /usr/local/lib/python3.10/dist-packages (4.6.4)\n",
            "Requirement already satisfied: requests<3.0.0,>=2.30.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (2.31.0)\n",
            "Requirement already satisfied: httpx<=0.27.0,>=0.25.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (0.27.0)\n",
            "Requirement already satisfied: validators==0.28.3 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (0.28.3)\n",
            "Requirement already satisfied: authlib<2.0.0,>=1.2.1 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (1.3.1)\n",
            "Requirement already satisfied: pydantic<3.0.0,>=2.5.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (2.7.3)\n",
            "Requirement already satisfied: grpcio<2.0.0,>=1.57.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (1.64.1)\n",
            "Requirement already satisfied: grpcio-tools<2.0.0,>=1.57.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (1.64.1)\n",
            "Requirement already satisfied: grpcio-health-checking<2.0.0,>=1.57.0 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (1.64.1)\n",
            "Requirement already satisfied: cryptography in /usr/local/lib/python3.10/dist-packages (from authlib<2.0.0,>=1.2.1->weaviate-client) (42.0.7)\n",
            "Requirement already satisfied: protobuf<6.0dev,>=5.26.1 in /usr/local/lib/python3.10/dist-packages (from grpcio-health-checking<2.0.0,>=1.57.0->weaviate-client) (5.27.1)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from grpcio-tools<2.0.0,>=1.57.0->weaviate-client) (67.7.2)\n",
            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx<=0.27.0,>=0.25.0->weaviate-client) (3.7.1)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<=0.27.0,>=0.25.0->weaviate-client) (2024.6.2)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx<=0.27.0,>=0.25.0->weaviate-client) (1.0.5)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx<=0.27.0,>=0.25.0->weaviate-client) (3.7)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx<=0.27.0,>=0.25.0->weaviate-client) (1.3.1)\n",
            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx<=0.27.0,>=0.25.0->weaviate-client) (0.14.0)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3.0.0,>=2.5.0->weaviate-client) (0.7.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.4 in /usr/local/lib/python3.10/dist-packages (from pydantic<3.0.0,>=2.5.0->weaviate-client) (2.18.4)\n",
            "Requirement already satisfied: typing-extensions>=4.6.1 in /usr/local/lib/python3.10/dist-packages (from pydantic<3.0.0,>=2.5.0->weaviate-client) (4.12.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.30.0->weaviate-client) (3.3.2)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.30.0->weaviate-client) (2.0.7)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx<=0.27.0,>=0.25.0->weaviate-client) (1.2.1)\n",
            "Requirement already satisfied: cffi>=1.12 in /usr/local/lib/python3.10/dist-packages (from cryptography->authlib<2.0.0,>=1.2.1->weaviate-client) (1.16.0)\n",
            "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.12->cryptography->authlib<2.0.0,>=1.2.1->weaviate-client) (2.22)\n",
            "Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.2.3)\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) (2.0.30)\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",
            "Requirement already satisfied: langchain-core<0.3.0,>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.2.5)\n",
            "Requirement already satisfied: langchain-text-splitters<0.3.0,>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.2.1)\n",
            "Requirement already satisfied: langsmith<0.2.0,>=0.1.17 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.75)\n",
            "Requirement 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) (2.7.3)\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) (8.3.0)\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: 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",
            "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.3.0,>=0.2.0->langchain) (1.33)\n",
            "Requirement already satisfied: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.3.0,>=0.2.0->langchain) (23.2)\n",
            "Requirement already satisfied: orjson<4.0.0,>=3.9.14 in /usr/local/lib/python3.10/dist-packages (from langsmith<0.2.0,>=0.1.17->langchain) (3.10.3)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (0.7.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.4 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (2.18.4)\n",
            "Requirement already satisfied: typing-extensions>=4.6.1 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (4.12.1)\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) (2024.6.2)\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: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain-core<0.3.0,>=0.2.0->langchain) (2.4)\n",
            "Requirement already satisfied: openai in /usr/local/lib/python3.10/dist-packages (1.33.0)\n",
            "Requirement 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",
            "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from openai) (0.27.0)\n",
            "Requirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (2.7.3)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.1)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.4)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai) (4.12.1)\n",
            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.7)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.1)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.6.2)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (1.0.5)\n",
            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai) (0.14.0)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (0.7.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.4 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (2.18.4)\n",
            "Requirement already satisfied: pypdf in /usr/local/lib/python3.10/dist-packages (4.2.0)\n",
            "Requirement already satisfied: typing_extensions>=4.0 in /usr/local/lib/python3.10/dist-packages (from pypdf) (4.12.1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# define environment variables\n",
        "OPENAI_API_KEY = \"Your_OpenAI_Key\"\n",
        "WEAVIATE_API_KEY = \"Your_Weaviate_Key\"\n",
        "WEAVIATE_CLUSTER = \"Your_Weaviate_Cluster\""
      ],
      "metadata": {
        "id": "L7_7b6QfG-D9"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# load pdf\n",
        "from langchain.document_loaders import DirectoryLoader\n",
        "loader = DirectoryLoader(\".\",glob = \"**/*.pdf\")\n",
        "documents = loader.load()\n",
        "\n",
        "# OR Following method\n",
        "\n",
        "# from langchain.document_loaders import PyPDFLoader\n",
        "# loader = PyPDFLoader(\"/content/RomanEmpire.pdf\")\n",
        "# documents = loader.load()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l_vcYSPUKFxr",
        "outputId": "0ae27db9-99f7-4449-abd8-d656dec7f9ff"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt.zip.\n",
            "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
            "[nltk_data]     /root/nltk_data...\n",
            "[nltk_data]   Unzipping taggers/averaged_perceptron_tagger.zip.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(documents)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "86KbBQvUPAJ2",
        "outputId": "693ee80e-7f8f-4bcd-c34e-0c294ef01ddd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# split document content\n",
        "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
        "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)\n",
        "text = text_splitter.split_documents(documents)"
      ],
      "metadata": {
        "id": "lIJTH0BwKWy5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "len(text)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qJAgT58UO-M_",
        "outputId": "813ddcc7-6e59-4994-b23f-e08db22dc4a6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "145"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Always try to use atop embedding model from hugging face embedding leaderboard: https://huggingface.co/spaces/mteb/leaderboard"
      ],
      "metadata": {
        "id": "2itMqkMTOeFX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# load embedding model\n",
        "from langchain.embeddings.openai import OpenAIEmbeddings\n",
        "embeddings = OpenAIEmbeddings(openai_api_key= OPENAI_API_KEY)\n",
        "\n",
        "# OR Following method\n",
        "\n",
        "# from langchain.embeddings import HuggingFaceEmbeddings\n",
        "# embeddings = HuggingFaceEmbeddings(model_name=\"BAAI/bge-small-en-v1.5\", encode_kwargs = {\"normalize_embeddings\": True})"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "id": "CcQZcRVoMZQp",
        "outputId": "7489577a-4dde-4d29-82de-8d0ba12fc4f8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The class `OpenAIEmbeddings` was deprecated in LangChain 0.0.9 and will be removed in 0.3.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run `pip install -U langchain-openai` and import as `from langchain_openai import OpenAIEmbeddings`.\n",
            "  warn_deprecated(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# # check embeddings\n",
        "# check = embeddings.embed_query(\"Trial sentence for check embeddings\")\n",
        "# check[0:10]"
      ],
      "metadata": {
        "id": "3sX5TbXjTrEw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "embeddings"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "id": "G_IiyVMAPn-j",
        "outputId": "86ed90e5-bc8c-49f7-b46a-d18194adbe12"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "HuggingFaceEmbeddings(client=SentenceTransformer(\n",
              "  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel \n",
              "  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n",
              "  (2): Normalize()\n",
              "), model_name='BAAI/bge-small-en-v1.5', cache_folder=None, model_kwargs={}, encode_kwargs={'normalize_embeddings': True}, multi_process=False, show_progress=False)"
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install -U langchain-weaviate"
      ],
      "metadata": {
        "id": "bHJgKgMHTWoU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# create vectorstore using weaviate\n",
        "import weaviate\n",
        "from langchain.vectorstores import Weaviate\n",
        "\n",
        "#Connect to weaviate Cluster\n",
        "auth_config = weaviate.auth.AuthApiKey(api_key = WEAVIATE_API_KEY)\n",
        "WEAVIATE_URL = WEAVIATE_CLUSTER\n",
        "\n",
        "client = weaviate.Client(\n",
        "    url = WEAVIATE_URL,\n",
        "    additional_headers = {\"X-OpenAI-Api-key\": OPENAI_API_KEY},\n",
        "    auth_client_secret = auth_config,\n",
        "    startup_period = 10\n",
        ")"
      ],
      "metadata": {
        "id": "IxQOVNUgPwXu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# define input structure\n",
        "client.schema.delete_all()\n",
        "client.schema.get()\n",
        "schema = {\n",
        "    \"classes\": [\n",
        "        {\n",
        "            \"class\": \"RomanEmpire\",\n",
        "            \"description\": \"Documents for Roman Empire\",\n",
        "            \"vectorizer\": \"text2vec-openai\",\n",
        "            \"moduleConfig\": {\"text2vec-openai\": {\"model\": \"ada\", \"type\": \"text\"}},\n",
        "            \"properties\": [\n",
        "                {\n",
        "                    \"dataType\": [\"text\"],\n",
        "                    \"description\": \"The content of the paragraph\",\n",
        "                    \"moduleConfig\": {\n",
        "                        \"text2vec-openai\": {\n",
        "                            \"skip\": False,\n",
        "                            \"vectorizePropertyName\": False,\n",
        "                        }\n",
        "                    },\n",
        "                    \"name\": \"content\",\n",
        "                },\n",
        "            ],\n",
        "        },\n",
        "    ]\n",
        "}\n",
        "\n",
        "client.schema.create(schema)\n",
        "vectorstore = Weaviate(client, \"RomanEmpire\", \"content\", attributes=[\"source\"])"
      ],
      "metadata": {
        "id": "BwFyjfSEhyDR"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# load text into the vectorstore\n",
        "text_meta_pair = [(doc.page_content, doc.metadata) for doc in text]\n",
        "texts, meta = list(zip(*text_meta_pair))\n",
        "vectorstore.add_texts(texts, meta)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "id": "EEZxLBYhimeX",
        "outputId": "2c7df17c-1c3f-4236-ded2-8869cd245af8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['d8addbe6-87c2-450f-8ab5-cf4bce43f91d',\n",
              " 'b778f89f-1d63-4dde-b81d-bbecbf50f938',\n",
              " '5d1054db-3444-49da-b0ed-a1152013c1b7',\n",
              " 'e288b636-b2d1-42fb-9893-42aef886657c',\n",
              " '3750701e-58bb-44a0-aa3f-fd7217847e28',\n",
              " '6477e409-084c-4808-8144-1df91fa9ce65',\n",
              " '83dd61dd-151c-428b-b61c-8d20b1548014',\n",
              " 'db7f2c51-d553-497a-b6fc-ab6fe8339f24',\n",
              " '52cf52e8-7563-461d-991a-91b6c7c5909b',\n",
              " '08c82c58-eedc-4d78-b5d9-74bce2078cf2',\n",
              " 'b48981ca-70e3-4a17-804b-eebc77383080',\n",
              " 'ca8f54e3-5d0c-431d-b491-8a65a7cb959d',\n",
              " 'bdeb944e-a35e-4f73-8932-78b8dac1e081',\n",
              " '9a9d1826-3433-4704-a0a9-25b067a1da3c',\n",
              " 'e147cb38-c299-4625-ad6c-fec0ecc48aa0',\n",
              " '435c05e4-330f-4e2f-905b-db1798b90d1f',\n",
              " '4b033538-91f0-4034-9b6b-0b148268b6c0',\n",
              " 'a7bf1677-6026-401e-8e12-1bf2cce201b7',\n",
              " '5af18673-0087-4640-b7c6-8a633ff9cae3',\n",
              " '7a2bfc14-cccc-4a5b-bb00-2d2f27a36096',\n",
              " '35825bef-0d46-40a5-90c9-ba711d2c787c',\n",
              " 'de9db13f-f709-424b-945d-b1b556bcdf20',\n",
              " 'e86092c5-5c53-481f-a9f6-b33e489a68f6',\n",
              " 'e2416c74-7fac-4730-afdb-34fb6222ae2f',\n",
              " '8e43e712-63a9-4dd4-9dab-7158be4d38e3',\n",
              " '0ff817f6-2b92-483e-82fb-585fc7d10279',\n",
              " '7c1f99be-d49b-49bb-bed5-466a26c48a46',\n",
              " '40c0637c-8da6-4769-b2f2-093960e55d34',\n",
              " 'b62512fa-12d4-4773-aad2-de608ab5b424',\n",
              " 'ef9ca77e-a9d2-4f49-827d-8acdf8ba0a77',\n",
              " '5138fa0c-eaaa-4c01-a6df-310e9e36001a',\n",
              " 'e8e28b86-0f02-4fe0-bbff-32474c82639c',\n",
              " 'cebf98e2-486f-419c-966a-f94b30a6ec96',\n",
              " '034601eb-5015-4373-8bb7-6c211473b7dc',\n",
              " '597edbb0-a6aa-4b5c-86c4-aa6a2b158882',\n",
              " '5fffd143-0fea-432d-8c3d-23c812244caf',\n",
              " '92b057ce-1b50-49ab-96f5-5cb0e35b4f21',\n",
              " '13f82083-9e49-4c82-9782-7f91287966ca',\n",
              " 'bc018292-189c-40f3-b0b5-5df81343b420',\n",
              " '2f6a6f8a-c8b2-4ec8-8091-c267fc71f359',\n",
              " '59b7044c-9656-4770-af85-6c4394b4432d',\n",
              " '363e25a2-0ed3-4e13-bcb0-0b72b6656397',\n",
              " 'e788f941-4c03-4b4d-9726-70960a6de4af',\n",
              " '29ec59b9-140d-4b25-b95f-b0294a65452d',\n",
              " 'bcbf06e0-66ca-401e-b189-0dccc4917780',\n",
              " 'f5b3d362-c028-455c-a680-d62bc30914da',\n",
              " 'e5dcacb7-e873-42ca-857c-11ad2da2302f',\n",
              " 'b783e65c-d77b-4172-936b-c3aa462494cf',\n",
              " '10c8ca8f-09e9-4201-bb6a-2a6bb6b8b695',\n",
              " 'dd6cd501-66b0-4745-bbf0-1b0ee47dc73b',\n",
              " 'e3c17dd5-6af2-4350-8ef3-c36e262100ab',\n",
              " '0d745d0d-b126-4e77-a20a-2f7ce0738f50',\n",
              " '090db073-e52b-4d14-83a3-2264516e7422',\n",
              " '6d8ca3ee-34b6-4498-8cbb-2f8e834f62db',\n",
              " '2fdaf0e5-6c64-4ffa-b40c-4b45f014e8fd',\n",
              " '29ecec3b-04c1-44c3-9c2a-ee3e2f686ad7',\n",
              " '6bf40ee5-9580-493b-a71c-b0a9dde2ed70',\n",
              " '182fefb9-dcf7-4fe6-9a85-24fbf2b4beb5',\n",
              " '2f1725a1-bb97-437f-907c-fa3051dbe669',\n",
              " '43293184-ac35-4c8c-b578-ec1e77185a1e',\n",
              " '16fb0541-502d-4a07-b89e-2e816848cfb1',\n",
              " 'b84f6235-5b87-4707-b3d7-bb3d1b48f669',\n",
              " '43ccd433-d846-4472-b2e8-613cac141eba',\n",
              " '03e9c5a0-ee94-47f8-b915-bd42fb69096b',\n",
              " '15c4265b-a5cf-4ba3-ba4f-ba6e134f3c99',\n",
              " '60ec49ae-12c1-4602-855b-7825b4559840',\n",
              " '57eed7e8-af4c-42da-83ef-ee4add39ef5e',\n",
              " '34a58e08-e259-4849-8d41-1fc572b48d1e',\n",
              " '0689ddfe-7bd8-407c-85b8-4a0b58f2ac49',\n",
              " '71bd60e6-c01a-4796-9463-e6a140792935',\n",
              " 'a1e8879a-4bfa-4375-956d-55cfee6a0961',\n",
              " 'e0635016-2dfa-49e7-8013-048ac8f460ea',\n",
              " 'd02a48ef-b242-4e43-b6a3-803d857e63e4',\n",
              " '9c1df575-9cc4-43fc-8de7-d0c1d98e499c',\n",
              " '60e8babb-b004-4963-bd0a-f362c3f28430',\n",
              " '0f1a75e8-c6d8-4210-98a1-ae5fd0010902',\n",
              " 'b32e91e5-eb65-40fb-88d1-05b90324a952',\n",
              " '8802de47-8d60-4288-9679-2243cc0d59c2',\n",
              " '9230cfba-3d4d-45b6-bb12-6c299b6e3784',\n",
              " 'dddf10ac-f34b-44ff-9827-b979a7b488cc',\n",
              " '0f4ec260-e808-49c9-ada0-f89e9ddafe0e',\n",
              " 'dffc1a39-b955-41d2-ae94-1e98cb5c7e0a',\n",
              " 'f674beea-0374-4e74-ba2b-984a52f19262',\n",
              " '0981f5b8-d33c-471e-9143-2ced895d2b1f',\n",
              " 'fbecee1f-ec14-41c0-9f8b-28d88385eb11',\n",
              " 'a06562f7-5afe-4e43-aede-d0138dec2da3',\n",
              " 'bcbd29c4-bad2-47b8-9b5b-08223a923c07',\n",
              " 'd66ba276-8286-4ee2-9cec-7908a63e08bd',\n",
              " '7ac1122c-310a-4cdc-9f84-44205b53a123',\n",
              " 'b8a5652e-d1ff-4b31-a378-fdd8b093457f',\n",
              " '9b45118a-f827-47da-b1f6-28aeabb51de8',\n",
              " 'e4268973-95c3-45b8-9696-58ad20b7eb0d',\n",
              " 'c162c174-6be7-43a9-86e5-54e262b603dd',\n",
              " '6b0e4edd-ec3f-46ca-90dd-dcc215276e2f',\n",
              " '9932b0cb-01ca-4e5a-893e-e4f4c603adf3',\n",
              " '4d3fc7d8-ce5e-4b1d-9713-47c456c3fd00',\n",
              " 'ef278108-5854-464b-9268-262838a6ae42',\n",
              " '6be41c75-c68b-49b7-a459-1d67cff13dfd',\n",
              " '2e3f9970-8782-4727-aaad-930b5f7a4dc0',\n",
              " 'f5f7b034-161c-4c2d-9f54-31c08ca0c18c',\n",
              " 'bb93ff74-9cca-4cff-a8fe-eb87f8eaff6a',\n",
              " '676f09ea-94bf-40a1-a2aa-34e229c229f3',\n",
              " '9a52013f-c51b-4944-b4b8-fe44e6a904fb',\n",
              " 'a50a756f-5157-4662-bfce-5e17d4a4dae5',\n",
              " '70446e6c-f095-456d-9b66-933f698a30fb',\n",
              " '75398fe1-1be3-43b9-9a03-173ec8dad48c',\n",
              " '2f723688-eecf-4cea-badb-c66e07872c9d',\n",
              " '47758d3c-4328-45fa-a74c-04796b53dc66',\n",
              " '1c38193c-cea5-4b38-b475-8ff769c6ef18',\n",
              " '5eea9511-a911-4a27-b651-8f6fffa0b1c5',\n",
              " 'd9fb78ad-3645-445a-81ec-f89751bf2bb6',\n",
              " '4bf596a7-74f0-4666-a75b-543e442e646d',\n",
              " 'a183b788-5934-41cb-8413-85f77adf2376',\n",
              " '4ee30bcf-ea40-4ef4-9a4d-b9562734c3ce',\n",
              " '443d46c2-f52d-43b4-8c36-4790d2ba48b3',\n",
              " 'b98d86fe-1e26-43d2-aa1e-8bb5288a9a84',\n",
              " 'd42b41c5-ec4e-4610-8e0d-9f067a7049b1',\n",
              " '5f9c4026-446a-4d4f-8274-bafb875f8cf7',\n",
              " '65082cd5-6cda-481a-af8a-ed7dc301e74e',\n",
              " '97e24cb9-618b-4816-9868-b793db0458be',\n",
              " '16708fde-e915-413a-9b8d-9a652056de4e',\n",
              " 'f2d91e12-4ae1-490f-8d01-b42ddc2169fe',\n",
              " 'd538dc42-f265-47d3-98ba-8fd0b08538d6',\n",
              " '278807b5-b162-4189-88da-d2a6c94de714',\n",
              " 'b17e6c7d-0e56-4785-b409-7efd542c219d',\n",
              " 'f68c6abf-a4ee-4ec5-a8bd-c5eebcd5af90',\n",
              " '6ad65aa1-2d83-4d78-b159-e596b9f2e906',\n",
              " '600cf2b7-b23b-42cb-84e7-815721ce7cb4',\n",
              " 'f2648c57-4820-4cd1-85b1-c0e16689e190',\n",
              " 'b5c4b9ab-0a24-499a-924b-e290cb06defa',\n",
              " 'e02ff7ba-4940-4b18-8809-7ffd395b5fc6',\n",
              " 'b48819d1-39c4-49fb-a3e8-37a56752c120',\n",
              " '4a46237b-7ee8-4603-b7d2-b80aeb73d3d9',\n",
              " 'c4c5611b-b980-4ad1-a068-dc6b45265920',\n",
              " '000ea3e7-29ce-401d-921c-ec117d126459',\n",
              " 'a950086e-c3b7-46f6-a94a-03019764d658',\n",
              " '4b79ed51-9484-482c-aee9-fcad3d0b94c6',\n",
              " 'd5e1caaf-392d-4d24-bd07-f43bcf2e3e17',\n",
              " '0daf8e09-3fcc-490f-b44d-36470a128f6f',\n",
              " '59059d09-0430-4f8a-951b-47f342e4fa45',\n",
              " '70efb192-c2ae-4423-9d08-16fe182ad961',\n",
              " '63dc9a1b-78e3-4d8b-9148-4567c000265d',\n",
              " 'de3d0c88-13ba-41ab-b983-d7a473080308',\n",
              " 'b9166c8f-82ed-4a1a-8dc3-9c7b96bccd19',\n",
              " '58369474-0691-4714-9896-83697d870331']"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# # load the vectorstore and check similarity\n",
        "# query = \"tell me interesting facts about Roman Empire\"\n",
        "# results = vectorstore.similarity_search(query) # k=5"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "id": "IdBYcn3SjY1l",
        "outputId": "b1f75039-465a-47d8-827c-74b388387d80"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[Document(page_content='Main articles: Demography of the Roman Empire and Borders of the Roman Empire\\n\\nFurther information: Classical demography\\n\\nThe Roman Empire was one of the largest in history, with contiguous territories throughout Europe, North Africa, and the Middle East. The Latin phrase imperium sine fine (\"empire without end\") expressed the ideology that neither time nor space limited the Empire. In Virgil\\'s Aeneid, limitless empire is said to be granted to the Romans by Jupiter. This claim of universal dominion was renewed when the Empire came under Christian rule in the 4th century. In addition to annexing large regions, the Romans directly altered their geography, for example cutting down entire forests.', metadata={'source': 'RomanEmpire.pdf'}),\n",
              " Document(page_content='Most of the cultural appurtenances popularly associated with imperial culture---public cult and its games and civic banquets, competitions for artists, speakers, and athletes, as well as the funding of the great majority of public buildings and public display of art---were financed by private individuals, whose expenditures in this regard helped to justify their economic power and legal and provincial privileges. In the city of Rome, most people lived in multistory apartment buildings (insulae) that were often squalid firetraps. Public facilities---such as baths (thermae), toilets with running\\n\\nwater (latrinae), basins or elaborate fountains _(nymphea)_ delivering fresh water, and large- scale entertainments such as chariot races and gladiator combat---were aimed primarily at the common people. Similar facilities were constructed in cities throughout the Empire, and some of the best-preserved Roman structures are in Spain, southern France, and northern Africa.', metadata={'source': 'RomanEmpire.pdf'}),\n",
              " Document(page_content='Like gladiators, entertainers were legally infames, technically free but little better than slaves. \"Stars\", however, could enjoy considerable wealth and celebrity, and mingled socially and often sexually with the elite. Performers supported each other by forming guilds, and several memorials for theatre members survive. Theatre and dance were often condemned by Christian polemicists in the later Empire.\\n\\nEstimates of the average literacy rate range from 5 to over 30%. The Roman obsession with documents and inscriptions indicates the value placed on the written word. Laws and edicts were posted as well as read out. Illiterate Roman subjects could have a government scribe _(scriba)* read or write their official documents for them. The military produced extensive written records. The Babylonian Talmud declared \"if all seas were ink, all reeds were pen, all skies parchment, and all men scribes, they would be unable to set down the full scope of the Roman government\\'s concerns.\"', metadata={'source': 'RomanEmpire.pdf'}),\n",
              " Document(page_content=\"first time\\n\\nThe Empire reached its largest expanse under Trajan, encompassing 5 million square kilometres. The traditional population estimate of [55--60 million] inhabitants accounted for between one-sixth and one-fourth of the world's total population and made it the most populous unified political entity in the West until the mid-19th century. Recent demographic studies have argued for a population peak from [70 million] to more than [100 million]. Each of the three largest cities in the Empire -- Rome, Alexandria, and Antioch -- was almost twice the size of any European city at the beginning of the 17th century.\\n\\nAs the historian Christopher Kelly described it:\", metadata={'source': 'RomanEmpire.pdf'})]"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Revtriever Code"
      ],
      "metadata": {
        "id": "gz3S_Fp-iDGo"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# create retriever\n",
        "retriever = vectorstore.as_retriever()"
      ],
      "metadata": {
        "id": "nTYyIwlBqjJb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "from langchain_core.prompts import ChatPromptTemplate\n",
        "\n",
        "template = \"\"\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question.\n",
        "If answer is not in the context, just say that you don't know. Use five sentences maximum and keep the answer concise.\n",
        "Question: {question}\n",
        "Context: {context}\n",
        "Answer:\n",
        "\"\"\"\n",
        "prompt = ChatPromptTemplate.from_template(template)"
      ],
      "metadata": {
        "id": "di2Hs7GEqoxm"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# load llm for chain\n",
        "from langchain_community.chat_models import ChatOpenAI\n",
        "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0, openai_api_key = OPENAI_API_KEY)"
      ],
      "metadata": {
        "id": "phhsoITkqtuY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# create a chain with a retriever, prompt, and llm\n",
        "from langchain_core.output_parsers import StrOutputParser\n",
        "from langchain_core.runnables import RunnablePassthrough\n",
        "\n",
        "rag_chain = (\n",
        "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
        "    | prompt\n",
        "    | llm\n",
        "    | StrOutputParser()\n",
        ")"
      ],
      "metadata": {
        "id": "IGbeSUOSq0fI"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Asking question from your knowledge base\n",
        "rag_chain.invoke(\"tell me interesting facts about Roman Empire\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "id": "QFDBntQireKp",
        "outputId": "d10364b2-5d79-4a0e-d3fc-52dab17f58e2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The Roman Empire was one of the largest in history, spanning across Europe, North Africa, and the Middle East. The ideology of the empire was expressed through the Latin phrase imperium sine fine, meaning \"empire without end.\" The Romans directly altered their geography by annexing large regions and cutting down entire forests. The Empire reached its largest expanse under Trajan, covering 5 million square kilometers. Estimates of the average literacy rate in the Roman Empire range from 5 to over 30%.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Asking question which is not in the knowledge base\n",
        "rag_chain.invoke(\"what is the capital of United States?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "RcKZB3qHrfk2",
        "outputId": "aa513b19-65e3-45b7-df08-678b53516ac3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\"I don't know.\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 55
        }
      ]
    }
  ]
}