experiments/Q_A_integration_using_RAGS (1).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain openai wikipedia tiktoken neo4j langchain_openai"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "af6KrY8JRQHr",
        "outputId": "7dd9f575-e4f7-40f6-f083-1ed7226bc07c"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting langchain\n",
            "  Downloading langchain-0.1.11-py3-none-any.whl (807 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m807.5/807.5 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting openai\n",
            "  Downloading openai-1.13.3-py3-none-any.whl (227 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.4/227.4 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting wikipedia\n",
            "  Downloading wikipedia-1.4.0.tar.gz (27 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting tiktoken\n",
            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m12.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting neo4j\n",
            "  Downloading neo4j-5.18.0.tar.gz (198 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m198.0/198.0 kB\u001b[0m \u001b[31m19.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting langchain_openai\n",
            "  Downloading langchain_openai-0.0.8-py3-none-any.whl (32 kB)\n",
            "Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n",
            "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.28)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.3)\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-0.6.4-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,>=0.0.25 (from langchain)\n",
            "  Downloading langchain_community-0.0.27-py3-none-any.whl (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain-core<0.2,>=0.1.29 (from langchain)\n",
            "  Downloading langchain_core-0.1.30-py3-none-any.whl (256 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m256.9/256.9 kB\u001b[0m \u001b[31m28.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting langchain-text-splitters<0.1,>=0.0.1 (from langchain)\n",
            "  Downloading langchain_text_splitters-0.0.1-py3-none-any.whl (21 kB)\n",
            "Collecting langsmith<0.2.0,>=0.1.17 (from langchain)\n",
            "  Downloading langsmith-0.1.23-py3-none-any.whl (66 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m66.6/66.6 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.25.2)\n",
            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.6.3)\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) (8.2.3)\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",
            "Collecting httpx<1,>=0.23.0 (from openai)\n",
            "  Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.1)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.2)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai) (4.10.0)\n",
            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from wikipedia) (4.12.3)\n",
            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
            "Requirement already satisfied: pytz in /usr/local/lib/python3.10/dist-packages (from neo4j) (2023.4)\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: 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",
            "Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
            "  Downloading marshmallow-3.21.1-py3-none-any.whl (49 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m5.2 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",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.2.2)\n",
            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n",
            "  Downloading httpcore-1.0.4-py3-none-any.whl (77 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.8/77.8 kB\u001b[0m \u001b[31m9.7 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[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting 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: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1.29->langchain) (23.2)\n",
            "Collecting orjson<4.0.0,>=3.9.14 (from langsmith<0.2.0,>=0.1.17->langchain)\n",
            "  Downloading orjson-3.9.15-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.5/138.5 kB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.16.3 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (2.16.3)\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: 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: 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: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->wikipedia) (2.5)\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",
            "Building wheels for collected packages: wikipedia, neo4j\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=b2ec4f9a937a5ceff3cdf8e773aae101728293f2b9bcc0f307fad48e4e5e112c\n",
            "  Stored in directory: /root/.cache/pip/wheels/5e/b6/c5/93f3dec388ae76edc830cb42901bb0232504dfc0df02fc50de\n",
            "  Building wheel for neo4j (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for neo4j: filename=neo4j-5.18.0-py3-none-any.whl size=273862 sha256=0a7afc6e69841e8f44d6fcdf02eb328904171e9c25478c26937849aa5a615d1d\n",
            "  Stored in directory: /root/.cache/pip/wheels/e7/e1/a0/dd7c19192f5383ff57d02a6c126cbfe4b7b2ae82f70c6994ce\n",
            "Successfully built wikipedia neo4j\n",
            "Installing collected packages: orjson, neo4j, mypy-extensions, marshmallow, jsonpointer, h11, wikipedia, typing-inspect, tiktoken, jsonpatch, httpcore, langsmith, httpx, dataclasses-json, openai, langchain-core, langchain-text-splitters, langchain_openai, langchain-community, langchain\n",
            "Successfully installed dataclasses-json-0.6.4 h11-0.14.0 httpcore-1.0.4 httpx-0.27.0 jsonpatch-1.33 jsonpointer-2.4 langchain-0.1.11 langchain-community-0.0.27 langchain-core-0.1.30 langchain-text-splitters-0.0.1 langchain_openai-0.0.8 langsmith-0.1.23 marshmallow-3.21.1 mypy-extensions-1.0.0 neo4j-5.18.0 openai-1.13.3 orjson-3.9.15 tiktoken-0.6.0 typing-inspect-0.9.0 wikipedia-1.4.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "xN0IBt7qQKXA"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "from langchain_community.vectorstores.neo4j_vector import Neo4jVector\n",
        "from langchain.document_loaders import WikipediaLoader\n",
        "from langchain_openai import OpenAIEmbeddings\n",
        "from langchain.text_splitter import CharacterTextSplitter\n",
        "from langchain.docstore.document import Document"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "from langchain.chains import RetrievalQA\n",
        "from langchain_openai import ChatOpenAI\n",
        "from langchain_openai import OpenAIEmbeddings\n",
        "url = \"\"\n",
        "username = \"\"\n",
        "password = \"\"\n",
        "model_version='gpt-3.5-turbo-16k'\n",
        "openai_api_key = os.environ.get('OPENAI_API_KEY')\n",
        "\n",
        "retrieval_query=\"\"\"\n",
        " MATCH (node)-[:PART_OF]->(d:Document)\n",
        "WITH d, apoc.text.join(collect(node.text),\"\\n----\\n\") as text, avg(score) as score\n",
        "RETURN text, score, {source: COALESCE(CASE WHEN d.url CONTAINS \"None\" THEN d.fileName ELSE d.url END, d.fileName)} as metadata\n",
        "\"\"\"\n",
        "\n",
        "neo_db=Neo4jVector.from_existing_index(\n",
        "        embedding=OpenAIEmbeddings(),\n",
        "        url=url,\n",
        "        username=username,\n",
        "        password=password,\n",
        "        database=\"neo4j\",\n",
        "        index_name=\"vector\",\n",
        "        retrieval_query=retrieval_query,\n",
        "\n",
        "    )\n",
        "\n",
        "llm = ChatOpenAI(model= model_version, temperature=0)\n",
        "\n",
        "qa = RetrievalQA.from_chain_type(\n",
        "    llm=llm, chain_type=\"stuff\", retriever=neo_db.as_retriever(), return_source_documents=True\n",
        ")\n"
      ],
      "metadata": {
        "id": "gShd_mi-QuVg"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "question =\"What do you know about Suarez\"\n",
        "result = qa({\"query\": question})\n",
        "res={}\n",
        "res['result']=result[\"result\"]\n",
        "list_source_docs=[]\n",
        "for i in result[\"source_documents\"]:\n",
        "  list_source_docs.append(i.metadata['source'])\n",
        "res['source']=list_source_docs"
      ],
      "metadata": {
        "id": "D5-79i18Qu_x"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "vector_res=res\n",
        "print(vector_res)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3_3k0sTDRYfG",
        "outputId": "b91ea810-a391-49ff-9c48-4dde442353df"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{'result': \"I'm sorry, but I don't have enough information to answer your question about Suarez.\", 'source': ['https://www.youtube.com/watch?v=NKc8Tr5_L3w']}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "question =\"What do you know about Apple Stock\"\n",
        "result = qa({\"query\": question})\n",
        "res={}\n",
        "res['result']=result[\"result\"]\n",
        "list_source_docs=[]\n",
        "for i in result[\"source_documents\"]:\n",
        "  list_source_docs.append(i.metadata['source'])\n",
        "res['source']=list_source_docs"
      ],
      "metadata": {
        "id": "tMRYLo5zTL1E"
      },
      "execution_count": 50,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "res"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GDn1KEeeTQP-",
        "outputId": "afdfa364-7767-4e6d-8cc6-66c0f4de6b76"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'result': \"Apple Inc. (AAPL) is a multinational technology company that designs, manufactures, and sells consumer electronics, software, and online services. It is known for its flagship products such as the iPhone, iPad, Mac, and Apple Watch. Apple is also a major player in the digital services industry with offerings like Apple Music, iCloud, and the App Store.\\n\\nIn terms of its stock performance, Apple has been one of the most valuable and widely held stocks in the world. It is listed on the NASDAQ stock exchange under the ticker symbol AAPL. The stock has experienced significant growth over the years, driven by strong product sales, a loyal customer base, and a robust ecosystem of software and services.\\n\\nHowever, it's important to note that stock prices can be volatile and subject to market fluctuations. It is always recommended to conduct thorough research and consult with a financial advisor before making any investment decisions.\",\n",
              " 'source': ['Apple stock during pandemic.pdf']}"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#####################"
      ],
      "metadata": {
        "id": "MrKv1IJKQ1Ki"
      },
      "execution_count": 48,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Query the knowledge graph in a RAG application\n",
        "from langchain.chains import GraphCypherQAChain\n",
        "from langchain.graphs import Neo4jGraph\n",
        "\n",
        "graph = Neo4jGraph(\n",
        "    url=url,\n",
        "    username=username,\n",
        "    password=password\n",
        ")\n",
        "graph.refresh_schema()\n",
        "\n",
        "cypher_chain = GraphCypherQAChain.from_llm(\n",
        "    graph=graph,\n",
        "    cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-4\"),\n",
        "    qa_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo\"),\n",
        "    validate_cypher=True, # Validate relationship directions\n",
        "    verbose=True\n",
        ")"
      ],
      "metadata": {
        "id": "qFdQZ4ynQ2BY"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "cypher_res=cypher_chain.invoke({\"query\": \"What do you know about Suarez\"})"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GEsXwM0pQ4jY",
        "outputId": "3d962d25-8e45-45c6-c979-55228ec02856"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new GraphCypherQAChain chain...\u001b[0m\n",
            "Generated Cypher:\n",
            "\u001b[32;1m\u001b[1;3mMATCH (p:Person {name: \"Suarez\"}) RETURN p\u001b[0m\n",
            "Full Context:\n",
            "\u001b[32;1m\u001b[1;3m[{'p': {'nationality': 'Uruguayan', 'name': 'Suarez', 'id': 'Suarez', 'position': 'forward'}}]\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cypher_res"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Mh8BeOgxRgO2",
        "outputId": "2883e23f-bfbd-4bb7-cff0-e17f330ea469"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'query': 'What do you know about Suarez',\n",
              " 'result': 'Suarez is a Uruguayan forward.'}"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cypher_res=cypher_chain.invoke({\"query\": \"What do you know about Apple Stock\"})"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2Mq2tTrxSC8X",
        "outputId": "a3be89b9-5de8-480a-c7a4-d72fdc770030"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new GraphCypherQAChain chain...\u001b[0m\n",
            "Generated Cypher:\n",
            "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
            "Full Context:\n",
            "\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "######################"
      ],
      "metadata": {
        "id": "vchIkFU0TZur"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "query=\"What do you know about Suarez\"\n",
        "final_prompt = f\"\"\"You are a helpful question-answering agent. Your task is to analyze\n",
        "and synthesize information from two sources: the top result from a similarity search\n",
        "(unstructured information) and relevant data from a graph database (structured information).\n",
        "Given the user's query: {query}, provide a meaningful and efficient answer based\n",
        "on the insights derived from the following data:\n",
        "\n",
        "Structured information: {cypher_res['result']}.\n",
        "Unstructured information: {vector_res['result']}.\n",
        "\n",
        "If unstructured information fails to find an answer then use the answer from structured information and vice versa. I only want a straightforward answer\n",
        "\"\"\"\n",
        "\n",
        "response = llm.predict(final_prompt)\n",
        "\n",
        "# print(re.search(r\"Answer: (.+)\", response[0]['generated_text']).group(1))"
      ],
      "metadata": {
        "id": "E6J_PxsZUTGm"
      },
      "execution_count": 45,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "response"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "FXK_TwidX9g6",
        "outputId": "119dcb46-8864-4fff-e3ad-4e06067d021f"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'Suarez is a Uruguayan forward.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    }
  ]
}