LangGraph_Agents_Controllability_Sub_graphs.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "zm8Jvgjj8hLg"
      },
      "outputs": [],
      "source": [
        "%%capture --no-stderr\n",
        "%pip install -U langgraph"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from operator import add\n",
        "from typing import List, TypedDict, Optional, Annotated, Dict\n",
        "from langgraph.checkpoint.memory import MemorySaver\n",
        "from langgraph.graph import StateGraph, START, END\n",
        "\n",
        "\n",
        "# The structure of the logs\n",
        "class Logs(TypedDict):\n",
        "    id: str\n",
        "    question: str\n",
        "    docs: Optional[List]\n",
        "    answer: str\n",
        "    grade: Optional[int]\n",
        "    grader: Optional[str]\n",
        "    feedback: Optional[str]\n",
        "\n",
        "\n",
        "# Failure Analysis Sub-graph\n",
        "class FailureAnalysisState(TypedDict):\n",
        "    docs: List[Logs]\n",
        "    failures: List[Logs]\n",
        "    fa_summary: str\n",
        "\n",
        "\n",
        "def get_failures(state):\n",
        "    docs = state[\"docs\"]\n",
        "    failures = [doc for doc in docs if \"grade\" in doc]\n",
        "    return {\"failures\": failures}\n",
        "\n",
        "\n",
        "def generate_summary(state):\n",
        "    failures = state[\"failures\"]\n",
        "    # Add fxn: fa_summary = summarize(failures)\n",
        "    fa_summary = \"Poor quality retrieval of Chroma documentation.\"\n",
        "    return {\"fa_summary\": fa_summary}\n",
        "\n",
        "\n",
        "fa_builder = StateGraph(FailureAnalysisState)\n",
        "fa_builder.add_node(\"get_failures\", get_failures)\n",
        "fa_builder.add_node(\"generate_summary\", generate_summary)\n",
        "fa_builder.add_edge(START, \"get_failures\")\n",
        "fa_builder.add_edge(\"get_failures\", \"generate_summary\")\n",
        "fa_builder.add_edge(\"generate_summary\", END)\n",
        "\n",
        "\n",
        "# Summarization subgraph\n",
        "class QuestionSummarizationState(TypedDict):\n",
        "    docs: List[Logs]\n",
        "    qs_summary: str\n",
        "    report: str\n",
        "\n",
        "\n",
        "def generate_summary(state):\n",
        "    docs = state[\"docs\"]\n",
        "    # Add fxn: summary = summarize(docs)\n",
        "    summary = \"Questions focused on usage of ChatOllama and Chroma vector store.\"\n",
        "    return {\"qs_summary\": summary}\n",
        "\n",
        "\n",
        "def send_to_slack(state):\n",
        "    qs_summary = state[\"qs_summary\"]\n",
        "    # Add fxn: report = report_generation(qs_summary)\n",
        "    report = \"foo bar baz\"\n",
        "    return {\"report\": report}\n",
        "\n",
        "\n",
        "def format_report_for_slack(state):\n",
        "    report = state[\"report\"]\n",
        "    # Add fxn: formatted_report = report_format(report)\n",
        "    formatted_report = \"foo bar\"\n",
        "    return {\"report\": formatted_report}\n",
        "\n",
        "\n",
        "qs_builder = StateGraph(QuestionSummarizationState)\n",
        "qs_builder.add_node(\"generate_summary\", generate_summary)\n",
        "qs_builder.add_node(\"send_to_slack\", send_to_slack)\n",
        "qs_builder.add_node(\"format_report_for_slack\", format_report_for_slack)\n",
        "qs_builder.add_edge(START, \"generate_summary\")\n",
        "qs_builder.add_edge(\"generate_summary\", \"send_to_slack\")\n",
        "qs_builder.add_edge(\"send_to_slack\", \"format_report_for_slack\")\n",
        "qs_builder.add_edge(\"format_report_for_slack\", END)"
      ],
      "metadata": {
        "id": "xMpvDj4G8sgV"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Dummy logs\n",
        "question_answer = Logs(\n",
        "    id=\"1\",\n",
        "    question=\"How can I import ChatOllama?\",\n",
        "    answer=\"To import ChatOllama, use: 'from langchain_community.chat_models import ChatOllama.'\",\n",
        ")\n",
        "\n",
        "question_answer_feedback = Logs(\n",
        "    id=\"2\",\n",
        "    question=\"How can I use Chroma vector store?\",\n",
        "    answer=\"To use Chroma, define: rag_chain = create_retrieval_chain(retriever, question_answer_chain).\",\n",
        "    grade=0,\n",
        "    grader=\"Document Relevance Recall\",\n",
        "    feedback=\"The retrieved documents discuss vector stores in general, but not Chroma specifically\",\n",
        ")\n",
        "\n",
        "\n",
        "# Entry Graph\n",
        "class EntryGraphState(TypedDict):\n",
        "    raw_logs: Annotated[List[Dict], add]\n",
        "    docs: Annotated[List[Logs], add]  # This will be used in sub-graphs\n",
        "    fa_summary: str  # This will be generated in the FA sub-graph\n",
        "    report: str  # This will be generated in the QS sub-graph\n",
        "\n",
        "\n",
        "def convert_logs_to_docs(state):\n",
        "    # Get logs\n",
        "    raw_logs = state[\"raw_logs\"]\n",
        "    docs = [question_answer, question_answer_feedback]\n",
        "    return {\"docs\": docs}\n",
        "\n",
        "\n",
        "entry_builder = StateGraph(EntryGraphState)\n",
        "entry_builder.add_node(\"convert_logs_to_docs\", convert_logs_to_docs)\n",
        "entry_builder.add_node(\"question_summarization\", qs_builder.compile())\n",
        "entry_builder.add_node(\"failure_analysis\", fa_builder.compile())\n",
        "\n",
        "entry_builder.add_edge(START, \"convert_logs_to_docs\")\n",
        "entry_builder.add_edge(\"convert_logs_to_docs\", \"failure_analysis\")\n",
        "entry_builder.add_edge(\"convert_logs_to_docs\", \"question_summarization\")\n",
        "entry_builder.add_edge(\"failure_analysis\", END)\n",
        "entry_builder.add_edge(\"question_summarization\", END)\n",
        "\n",
        "graph = entry_builder.compile()\n",
        "\n",
        "from IPython.display import Image, display\n",
        "\n",
        "# Setting xray to 1 will show the internal structure of the nested graph\n",
        "display(Image(graph.get_graph(xray=1).draw_mermaid_png()))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 563
        },
        "id": "Ganqjm9b9DRo",
        "outputId": "6bc73757-5d97-4682-f44f-003b2a2fcff9"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/jpeg": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "raw_logs = [{\"foo\": \"bar\"}, {\"foo\": \"baz\"}]\n",
        "graph.invoke({\"raw_logs\": raw_logs}, debug=False)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jhfjsE3S9GPb",
        "outputId": "6662ec0d-12f7-420c-cbba-ce3724e799b4"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'raw_logs': [{'foo': 'bar'}, {'foo': 'baz'}],\n",
              " 'docs': [{'id': '1',\n",
              "   'question': 'How can I import ChatOllama?',\n",
              "   'answer': \"To import ChatOllama, use: 'from langchain_community.chat_models import ChatOllama.'\"},\n",
              "  {'id': '2',\n",
              "   'question': 'How can I use Chroma vector store?',\n",
              "   'answer': 'To use Chroma, define: rag_chain = create_retrieval_chain(retriever, question_answer_chain).',\n",
              "   'grade': 0,\n",
              "   'grader': 'Document Relevance Recall',\n",
              "   'feedback': 'The retrieved documents discuss vector stores in general, but not Chroma specifically'},\n",
              "  {'id': '1',\n",
              "   'question': 'How can I import ChatOllama?',\n",
              "   'answer': \"To import ChatOllama, use: 'from langchain_community.chat_models import ChatOllama.'\"},\n",
              "  {'id': '2',\n",
              "   'question': 'How can I use Chroma vector store?',\n",
              "   'answer': 'To use Chroma, define: rag_chain = create_retrieval_chain(retriever, question_answer_chain).',\n",
              "   'grade': 0,\n",
              "   'grader': 'Document Relevance Recall',\n",
              "   'feedback': 'The retrieved documents discuss vector stores in general, but not Chroma specifically'},\n",
              "  {'id': '1',\n",
              "   'question': 'How can I import ChatOllama?',\n",
              "   'answer': \"To import ChatOllama, use: 'from langchain_community.chat_models import ChatOllama.'\"},\n",
              "  {'id': '2',\n",
              "   'question': 'How can I use Chroma vector store?',\n",
              "   'answer': 'To use Chroma, define: rag_chain = create_retrieval_chain(retriever, question_answer_chain).',\n",
              "   'grade': 0,\n",
              "   'grader': 'Document Relevance Recall',\n",
              "   'feedback': 'The retrieved documents discuss vector stores in general, but not Chroma specifically'}],\n",
              " 'fa_summary': 'Poor quality retrieval of Chroma documentation.',\n",
              " 'report': 'foo bar'}"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Custom reducer functions to manage state"
      ],
      "metadata": {
        "id": "F8gOJZHD9klW"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from typing import Annotated\n",
        "\n",
        "from typing_extensions import TypedDict\n",
        "\n",
        "\n",
        "def reduce_list(left: list | None, right: list | None) -> list:\n",
        "    if not left:\n",
        "        left = []\n",
        "    if not right:\n",
        "        right = []\n",
        "    return left + right\n",
        "\n",
        "\n",
        "class ChildState(TypedDict):\n",
        "    name: str\n",
        "    path: Annotated[list[str], reduce_list]\n",
        "\n",
        "\n",
        "class ParentState(TypedDict):\n",
        "    name: str\n",
        "    path: Annotated[list[str], reduce_list]\n",
        "\n",
        "\n",
        "child_builder = StateGraph(ChildState)\n",
        "\n",
        "child_builder.add_node(\"child_start\", lambda state: {\"path\": [\"child_start\"]})\n",
        "child_builder.add_edge(START, \"child_start\")\n",
        "child_builder.add_node(\"child_middle\", lambda state: {\"path\": [\"child_middle\"]})\n",
        "child_builder.add_node(\"child_end\", lambda state: {\"path\": [\"child_end\"]})\n",
        "child_builder.add_edge(\"child_start\", \"child_middle\")\n",
        "child_builder.add_edge(\"child_middle\", \"child_end\")\n",
        "child_builder.add_edge(\"child_end\", END)\n",
        "\n",
        "builder = StateGraph(ParentState)\n",
        "\n",
        "builder.add_node(\"grandparent\", lambda state: {\"path\": [\"grandparent\"]})\n",
        "builder.add_edge(START, \"grandparent\")\n",
        "builder.add_node(\"parent\", lambda state: {\"path\": [\"parent\"]})\n",
        "builder.add_node(\"child\", child_builder.compile())\n",
        "builder.add_node(\"sibling\", lambda state: {\"path\": [\"sibling\"]})\n",
        "builder.add_node(\"fin\", lambda state: {\"path\": [\"fin\"]})\n",
        "\n",
        "# Add connections\n",
        "builder.add_edge(\"grandparent\", \"parent\")\n",
        "builder.add_edge(\"parent\", \"child\")\n",
        "builder.add_edge(\"parent\", \"sibling\")\n",
        "builder.add_edge(\"child\", \"fin\")\n",
        "builder.add_edge(\"sibling\", \"fin\")\n",
        "builder.add_edge(\"fin\", END)\n",
        "graph = builder.compile()"
      ],
      "metadata": {
        "id": "Ko5nDADx9beC"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import Image, display\n",
        "\n",
        "# Setting xray to 1 will show the internal structure of the nested graph\n",
        "display(Image(graph.get_graph(xray=1).draw_mermaid_png()))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 707
        },
        "id": "3IdfursV9tOh",
        "outputId": "81b95931-c156-401c-b12f-824f02c075b3"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/4gHYSUNDX1BST0ZJTEUAAQEAAAHIAAAAAAQwAABtbnRyUkdCIFhZWiAH4AABAAEAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAACRyWFlaAAABFAAAABRnWFlaAAABKAAAABRiWFlaAAABPAAAABR3dHB0AAABUAAAABRyVFJDAAABZAAAAChnVFJDAAABZAAAAChiVFJDAAABZAAAAChjcHJ0AAABjAAAADxtbHVjAAAAAAAAAAEAAAAMZW5VUwAAAAgAAAAcAHMAUgBHAEJYWVogAAAAAAAAb6IAADj1AAADkFhZWiAAAAAAAABimQAAt4UAABjaWFlaIAAAAAAAACSgAAAPhAAAts9YWVogAAAAAAAA9tYAAQAAAADTLXBhcmEAAAAAAAQAAAACZmYAAPKnAAANWQAAE9AAAApbAAAAAAAAAABtbHVjAAAAAAAAAAEAAAAMZW5VUwAAACAAAAAcAEcAbwBvAGcAbABlACAASQBuAGMALgAgADIAMAAxADb/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/2wBDAQMEBAUEBQkFBQkUDQsNFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBT/wAARCAKyASEDASIAAhEBAxEB/8QAHQABAAIDAQEBAQAAAAAAAAAAAAYIBAUHAgMJAf/EAFkQAAEDAwEDBAoOBgYHBwUAAAEAAgMEBQYRBxIhCBMxdBQWIjZBVZSytNIVFzI1OFFUVmGTldHT1CNScYGSswlCdXeRoSQzU2JzhLElN0ZjcnaCJjSiwfD/xAAbAQEBAQADAQEAAAAAAAAAAAAAAQIDBAUGB//EADgRAQABAgEGDAQHAQEBAAAAAAABAhEDBBIhQVGRExQxM1JTYXGhscHRNHKi0gUVIzJCYvCBIrL/2gAMAwEAAhEDEQA/AP1TREQEREBERAREQEREBERAREQEREBeJpo6eMySvbHG3pc86AfvWmvF3qn1rbTamtdcHs5yWokbvRUkZOgc4ajVx0O63w6EnQArGi2e2aSRs90gOQVo6aq7aTuB+NrCNyP9jGtH0cSueKKYi+JNvP8A3+sttrYnKLM06G70IPxGpZ96dtVl8cUHlLPvX8GK2UAD2HoNBwH+is+5f3tVsvieg8mZ9yv6Pb4LoO2qy+OKDyln3p21WXxxQeUs+9O1Wy+J6DyZn3J2q2XxPQeTM+5P0e3wNB21WXxxQeUs+9O2qy+OKDyln3p2q2XxPQeTM+5O1Wy+J6DyZn3J+j2+BoO2qy+OKDyln3rIpLxQXB27S1tNUu+KGVrz/kVj9qtl8T0HkzPuWPV4Njtcwtnsdvfw03uxmBw468HAajjx4J+j2+CaG8RRaWlrMMY6ppZam52Vmrp6KUumqKdv60LvdPA8MbtXEe4OrQx0lgnjqYY5oZGywyND2SMcHNc0jUEEdIK466M3TE3gs+iIi40EREBERAREQEREBERAREQEREBERAREQEREBERARF5ewSMc09DhoUEa2eaVuOsvTwDPenm4ueNeLH/6kcf1YhG3930qTqNbNiWYLZaZ+omoqdtDKC3dPOQ/on8P/UwqSrnyjnau+VnlFo80zax7PMdqb7kVwjtlrpy1r53tc87znBrWta0FznFxADWgkk8At4uebebRZ71s2rae92e+3qjE9PK2PGonSXCCVsrXR1EIad7ejcA/hqdGng7oPAiK5pyrMXxmHCKuhhuF1t2R3WW3vnjtdbzlK2ON7pHGEQF5eHNa3myA4hznAEMdpKMy5QWB7Pp6KHILzNbZKukZXMD7dVPEcDyQ2SYtiIhGrXD9Ju6aHXTQriDqvaFX4bgeT5HY8gvsWL5zJPHvWvcvFTaOxpoYqmakYAecDpdHNa0OLQHbvErJ2y1OT55fr7SVdpz52O3PGou1u12CCalimq5mSidtxe0tMbmkxDm5nNj3d7gTqg7blW3fB8MvdNZ7neXm6VNE25U9HQ0NRWST07nOaJI2wxv3xq12u7qQBqdBxWl2e8oO1Z7tOzDDWUNfSVdjruw4Zn2+q5uoDYWSSPfI6ERxaOc5rWudq8NDm6hwUC2D41d4NpWE3O4WK5ULKXZZb7VNUV1FJFzNUyo/SwOc5o0eN3Ut6SND0EFSXZ/UXDDNvu0i2XHHr0abJ7lS3K3XinoXy0BjbQRRvEk7RuxOD4XN3XaE7zdNQUHcEREBRfDP+zq2+2RuggoKoPpmj+rDKwSBv7nmVoHQGhunxCUKMY0OysqymubrzXPQUTXEabxjj3nEfGA6Ut/a0/Euxh/sridkb7x6TKxySk6Ii66CIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAiIgIiIIxVskxK6VdyiidLaK14lrWRtLn08oaG881o6WENG8BxBG9x1dp4yTBMM2qUdvqL7Y7NldLCHPo5aynjqmMD9N4xkgjjut106dApUo7W4Ja6mqkqqbsq1VUpLpJbbUvp+cJ6S5rTuuP0uBK7GdRifv0Tt9/fwXRPKjQ5N+ykRuYNnGLhjiHFvsTBoSNdDpu/Sf8St1iOyTCcAuEtfjWJWWwVssRgkqLdQxwSPjJDiwuaASNWtOn0BfU4TUE8MovzR0aCaL/wDcSdpNR86r99dD+EnB4fT8JLRtShFF+0mo+dV++uh/CXJdu16yHZxe9mFJacnujoskyqms1b2Q6J5EEjXlxZpGNHdyOJ1/YnB4fT8JLRtWCWHeLPQZDa6q23OjguFvqozFPS1MYkjlYelrmngQfiK0faTUfOq/fXQ/hJ2k1Hzqv310P4ScHh9PwktG1HjyatkxGntbYt9kQeqsm28nzZjZrjS19Bs/xqjrqWVk8FTBa4WSRSNIc17XBuoIIBBHQQtx2k1Hzqv310P4Sdoccw3ay+XuujI0Mb64xBw+nmgw/wCfHoPBMzDjlr8JLRtZd4yB/ZD7XaObqry4cQ4F0VICP9ZMR0D4mahzzwGg3nNz7JZ4LDa4KGnLnMj3nOkkOr5HucXPe4+FznFzifjJXq12iislIKWgpYqOnBLubhYGguPS46dJPSSeJ8KzFiqqLZlHJ5giIuJBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQFXflad9Owb+8Ch8yRWIVd+Vp307Bv7wKHzJEFiEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQFXflad9Owb+8Ch8yRWIVd+Vp307Bv7wKHzJEFiEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQERRu9ZRVRXGS3WijirauFrXVElTMYoYN73LdQ1xc8jU7oHAaEkat15KMOrEm1K2ukiKEezuYfILH5XN+Gns7mHyCx+VzfhrscVr2xvgsm6KEezuYfILH5XN+Gns7mHyCx+VzfhpxWvbG+Cybr8OeVNsTm2C7ab5jQieLU9/Zlqkdx5ykkJLOJ4ktIcwnwuY5fsf7O5h8gsflc34a47t55Pc3KCvWH3K/0Fnjmx6tE5bHUSuFZTkhz6aTWP3LnNbx6QN4D3WqcVr2xvgs8f0fmw32oNhtNcq+DmsgyksudXvN0fHDu/6PEf2McX6HiDK4eBWcUIF7y9oAFvsYA4ACrm/DT2dzD5BY/K5vw04rXtjfBZN0UI9ncw+QWPyub8NPZ3MPkFj8rm/DTite2N8Fk3RQj2dzD5BY/K5vw16bkuU0h52qs9tqqdvF7KKsfz274dwPjDXH6C5uvxpxXE2xvgsmqLGt1xp7tQU9bSSCamnYJI3gEatI1HA8R+w8QsldSYmJtKCIigIiICIiAiIgIiICIiAiIgIiICIiAiIgIiICgNlOuTZnr4Lqwa/8lSqfKA2TvmzP+1mehUq72S/z7vWFjW3aKu+2rahkFqz/ACCy0ma0ez+jsuNC90slVSwSm6zF8oLNZgf0bObaC2PR5MnT0BYmLZJtHzbMsOxx2WVeNRVGAUV8ubzb6WWs7NfKWO034t1pPQ4Fug3dA0E6jWdF7Ismiq3n+2fKsdzipuuP3+7X/GbfkNLZ7hSmx0sdrg3544JYeyi4Tvma6T3TA5gdo0gcV9Mr2h7Q6exbYsroMtbS0uD3mWKis5ttO+Kphjgp5nxzSFu/oRI4AsLXA6kudwAZ0Czs88dNDJNNI2KKNpe+R5Aa1oGpJJ6AF8bbcqS82+mr7fVQV1DVRtmgqqaQSRSxuGrXtcCQ5pBBBHArgeVZJmO1HI9oltsOStxKw4rQRRPiZQRVU1xqJ6Tsh3OGQHciax7GgM0cSXHeGgUY2R3HLr/T7LsPsuX1GL2r2taK6vNLQU1RI6cOjiB1mjdoNDxH0cNDxTO0i1iKsQ2yZNfcHtVsfkddQZxHfblZHMxmywVc937Ckcx80bKg81CzTcc5zjoCdARqFiWXa/tDzDG9mdFDd22O/XLKLlj92qpLfC50kdMyp1eYtXtZJpE12jXFu+P6ze5LOgWoRVoyrPNoc20O54Pj1fklc3GaCkkrbtabZapqqsqKgSPaZm1MkMbIw1gAETNSd7VzdBrl2bK9qWXZlhuL3e6uwO5VmM1txusVLRU1RKJoauKFj4y/nGML2vDiNXgBxHTo4M4WKfIyPd33NbvHdGp01PxL0qhXu8ZRtRsmxOrrcmqLVeocyr7RUVlupKfSSaBlbE2pDJI3gOLYT3Puf0ruHBpFt6KGSmo4IZqh9XNHG1j6iRrWulcBoXENAAJ6dAAOPAKxNx52XHXB6D6HzgfQBM/RStRTZb3j0H/En/nyKVrr5Tz9ffPms8siIi6yCIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAoDZO+bM/7WZ6FSqfKD3Omqsav1yrRRVFdbrnIydz6OIyyQSiNkRDmNG8WlsbSHDXjvA6dzr3clmL1U65j1iVhw/lB7OMjyjPbVeLLYsguZpaAQw1Vpu9thZTy8452phrYX7pOrdZIjq4BoLTuBT/Zzs7udFWWbLsurzW52MfistxdSlgpH7splLw0MB395xBI0b8TQpP2503iy/fYlX+EnbnTeLL99iVf4S7PAV3vmyubOxzy/8l/Hr+bxC7IMlobXcrgbubVR1zGUsFcZBKaiNpjJJ5wb+48uZvHXc6NN/X7D7FcMXz+xS1dxFJmtVNV3F7ZIxJE+SGOFwhO5o0bsTSN4O4k/sEk7c6bxZfvsSr/CTtzpvFl++xKv8JXgK+jJmzsQ3JuT3ZsgyGrvNJfshxuruFHHQXNtkrWwx3GONpYwzNcx3dNaS0PbuuA4aqGS8nSvh2j43TWq95DYMXsmFssUN5tldBHVSSMnbuxSBzDrrGN4uEYGoGhB4LsvbnTeLL99iVf4S1t32sY/j8tviuhuVtluFQ2ko2VdrqYjUzu1LYow6Mb7zodGjUnRTgK+jJmzsRt3Jxxujs+MUVluF5xuqx7sgUl0ttU3st4qCDUc66VjxJzjgHOJbrqAQQveM8nbHMUnsklHcLzK2z3qpvtKyrqmzfp6iF0UrXuczfc07738Xb2+4ne07lTPtzpvFl++xKv8JO3Om8WX77Eq/wAJXgK+iZs7EazXYlbMuypmTUl7vuKX40ooqiux+rZC6qgBLmsla9j2u3STo7QOGvAra27Zjbbdl1myMVtxqbja7K+xRGqqBKJYXPieZJHOG++TWFvdb3HV2oJOo2HbnTeLL99iVf4SdudN4sv32JV/hJwFfRkzZ2IbVcnnH6jDqTH4rleKI0N6mv8ARXSlqGMrKWrlllkcWO5vd3f00jd1zSN06HU8V0Wz291ptVHRPrKm4Op4WxGrrHB0026NN95AALj0kgDj4FrO3Om8WX77Eq/wl6blL6w81QWW8VFS7gxk9vmpY9fjdJK1oA+M8T8QJ4JwNcarGbLa7Le8eg/4k/8APkUrWpxSyOx3HqG3vkE0sLP0kjRoHPJLnED4t4lbZefj1RXi11RyTM+aTyiIi4EEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBV35WnfTsG/vAofMkViFXflad9Owb+8Ch8yRBYhERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBV35WnfTsG/vAofMkViFXflad9Owb+8Ch8yRBYhERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEXh80cZ0e9rT8ROi89lQ/7aP+IK2kfVflrtx/pAKzM8qw+C4bNn2GvwrJo7rUUkl6510skG+x0B/0du4dSe67rTToK/UXsqH/AG0f8QX5nf0hXJprZ9tePZJilKKlubVMdvmij9zHcODQXEcGiRmjtfjjkcUtIuJyUuUhcuUzi94yCfDDilrpKltJSym5dl9lv3S6XQc1HuhmsfHjqXEcN0ruShOx/Z7aNj2zTH8PtcsRprXStifKNGmeU91LKR8b3lzv3qY9lQ/7aP8AiCWkfVF8uyof9tH/ABBfVLAiIoCIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAtBnV1qLNjNRPSSCGpkkhpo5SAebdLMyIPAIIJG/qNQRqOI0W/UT2od6Q/tG3emwLsZPEVY1ETyXjzWOWGpGA445v6eyUNbKTq6esgbPLI7hq5z3guc46DUkklPa+xb5tWfyCL1VsL/AH2hxexXK83Ofsa226mkq6qfcc/m4o2l73brQSdGgnQAk+AKJ4ftxwnO7zBarNeXS3CopzVU0NTR1FL2TCNCXwmWNolaAQSWE6L0OHxI/nO8vO1vPa+xb5tWfyCL1U9r7Fvm1Z/IIvVWhxXbtg2a5L2v2i+c/dnNkfFBNSTwCcM92YnyMa2Xd8O4XaDilg264PlFbV01svRqTR9kdlzmjqGU9KYHObKJZnRiOMt3SdHOBI0cNQQTOHxOnO8vO1vva+xb5tWfyCL1U9r7Fvm1Z/IIvVUasXKE2f5Ga0UN/DnUlHLcHtno6iAyU0Y1fLEJI2880DjrHvdI+ML7Yzt4wbMLlHQWi9mrqZaV9ZTjsOoY2qhYAXuge6MNm3dRqIy4jwhOHxOnO8vO1v8A2vsWH/hq0eQReqvrYoIcVyq3223RtpbZcIZi6iiG7FHJGGkOY0DRuoLgQNAeB011Khew3bnbttljqaumoqy31cFRURvgmo6hkYjZUSRRuE0kTGPc5rA5zWklhJa4AhTWo7/sY/8ARV+Y1ajEqxaZiqbxafKViZnlTxEReMyIiICIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAiIgIiICie1DvSH9o2702BSxRXacwuxF56Gx1tDK46Hg1tXC5x/cAV2cm5+jvjzap5YQrb5/3FbRv/bdy9FkXHLBcLxtTvGx4WXFb3a4sTpXV9Zdr1QupIHE0DoGQQud/rQ97wXFmrd1uupVkL/YqHKLFcrNc4OybbcaaSkqoN9zOcikaWPbvNII1aSNQQR4CvtbbdT2i3UtBSR81SUsTIIY94u3WNAa0anUnQAdK7ExeWVRMOt+U3XPdkt+vtpz6tyKguc4ySqusEzbfRyzUs0QbTxA83zW+4DnYmloYAXu4hSu27LMhyLkmZzitHQTWzIbpX3iSGnq2Op3z71fK9gO9pwkjDWhx4FrgddFZlFIpFWaHFrJmNlu1VBiG0umyS24/cDTdtVXcJ4KeeWmdC6CETzObK9weQDG1wIbrqDoFJrXjF3huHJqebTWsFpoJori40zx2FraSzdm4fo9ZAG6O07oAdKsAiZo4tybZ6/GrTc8Hu1hvFuuNtudzquzqihe2hqYpa6SWN0M/uHktmad0HUbrtQNF1Co7/sY/9FX5jVuVqJWGTPsb3RruQ1b3cOhu6wa/4uA/euXD0X7p8pWE6REXlIIiICIiAiIgIiICIiAiIgIiICIiAiIgIiICIiAiIgIoptH2qYnsjsD7zl19pLHQDUNdUP7uUj+rGwaukd9DQSuHHaDtg5Rv6LAbXJsrwaXgcryCnD7nVxnw0tLrowEdD3niCCCCNEHVdrvKCwnYpTQ9sd13rpU6CjstAzsivq3E6ARwt48Tw3jo3XhqoDiVXto2zZJQXi8UNHsx2eRS77serYG1l0u8JGhjqd7uYGOB9yO6HEEHgVMNkfJrwvZBUy3Sipp73lVTq6rya+S9lXCocfdHnHe4B+JgAOg116V1VOQRB2z6WICOiye80NO3gyFvY8wYOGjQ6WF7yBp4XE/SvHaBcPnne/qKL8upki7XGcXbG6PZbyhvaBcPnne/qKL8unaBcPnne/qKL8upkicZxOzdHsXQ3tAuHzzvf1FF+XTtAuHzzvf1FF+XUyROM4nZuj2Lod2g3D553r6ii/LqObQtmmYPx+OfZ/l7bRlkNQ2d9deqVlTHXRta4diy7rQIoiXb2sbdQRrprxXVEWasfErjNmdHZER5F1dcb5WMmJ3qmxjbVjsmza/yu5unurnGWy15+OKp4iP49157kaau14Kw1PUxVlPFPBKyeCVofHLG4Oa9pGoII4EEeFa/JcXs+Z2WptF+tlJeLXUt3ZqSthbLG8fS0jTUeA9I8CrvVcnXOthc8ty2F5JvWfeMkuA5LK6agf4SKaYnfgcfACdCT3TtBouuiziLhOzblbY7k1/bieZ26r2aZ4NGuseQaMZO48AaefgyVpPR0F3gB6V3ZAREQEREBERAREQEREBERAREQEREBERARFg3ytkttluFXEGulp6eSVgeNQS1pI1+jgg+WSZPaMOs1Td77c6S0WumbvTVdbM2KNg+lzjp+weFV5qOUTm+3Goltuw3GwbRvGObPslifBb4/ATTQkb87h4CRoCO6bodVHuT9sYp+UbieObV9rd3q87uNwD6mhsNUBFabaBI5gDKZvcvdo3iX66g8QSNVbWmpoaOnigp4mQQRNDI4o2hrWNA0AAHAAfEg4ls45J+P43f2ZbmVxq9pWeEhxvl/AeynOuoFNT8WQtB4jTUt8BHQu5IiAiIgIiICIiAiIgIiICIiCI7Stk+I7X7A6zZfYqS90R1LOfbpJC4/wBaOQaOjd9LSCuDnZ7tk5NX6bALpJtWwOHicUv84bc6SMf1aap00eABwa4cBoAwnirTIg5Hse5T+E7ZKmS1UdTPYcspyW1eMXyPsWvgePdDcd7sD4266DTUDoXXFzPa/wAnXBttsUMmRWox3emIdSXy3P7Hr6VwOrSyZvHgeIDtQDx01UH5MeRZZR55tT2c5NksuX0+GVFvjt92rYGsq5IqiB0u7M4Huy3Ro3jxPEk8QAFhEREBERAREQEREBERAREQEREBERAWpyzvVvPUpvMK2y1OWd6t56lN5hQci5D/AMFTZ51KT+fKu5rhnIf+Cps86lJ/PlXc0BERAREQEREBERAREQEREBERAREQFXbYR8KflIdZsXoL1YlV22EfCn5SHWbF6C9BYlERAREQEREGPcav2Pt9VVbnOcxE6Xd1010BOmv7lFKTLchrKWGoZYbcGSsbI0Our9dCNRr/AKOpFkfe9dOqy+YVH7D7x27q0fmhcMUVYuNmZ0xFr6Lbe2Jai1nvtlyTxFbPtWT8unbLkniK2fasn5dZaLs8UnrKvp+0vGxidsuSeIrZ9qyfl07Zck8RWz7Vk/LrLROKT1lX0/aXjYxO2XJPEVs+1ZPy6dsuSeIrZ9qyfl1lonFJ6yr6ftLxsYnbLkniK2fasn5dO2XJPEVs+1ZPy6y15kkbDG6R53WNBc4nwAJxSesq+n7S8bGN2y5J4itn2rJ+XWrynI8idjN3DrHbWtNHMCRdJCQNw+Dsdc92T55tC2pU9py5lLjtrwa6OfLT0EzZ33PsXVwjldIHc2HO0a7c3dAHe6JC4tsxz7M8B2F4lUVNLY6jC7tcqqyNij572QjdPVVDGTF5PN6c5wLA3Xd0O9rqBji09ZV9P2l42OrcjG+3yl5MWBRUtooKinbRyBkstxfG5w5+TpaIXaf4ldp7Zck8RWz7Vk/Lr89OT1XNq+TdTRGhpaaamzzHon1FPzm/UgzUjmukDnuG8GuDe4DRo0cNdSbR7QNoWaZVfs7xvC6axwWzGaAMutbexM99TPNTmUQwCNw3N2MtJkdvcXgBp0KcXmrTwlX0/aX7HaO2XJPEVs+1ZPy6dsuSeIrZ9qyfl1BOTf8AB92bf+3aD0di6MtRkkzHOVfT9peNjE7Zck8RWz7Vk/Lp2y5J4itn2rJ+XWWivFJ6yr6ftLxsYnbLkniK2fasn5dO2XJPEVs+1ZPy6y0Tik9ZV9P2l42MTtlyTxFbPtWT8unbLkniK2fasn5dZaJxSesq+n7S8bGJ2y5J4itn2rJ+XW4xe9SZDZo62WnbSymSWJ8TJOcDXRyOjOjtBqCW69A6VhLzs772B12t9KlXWqw6sHGppz5mJieW2qadkRtNEwkqIi5mRERAREQFXbYR8KflIdZsXoL1YlV22EfCn5SHWbF6C9BYlERAREQEREGuyPveunVZfMKj9h947d1aPzQpBkfe9dOqy+YVH7D7x27q0fmhTB+In5fVrUzkRF6jIiIgItXdchhtlRHSsgnr66Ru+KWkaHPDNdN928QGt14akjXjproVr+2u4/NC9/WUf5hcsYVVUX9YjzWySL+OaHtLXAOaRoQegqOdtdx+aF7+so/zCdtdx+aF7+so/wAwtcDV2b49yyE7PNjWSbNJ6C1WnPXuwagme+lsVRao31EcLi4in7KL9TG0u4dxvAADe0VNeW1spzDYrg+BPtmW3WrxmjdJSTx00slNBHW9kz1UM/NCQgPIlc0P6RzA4jUBfoB213H5oXv6yj/MKGbZMdfth2Z3/Ea/D7w1lxpiyGZzqM8xMO6ik/8AuP6rw06eEAjwriqyaqYtFt8e5Z+cvI32a5jtnzOezWzK7nYMetBivFS+N7paYVUZb2KXQFwY92+xpG9/VicARoF+h192GZBNk17vWP517AyZHRQ01+gfaWVMdVLHFzQqIg6Qcy/c4Ed2DoNQdFFuSfsouPJ32Yiy1mK3GsyCsqHVVyq6SWkdE9/uWMYXTtdutYB0gcS46DVdo7a7j80L39ZR/mFKMmqiNNt8e5Z/dm+H+19s+xrGOy+z/Ya3U9v7K5vm+e5qNrN/c1O7ru66anTXpKkajfbXcfmhe/rKP8wnbXcfmhe/rKP8wuXgauzfHuWSRFG+2u4/NC9/WUf5hZVBk7KmsipKy31loqZtRCytazSUgalrXsc5u8Bqd3XUgOIBDSQnCriL+sT5Fm6REXCgiIgLzs772B12t9KlXpednfewOu1vpUq8zKOfo7qvOlrUkqIiMiIiAiIgKu2wj4U/KQ6zYvQXqxKrtsI+FPykOs2L0F6CxKIiAiIgIiINdkfe9dOqy+YVH7D7x27q0fmhSDI+966dVl8wqP2H3jt3Vo/NCmD8RPy+rWpnIiL1GRERBHMcdzmTZW53umVcMQP+6KaJwH+L3f4qRqN4z3yZf1+H0SBQ7NdoGWVm0xmCYPT2eK4U9rbd7jdL62WWCGN8jo4omRROa5z3FjySXANDfCToubH0VR3R5Q1PK6qirZdPbEdykHMsxxmLJDgdI6ulrm1D6MOFdU9zExpa8hzvC5w3Rx0d0L623abWbSMm2A3+otNsjo75JXl0MgmdU0NZFR1HOOikbI1jmHcczR8buBJ4HTTrZzKxyKr+zfaJcsJ2QWa24/Q01wyjI8xvFstsVc9zaaN3Z1XJJNKW90WMZG4kN4k6AdOqlGwtuQs247X25RJbJru2Gyh8tojkjp3t5ifdIZI5zmnTpG8f2pFV7DvCKHbYMvu+BbNL/f7FaTe7rQwCSGi3XuDu6aHOLWd0WsaXPIbxIaQOK4jtEz3NMl2R4neLRl2L1U9Zl9rpm3HH4qk000T6iINZIzng5ukhIkjLjvNGnck8LNVhZ9Fw/a5tRy/Z1TWKjhvWIuvs1JJNUUs1suFRLVyM01MFPTue+OLwGR5cGnTpWDHt2yzNJ9ksOI2+z0Zzay1dzqZLu2WZtC6FtOe5DHsMg1le3TgTq06t0OrOgd+Udz53N48yQe7ZXUTmn4j2VFx//v2dC5Jsyq9oNTyiNoNJc7/aKq00ENq7KpGUVQNA+nlLext6oLYe71L9Wu3uHQeK6ztB72j12i9KiXPk83xaO+PNY5YSRERcSCIiAvOzvvYHXa30qVel52d97A67W+lSrzMo5+juq86WtSSoiIyIiICIiAq7bCPhT8pDrNi9BerEqu2wj4U/KQ6zYvQXoLEoiICIiAiIg12R97106rL5hUfsPvHburR+aFIMj73rp1WXzCo/YfeO3dWj80KYPxE/L6tamciIvUZEREEbxnvky/r8PokCjOc7JrpeM5psyxTKTimQtofYurdNQNrqarpg8yMa+IvYQ9rnOIeHA90QQQpCyupsVyO7yXOaOipLlJFPBVzO3Yi8RtiMZeToHdw0gHTeDuGujtM7t4xzx/a/LY/WXZxcOquYmmJmLR5Q1MTPIjWM7Ma60bQmZdc8hN6uBx6Cxz71E2AyvjqJJjP3Lt1uvObu4G8N3XU6rQYhyfu1Wi2YU/s92V2k1NdUb3Ye52b2RFPHp/rDze7z+uvda7vg14dE7eMc8f2vy2P1k7eMc8f2vy2P1lw8BX0Z8UtLlU3JpqIrNNRW7MKignochlyPHqsULHvtc0rpHTRPBcBPE4zSDQ7p0Omp0WfjmHZFsovuUZXcZrhtIu+SOooZqayW+mojTCCOVoeBNUtaWHeA90XA6dIJI6N28Y54/tflsfrJ28Y54/tflsfrJwFfRnxLSi0mUZPm1HV2mgx3I8BrpY96C+3OC31MMLmuB0MUdU8u3gCNNB0niDookzk0SzYhklJV5U52TXm+U+Qm80luZBBT1kBiMTmUu+Rp+iG8C4l2pJOq6sM4xw/+ILX5bH6ydvGOeP7X5bH6ycBXPLTO4tLnNdsWyqqyWmyWLPYqTIZrT7C3WsjsjC2pgE8krHQMdKeYe3nHDUmRp0BLToveA7AXYPU7OpDkBr2Ybba+1xNNHzbqmKofEYy4753XMbE1p4HfJJ7noXQ+3jHPH9r8tj9ZO3jHPH9r8tj9ZOAr6M+JaUVdsuulv2tV2ZWTJRbqS7RUsV4tM9A2cVXY++I3Ry77TEd15aeDteBUh2g97R67RelRLJ7eMc8f2vy2P1lrb7d6DLIILVaayC4zPqqeWV1LIJGQRxyskc55B0aSG6NHSS4cCAdObBw6qMSmqYmIibrETdLURF1mRERAXnZ33sDrtb6VKvS87O+9gddrfSpV5mUc/R3VedLWpJUREZEREBERAVdthHwp+Uh1mxegvViVXbYR8KflIdZsXoL0FiUREBERAREQa7I+966dVl8wqP2H3jt3Vo/NCkGR97106rL5hUfsPvHburR+aFMH4ifl9WtTOREXqMiIiD+OaHtLXAOaRoQRwKx/Y2k+SwfVj7lkorEzHIMb2NpPksH1Y+5PY2k+SwfVj7lkomdO0Y3sbSfJYPqx9y1mUW6kbjN3IpYQRRzaERj9QreLV5V3sXjqc3mFM6do5FyNKSCp5MmBSzQxyyOo5C572Ak/p5Okldo9jaT5LB9WPuXHeRb8F/AOpyfz5F2tZpqnNjSMb2NpPksH1Y+5PY2k+SwfVj7lkotZ07RjextJ8lg+rH3L7RRMhZuxsbG39Vo0C9okzM8oIiKAiIgLzs772B12t9KlXpednfewOu1vpUq8zKOfo7qvOlrUkqIiMiIiAiIgKu2wj4U/KQ6zYvQXqxKrtsI+FPykOs2L0F6CxKIiAiIgIiINdkfe9dOqy+YVH7D7x27q0fmhSDI+966dVl8wqP2H3jt3Vo/NCmD8RPy+rWpnIiL1GRERAREQEREBavKu9i8dTm8wraLV5V3sXjqc3mFQco5FvwX8A6nJ/PkXa1xTkW/BfwDqcn8+RdrUp/bAIiLQIiICIiAiIgLzs772B12t9KlXpednfewOu1vpUq8zKOfo7qvOlrUkqIiMiIiAiIgKu2wj4U/KQ6zYvQXqxKrtsI+FPykOs2L0F6CxKIiAiIgIiINdkfe9dOqy+YVH7D7x27q0fmhSDI+966dVl8wqP2H3jt3Vo/NCmD8RPy+rWpnIiL1GRERAREQEREBV+5SHK3w/YZc34pkFuvdTcLlajVQzW+nifCGvdJGA4uladQYyToDwI/YrAqrH9IRsSG0rZA7JbfTmS+4tv1Y3B3UtIdOfb/8AEASfQGOA90sV3iLwINyPOWFiFFh2z7ZW2zZDV5K53YJkp6WF1M1z5XuLy4zB241rt5x3dQGngVeBUB/ozNiWguu0+5wDjvW20B7f2c/MP8owR/5gV/lnDvm6QREXKCIiAiIgIiIC87O+9gddrfSpV6XnZ33sDrtb6VKvMyjn6O6rzpa1JKiIjIiIgIiICrtsI+FPykOs2L0F6sSq7bCPhT8pDrNi9BegsSiIgIiICIiDXZH3vXTqsvmFR+w+8du6tH5oUgyPveunVZfMKj9h947d1aPzQpg/ET8vq1qZyIi9RkUcrXT5DfKy1x1k9BR0Ucbpn0rg2WZ794hm9oS1oAB7nQkuHEAEOkajdi78cn/5X+WVzYWiKqtcR6xDUP72jUvjO9/as/rJ2jUvjO9/as/rLOyPLLHh1AK6/wB5t9joi4MFTcqplPHvHoG88ga/QoXdtu2O2XOrZZquvtlPYq6xz3puRTXKNlMBHPDCIwT3J3ue1Dt/+rpoddQ4fEj+RnSk3aNS+M739qz+snaNS+M739qz+ssHJdpdvs9biVLQ1NquMuQ1jYoGSXeCne+nLS508DXHWo3TzY3I9SecB1Xz2fbTafNbBfrtVU8dlprTd7hbJXzVIczdpZnRGZziGhocGb2h9z8Z6VOMYnJnGdLZdo1L4zvf2rP6y8T7P6GphkhmuF4likaWPjfc5y1zSNCCC7iCtFh+2izZ3tHuuNWKehu9BQ2qnuQvFur2VEUjpZZozFowEAt5rXXePuugacZ1crnR2a31FfcKuChoaaMyz1NTII4omAalznOIDQB0kq8PiT/IzpReybKbHjNrp7ZZ33C1W2nBbDR0NdLDDECSSGsaQBxJPAdJKzu0al8Z3v7Vn9ZYsu13BKdte6XNcdjFA8RVZfdYB2M8nQNk7vuDqCNDovnfdpVBbr5iVtoam1XGXIJzzbXXeCGTsYRufz8MbjvVA1DRpH4H666BTh8TpGdLO7RqXxne/tWf1k7RqXxne/tWf1lGtqW3THtm1PzDa62XTIBWUVKbGLlHFVBtRURw85ud07Rok3vc8dOka6rL2tbZce2S4zeK6uuVsfeKO3T19LZKi4R09RW82xzt1gOruJbpqGn9hTjGJ0kzpbrtGpfGd7+1Z/WTtGpfGd7+1Z/WWnxDah2153d8b9jOxewLTb7p2Tz+/wA52Vzv6Pd3Rpu8106nXe6Bpx31nzzGciutXa7VkVpudzpNRUUVHXRSzQ6HQ77GuJboeHEK8PidJc6WHUQTYhPRTxV1VWUE9RHSzQVsxlLDI4MY9j3d1rvEAgkgh3gIUpUbzz3poP7Vt/pcSkitf/qimueXT6e5OmLiIi4GRednfewOu1vpUq9Lzs772B12t9KlXmZRz9HdV50taklRERkREQEREBV22EfCn5SHWbF6C9WJVdthHwp+Uh1mxegvQWJREQEREBERBrsj73rp1WXzCo/YfeO3dWj80KQZH3vXTqsvmFR+w+8du6tH5oUwfiJ+X1a1M5EReoyKN2Lvxyf/AJX+WVJFG7HwzLJx4f8ART+7mz9y5sP9tfd6w1HJLj21e5WHEuUZYMhz+OJmHjHJaS2V9fAZaOkuJqN6XeOhbG98O4GudpqGOAPgXzoaXEc35ROEVNtttBXY+MLuM9BG+hDImHs2mZvsje0buoc8a6DUOPgKsSi62ayp5i9LDTYFsggiiYyKh2qV1HTNDR+hhbLct2NvxNGg4fQPiWHeKiNuzfKLTcKapnt1k2ny3DKrY2ne5xtMtdLK2RzANZInDm5Du6gta74irnopmCu2x2/4jk3KSzC4YW+hmtEmL20Ga3Qc1FJIKipBI0aA4hu4NRr7nTwaCe8pr4PG0j+wK3+S5TTKcXpcutraKrqrlSRNkEvOWu4z0MuoBGhkhexxHH3Ouh4cOAWnxvZda8XusdwpbpklVMxrmiO5ZFXVkJ1GnGKaZzCfiJHDwK2m1hyagw+wx8obZxGyy29sceC1m4wUrNG7s1I1ug08DXvA+hzh4SoNs5p4o8O5Pm7GxvMZpeaaIho1ZE11za1g+JoDWgD6ArhImaKHS3jE6DY3DjV5hp4drUOYUs93jq6Q9mvqDd2E1HOFvFjoiA14O7uuDQeOi2+0i8YnYMa5RFpzWGnjz65zV9RbXXCkMktVQ9jt7CNO/dILI9NO5PcOa4nTpV2kWcwVTupukGXbQrRanTUuSZHs5oW2Ata5vZM0MVUHtjf0B7TIzhrqN4FY2wCy4JkN/wADdQZtcqrI8fpnTNx11mo6OSgfzBhmhqHQ0kb2gc4Ruvf3RaD3Wmqtqi1m6biN55700H9q2/0uJSRRzPONqoB4fZWg9KiKka7NXNU98+i6hERcKC87O+9gddrfSpV6XnZ33sDrtb6VKvMyjn6O6rzpa1JKiIjIiIgIiICrtsI+FPykOs2L0F6sSq7bCPhT8pDrNi9BegsSiIgIiICIiDXZH3vXTqsvmFR+w+8du6tH5oUgyPveunVZfMKj9h947d1aPzQpg/ET8vq1qZyIi9RkWmutmqjXeyNqqYqSvdGIpW1EZkhnYCS0OAIIcC46OB8JBB4ablFqmqaZvC3sje7l/wCvZP4JvvTdy/8AXsn8E33qSIuXhf6xuW6N7uX/AK9k/gm+9N3L/wBeyfwTfepIicL/AFjcXRvdy/8AXsn8E33rGudXlttttXVuNle2nifKWhkwJDQTp0/QpatXlXexeOpzeYVOF/rG4ugGyLaLk+1zZxY8vpaa02+nusTpWU03OvfGA9zdCQdD7lS/dy/9eyfwTfeucci34L+AdTk/nyLtalONMxE5sbi6N7uX/r2T+Cb703cv/Xsn8E33qSItcL/WNxdG93L/ANeyfwTfem7l/wCvZP4JvvUkROF/rG4u0FNZrjX1dNUXqpppW0r+dhpaOJzGc5poHvLnEu01Og0ABOvEhpG/RFx1VzVypM3ERFhBednfewOu1vpUq9Lzs772B12t9KlXmZRz9HdV50taklRERkREQEREBV22EfCn5SHWbF6C9WJVdthHwp+Uh1mxegvQWJREQEREBERBrsj73rp1WXzCo/YfeO3dWj80KQZH3vXTqsvmFR+w+8du6tH5oUwfiJ+X1a1M5EReoyIiICIiAiIgLV5V3sXjqc3mFbRavKu9i8dTm8wqDlHIt+C/gHU5P58i7WuKci34L+AdTk/nyLtalP7YBERaBERAREQEREBednfewOu1vpUq9Lzs772B12t9KlXmZRz9HdV50taklRERkREQEREBV22EfCn5SHWbF6C9WJVdthHwp+Uh1mxegvQWJREQEREBERBrsj73rp1WXzCo/YfeO3dWj80KQZH3vXTqsvmFR+w+8du6tH5oUwfiJ+X1a1M5EReoyIiICIiAiIgLV5V3sXjqc3mFbRUP/pI6zaDhd4xvJseyu+WjGK2kNqqqS2XCanhbUNdJIHPax4aTIx5HRrpCdfAsVTmxcWF5FvwX8A6nJ/PkXa1+V/IPbtB2hbWbLaabMcjpMMxwC4VlDBdJ2Uu412scHN725pJJpq3Ti3nPpX6oKYc3pBERcgIiICIiAiIgLzs772B12t9KlXpednfewOu1vpUq8zKOfo7qvOlrUkqIiMiIiAiIgKu2wj4U/KQ6zYvQXrJ5clmzG4cn+6XLB79dLDeLFOy7SvtFVJTzVFNGx7ZYy+NwO6Gv5zTw80OGui/KzZ1n21bJ9ocNDjOa5MzJ8mq6enmqIbvUMkq5B3EZneHavDGk8Xa7rdfAg/dNFqcTss2N4rZrRUXCpu9RQUUNLJcKx5fPVOYwNMsjjqS9xG8SekkrbICIiAiIg12R97106rL5hUfsPvHburR+aFIMj73rp1WXzCo/YfeO3dWj80KYPxE/L6tamciIvUZEREHmWVkET5JHtjjYC5z3nQNA6ST4Ao8c2ikAfTWi71cLuLZoqQhrx0gjeIJB+PRfzPu6slNEeMc1yoYpGnocx1VEHNP0Eag/QSpIueIppoiqqL3v4W911XRvtzd83735K31k7c3fN+9+St9ZSREz8PoeMreNiN9ubvm/e/JW+soNtusFLtn2X37EqywXiM10B7HqH0gPMTt7qKTg7XQOA106RqPCuuopNWHOjM8ZLxsVq5I+yd/J02cTW24WSvrMluNQ6ouVZRU29G7QlsUbHO3XFrW8eIHdPf4F3Htzd83735K31lJESKsOItFHjJeNiN9ubvm/e/JW+snbm75v3vyVvrKSIrn4fQ8ZLxsRvt0I4usN7a3wu7E10/cHE/4Bby33CnutHHVUsnOwv10OhBBB0IIPEEEEEHQggg8VkKN4/wDo8ryiJvcxmWnm3R0b7ogCf3hjf8EtTXTMxFre8R6nKkiIi4GRERAXnZ33sDrtb6VKvS87O+9gddrfSpV5mUc/R3VedLWpJUREZFg3i80lio+yayQsYXBjGtaXPkeehrWji4n4gs5QrJjzu0Kwxu7pkdurZmtPQH85TN3v27rnD9jj8a58HDjErzZ5NM7ousRd9ztGi14WG+OHgIowP+rtV/PbHj8QX3yRvrrMRdzMwej4reNjBk2hQTRujkx29vY4Frmuo2kEHpBG8qm8njku0GxPb5k+bzWivrLODIMapIqUmWjbKTvmQO0AcxpMbS1ztWucTodArgImZg9HxLxsYftjx+IL75I3109sePxBffJG+usxEzMHo+JeNjFZtIom91VWy7UEA91UVFGebYPjcWk6AeEngPCpWx7ZGNexwexw1DmnUEfGo8sbZef/AKNgj6GQVdZTxt8DY46qVjGj6A1oH7lxY2FRFGfRFtMRvv7JquliIi6KNdkfe9dOqy+YVH7D7x27q0fmhSDI+966dVl8wqP2H3jt3Vo/NCmD8RPy+rWpnIiL1GRERBG8996rf/a1v9KiXx2qZ/TbLNnl+yurp31kVrpjMKaM6OmfqGsYD4N5xaNfBrqvtnvvVb/7Wt/pUS+ufYRbdpGGXjGLw17rbdKd1PMYnbr2g9DmnwOaQCOniAuarmabbZ9F1OM7WXbSJNgW0mbNe1mOklxiseymsrKgTU8piP6Nz5HFsgA3u6AbxA4aFbLEc8z+1ZHYcSv0OORyX/H6itslVQMne2lnp2xAxVIc4c63SZh3mc3ruuGg1BGxrNjea5Dg+R4vkm0kXuhulnntUL/YOOF8TpAGieUiQmV4Go0BY07x1GuhEpqtmPZOdYRkfslu9rNurKDsbmNeyefbAN/e3u43eY6NHa73SNOPVtPKjguyW4i7Xfk7VYoKO2GWHJi6loOd5hrt7Rxbzr3v0JBdxceJOnDQL47ZtoOZ7UdjmQ5BQ01jotnns1TUVMyYTOuVUyG5xRGoDg7m2AysOjC0nd1O9roF1LH+TtNjNr2cR0OUPiuWG1dXKKrsFpjrKepkc6eF0ZedwlpDQ8OO6Rroehaa88mG81NhvGK2rP3W3CK65C5xWaazsnkpX9lNqXxMn5xp5syBxA3dRve6PEHNptYWAVcc85SOQ0+b5PZ8VoqV1PjkjaWbsuxXS4Or6nmmyOjZJSRlkAAe1ur9466ndA0J6hWbTb1S1c8LNmOXVTI3uY2eF9s3JADoHN3q0HQ9I1APHiAoy/ZHkcmRXbKMPyyqwE5OyKpu1nr7XBXOjqGxhnORkS7kcu6Gh2hkYS3XQrc3nkGppdru0LN8pltOM2qzWJzMYt+QOhyOnqHVEM05mDqV7GPZx1jA3uG7unuX7w3fFm2+ZNtOhwa3YRbrVRXu+WBuRXGovfOy01DBviIMYyNzXSPdLvgd00AMJOuui6VbdnTqDadecwdcjM65WektRpDBu7hhkmfzm+Hcd7ntN3dGm70nXhzyx8mq5Yba8IkxjNTaMjxy0mxz3GW1tnguNIXiTcfAZAWkPG81zX6jU66gqWqGdyTjWHZzezcRALh203nskUpJiEvZsu/ub3Hd110146aLoli78cn/AOV/llazZBs4n2XYtVWqpvBvtTU3KsuUtaaYU5c+omdKRuBxHAuI1GgPxDoWzsXfjk//ACv8srs4Wiivu9YajklJERFxMiIiAvOzvvYHXa30qVel52d97A67W+lSrzMo5+juq86WtSSoiIyKE5H/AN49k/smt/nUqmyhOR/949k/smt/nUq7eS85/wAnylqEA2/bTb1sxsdkq7TFb6eCtuLaStvV3hllorXEWOIlmbEWu3S5rWbxc1oLhqQo7JfbtV7bdkpu7MburLjZLnPBcLUKgmKVrYTK6GTndx8UjXxaBzCRuHR3FdMz/H8jyK208ON5LDjdQyUumfU2xlfFURlpaY3Mc9hA1IOocDqB0jUGFYPyeqbBajZu6kvUlRDh1HcqbclpgDVurHRvc4EOAjDXMOjACNHAajd48kxN2XIdg+0PNdmexTZfcrlSWKuwKvmgtTxSiZlwozPO6OOZznExvbvkBzQ0EBw0LuK/lzr6u18mnaXVwUlsuNLHm917NoroyZ0c8BubmlrTFLG5r94scHbxGjSNDrw6Dh/JkutktGI47ec7ffMPxqohrae0x2mOmfPUROL4zLMHuLo2yHeDAB0NDnO01O0uXJ2mrMK2gYrFlD47Tk90N2pmS0LXut0klQJ527we3nWueOGuhbr0uWYibDV5htd2g01+2qssFLjnsXgscNUW3COd09cx1CypfECx4bG73ej9HDi0FnAuOLlW33Lbo7IZ8Ko7FTUWOYzS5HW9sHOukqhURSTMii5tzQwNZEdZHbw3iBoOJU8q9jnZVTtVl9l93t6p2Qadja9g7tEKXX3f6To39O5+L6VwXbbsvqrXk2Oxw2+5X99qxyltkLm4VJdaOqdEXase+Kpj3d4hpLJg5jeBa7i5Wc6BaXAb3UZLguOXer3eyrhbaarl3YjEN+SJrnaMJcW8SeGp0+Mra7L+9I/2jcPTZ1rMGq7xcMMsdTkFvhtV9mooX11DTu1jp5ywF7GnU8AdR0n9p6Vs9l/ekf7RuHps63icxPfHlUupLERF5yNdkfe9dOqy+YVH7D7x27q0fmhSDI+966dVl8wqP2H3jt3Vo/NCmD8RPy+rWpnIiL1GRERBos0o5qyyNdTxOnkpqumq+aZ7p7Yp2SOAHhO606DwnQLLpcltNZAyaG5Ur43DUHnmj9xGuoP0FbJa6qxy010plqbXRVEruJfLTsc4/vIXNTVTNObXqXsl9PZu3fL6X65v3p7N275fS/XN+9YvahYfElu8kj+5O1Cw+JLd5JH9yv6Xb4LoZXs3bvl9L9c3709m7d8vpfrm/esXtQsPiS3eSR/ctbk2KWSHHLrJHZ7ex7aSVzXNpWAghh0IOin6Xb4GhvPZu3fL6X65v3p7N275fS/XN+9cU5IVmt995N2DV9yoaa4V01JI6WpqoWyyyHnpBq5zgSeAA4/Euw9qFh8SW7ySP7kjgpi+nwNDK9m7d8vpfrm/ens3bvl9L9c371i9qFh8SW7ySP7k7ULD4kt3kkf3K/pdvgaGQ+/2yJhe+40jGjiXOnaAP81q8WHZ10vV3j40VbJE2mk8ErGRgc4P90uLgD4QNRwIKzo8UskTw9lmt7HtOoc2lYCP8ltVJqopiYo17d6aNQiIuFBERAXnZ33sDrtb6VKvS87O+9gddrfSpV5mUc/R3VedLWpJUREZFC8zb7GZNZr1P3FvjpqiimnPuYXSPhcxzviaTE4a9AJb8ami8vY2RjmuaHNcNC0jUELmwsTgq863+nQsTZEBfLa5oIuFKQRqCJm8f81/fZu3fL6X65v3rbvwzH5HFzrFbXOPSTSRkn/JfztKx3xDbPI4/VXb4bB7fBdDU+zdu+X0v1zfvT2bt3y+l+ub9623aVjviG2eRx+quCbE7Nb7hyl+UFQVVDTVNDQVFkFJSzQtfFTh9G5zxG0jRm8eJ001PSnDYPb4Gh2X2bt3y+l+ub96ezdu+X0v1zfvW27Ssd8Q2zyOP1U7Ssd8Q2zyOP1U4bB7fA0NJVZLaaKF0s1xpmtHgEoc5x+IAcST4AOJ8C2ez+2VFqxWmiq4jBUSzVFU+Fx1MfOzPl3Tp4QH6H6Qs+ixmz22YTUlqoaWYdEkNMxjh+8BbNcWLjU1UZlEaOXT/u1OyBERdNGuyPveunVZfMKj9h947d1aPzQpBkfe9dOqy+YVH7D7x27q0fmhTB+In5fVrUzkRF6jIiIgIiICIiAtXlXexeOpzeYVtFq8q72Lx1ObzCoOT8i34L2AdTk/nyLti4nyLfgvYB1OT+fIu2KU/tgERFoEREBERAREQF52d97A67W+lSr0vOzvvYHXa30qVeZlHP0d1XnS1qSVERGRERAREQFXbYR8KflIdZsXoL1YlV22EfCn5SHWbF6C9BYlERAREQEREHzngZUwSQytD45GljmnwgjQhR5uzjH2NDW0UjWgaACqmAA/jUlRcVeDh4k3rpie+FiZjkRv2u7B8jl8qm9dPa7sHyOXyqb11JEXHxXA6uN0LnTtRv2u7B8jl8qm9dPa7sHyOXyqb11JETiuB1cboM6dqN+13YPkcvlU3rp7Xdg+Ry+VTeupIicVwOrjdBnTtRv2u7B8jl8qm9dPa7sHyOXyqb11JETiuB1cboM6dqN+13YPkcvlU3rrV5Vs9sMeMXdzaSQObRzEf6VN+of99ThanLO9W89Sm8wpxbA6uN0JnTtcF5FuE2e58l/AKqpppHzyUchc4VErQf08g6A4ALtntd2D5HL5VN665hyH/gqbPOpSfz5V3NWcmwZm80RugvO1G/a7sHyOXyqb109ruwfI5fKpvXUkRTiuB1cboXOnajftd2D5HL5VN66e13YPkcvlU3rqSInFcDq43QZ07Ub9ruwfI5fKpvXT2u7B8jl8qm9dSRE4rgdXG6DOnajftd2D5HL5VN66e13YPkcvlU3rqSInFcDq43QZ07Ub9ruwfI5fKpvXW5tdqpbLQx0dFEIKaMuLWAk6EuLidTxOpJP71lot0YOFhznUUxE9kQl5kREXMgiIgIiICrtsI+FPykOs2L0F6sSq7bCPhT8pDrNi9BegsSiIgIiICIiAiIgIiICIiAiIgIiIC1OWd6t56lN5hW2WPcKKO5UFTSSlwiqInRPLTodHAg6f4oOKch/4KmzzqUn8+VdzVU7Fje1rkjWqC2WKiG1vZdRb3M0FPG2nvltjLi4hgaN2oALidAN4k8A0LtOyTb5hO22hklxi8MmrYOFXaapvM11I4HQiWF3dDQ8NRq3XoJQdDREQEREBERAREQEREBERAREQERYtzulFZLfUV9xq4KChp2GSapqpGxxRtHS5znEAD6SgylXbYR8KflIdZsXoL18Lryor7tOuFRZNhOL9uE0TzFUZZdt+msdI4dOj+Dp3D9VmnSCN4KZ7BdiV02YVuVZHk+TPyrM8rlp57tVx0zKemYYWOZGyGNo1Aa1xbqendB0HHUOuoiICIiAiIgIiICIiAiIgIiICIiAiIgLku1vkyYbtaror1LFU43mFN3VJlFhl7Fr4XAcCXt/1g8GjgeGuhGq60iCsftmbXOTmOZ2j2h+0vCYeAzHG6fdr6Zg/rVdIOkAdL2HQAakuJXdNnm0/FdrFgjvWJXykvlvdoDJTP7qMn+rIw6OY7/dcAfoUoXC9ofJOsN8v78twa51ezLO+LvZiwgNhqTrrpU03BkrSeJ6CT0k9CDuiKs9LyjM02JVMds2541zNr3hFDnmNxPntsuvAGoiA34HH9mhOujQBqrDY7klpy6z012slypbvbKlu9DWUUzZYpB9DmkhBskREBERAREQEREBfxzgxpc4gNA1JPgXHNqfKkxTZ5eRjNrhq84zqXVsOMY6zsipDv/OcNWwtHAku4gcd0hQpuxTaXygXCq2w344vish3m4Di9QWiRn6tZVjjJ9LWdz4QWlBu8z5WVBUX6fE9ldkqNqWYM7mWO1vDbdQno3qirPcNAPgaTqQQS0rW2zkwX3alcKe+bdcm7a5I3ianxC0F9PZKN3g1bqHzuH6z/jIO8F3TDMGx/Z3YYLLjNno7Ja4fcU1FEGN18Ljpxc4+Fx1J8JW8QYtrtVFY7dT0Fuo4KChp2COGlpYmxxRNHQ1rWgAD6AspEQEREBERAREQEREBERAREQEREBERAREQEREBERB8qmmhraaWnqImTwStLJIpWhzXtI0IIPAgjwKvWRclCbD7xU5NsTyJ+zi+yu5yos+6ZrJXn4pKfiIyejeYO5GujdeKsUtfkFoGQWG5Ws1lZbhXU0tMay3zGGpg32FvORSDix7ddWu8BAKD8hdtHLQ2h5Vtpx7IjUWigrMInlp6Fljfz1HNISGVMgl1Jljm5sAaO3eb3QOJc536ZbOtv1r2u7OccyLGBG+svQdG6lndqKGWNoM4l00J3CWgAaF+/GeDXbw4bN/RWbJJZC5t9zGEfqMrqXQf40xKl+xzkvWHkzZxHS49fL1dKG8UtTKaa6yxvbA6N0I3mbjGjVweA46cdxvxLs5PTFeJarZM7omVh2Ax5W469sdK0+ENtg01+jWQ/wDVOayv5yU32Y3119skyS2YhYq283mtit1roozLPUzHRrG/9SdSAAOJJAHFaex7T8cyKqs9LRVdQKm7wT1VFDU0FRTvkjhe1kri2SNpZoXN4O0J11Go4ru5/ZG6PZbtlzWV/OSm+zG+uvpDf7zjs0El4q6a526aVkD5YqbmJYHPcGMce7Ic3ecAeAI1146FbRRbafRm4YPcaVtRNSGcxRCopnBssW9KwbzCQQHDXUEg8fAt0WxKooqiLTo5IjygibzZQv8ApCOVlV5PndPg2G3WakteM1jaiquFDMY3zXGN2rdx7TqBC4cCD7vU/wBVpXZdh2VbVOWxgVNU1mZR4Ph1vLLVdpLC3S8XWrjhjdM4y7jWU7H77XgRA6b5aQQFlQf0VOy8sJqsnzCeYkkvjqqVgP7jTu/6rt3J35LGI8maK+sxasu9YbzzHZL7tPHKf0PObm7uRsA/1rteHgC8ZlLNlmxfDNi9mNuxGx09rZJoZ6kDfqKl360srtXPOup4nQa8AFN0RAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBQrK+/8AxrqNf51MpqoVlff/AI11Gv8AOpl28l53/lX/AMysOQ8sixx3nYnOZKqupeYu1rI7Cq5IN/fr4IyH7hG8AHkgHocGuHFoI+N4o6vENvWK2yivt8mt82I3IS0tZdZ6iOR9O6mbHK5r3EGXSR2sh7o68SuvZZiNpziySWi90nZtuklhndDzj49XxSsljO8wg8HxsPTx00OoJC8XDDLNdcko79VUfO3ajpJ6GCo5143IZiwyt3Qd06mNnEjUacCNSuWY03RWjZvXX6xYpsBy2XLchu9flFVBbbtBc7i+emnilop5Gnmj3LXsdCwh4Ac7jvFxJJsjn3evP/xqf+exYlLsqxaisuK2mG17lvxeeOotEPZEp7GkZG+Nh1LtX6MkeNHlw469ICy8+715/wDjU/8APYufJ4tiU98LHLDoiIi8hBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBR/KrFU3GShuFAWeyFCX7kUri1kzHgB7CR0E6NIOh0LRw0UgRbornDqzoORA3XLIGnQ4hXOPhLKul0/drKD/ko1l+1c4JV4/TXvG7lRzX64x2q3tEtPJz1S8EtZq2Q7uoaeLtB9K7Cq78rTvp2Df3gUPmSLt8a/pHj7rfsdL9lMg+Z1x8rpPxl7jtN3yiWCC4Ws2e2xyxzzc9UMkmmLHB7WNEZc0NLmjeJd0DQA72rZ0ik5VP8aYif++slxERdJBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAVd+Vp307Bv7wKHzJFYhV35WnfTsG/vAofMkQWIREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAVd+Vp307Bv7wKHzJFYhfkht25ae1Wvzu02jK7BjNBd8FyIXCOKkpalrX1MBcwB+9Od6M6k9zukjQgoP1vRV85GO2naBt9wC4Zbmlsstrt8tT2PaW2mnmiMzWaiaR3OSyat3tGt004sfrrwVg0BERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBfxzgxpc4gNA1JPgWBfr5R41aKm5V8nNUtO3ecQNSSSA1oHhcSQAPCSAq95Xk9xzipc+5vdHQ6nmrYx55ljfBvjokd8ZPAHoA8PqZF+H4mWzMxNqY1+y97t1TtNxGjmdFNk9oZK06OZ2bGXN/aAeC+Xtr4Z86LV5Wz71wKONkTAxjQxo4BrRoAvS+g/I8Hpz4JeHe/bXwz50Wrytn3qhPLu2JWjajtYxTKMNu9tnlvssdsvUkc7HMpXN0EdVJoddzm9WuPg5pg6XLvaK/keB0p8PYvDruCZJs62dYbZsZs+RWmC2WqlZSwN7LZqQ0abzuPFzjq4nwkkrfe2vhnzotXlbPvXBET8jwOlPh7F4d7G1bDXHQZRafK2fet5aL9bL/AZrXcaS5Qg6GSknbK0fvaSq0L5NpWRVjKyAvpK5nuKumcY5m/se3Q6fGOg+EFYr/AsOY/8VzE9un2LwtWi53sx2jyZA/2Hu72+y8ce/FUNaGNq2DgToOAe3hvAaA67zQBq1nRF8rj4FeTYk4eJGmAREXXBERAREQEREBERAREQEREBERAREQEREBERAREQEREHINu9zkkr7BaGu0gIlrpW/rOZusjH7P0jz+1rf3c4XQ9u1C+G84/cdDzMkc1E52vAPO7IwfvDJP8ABc8JAGp4Bfof4XFMZHRm9vnJVqEUT9t3Bfnrjv2rB66/rtreDNcWuzTHgQdCDdYOH/5r0OFw+lG9hrr9tjtdjrrlE21Xm5UVrcW3G52+kEtNRuDQ5wed4OcWtILtxrt0dK+N4212q2V92pqe03m8C1QRVdXUW6nY+KOCSPnGybznt1G7rwGruB0BHFQGHZf2BkmQTybO7NntDeri+6UV6knp282ybRzo5OcBcWtOpaWB2oI6FM6XBrjRX3aW6nt7IaC6W6kpbY1j2BrzHTSRlobr3IBLR3Wg+LgujGJlFXZp2Tsnsts2q2962tWm21NrpaCiuWRVtxpBcIqWzwCV7aY6aTP3nNDWknQanUngAV52KZPcMy2Z2m8XSZ1RW1Lqjfe+JsbtG1EjWgtaAAQ1rR0eDjxUKxbFMu2dXCxXOlx72cFRjVvtNwpI62GKajqKdp4hz3brmHfIO6SdW6jVbrZjerbswwCz2LMLvaccvjOfnkoa25QNeGvqJXNI7riCD0j6fCCFcPFrnEirE0RaeyNVtOvWOpoon7bmC6a9umPafH7KweutzYspsuUxSy2W70F3jicGyPoKlk4YT0AlpOhXejEoqm0TCM+S6PsE9LeIiWyW2dlUCOB3Wn9I3/5Rl7T9DirVKqVXQyXZsVsh1564Sso2bvSOccGk/uBJP0Aq1vQvlvx7Nvhzr07tFvVvUIiL5QEREBERAREQEREBERAREQEREBERAREQEREBERAREQanKsapctsVTbKveYyUAslZ7uJ4OrXt+kEA/Eeg6gkKvN/s9bilyFBdoxDK9xEE4GkVSB4WH49Olmu8PpGhNnFjXC20l3o5KSupYa2lkGj4KiMSMePiLSCCvXyD8RryOZpmL0zq9YXvVc7Cp/8AYRfwBOwqf/YRfwBdzm2J4dNI54tc0G9/Vpq+phaP2NZIAP3BfP2jcO+RV/2xWfjL6GPxvJNdNW6PdLQ4sAAAANAPAEXafaNw75FX/bFZ+MntG4d8ir/tis/GV/O8k2Vbo+4tDiy+clPFK7efEx56NXNBXbfaNw75FX/bFZ+MntG4d8ir/tis/GT87yTZVuj7i0OIdg03yeL+AL+PkpqBo13Id9wa1rRxe49AAHEn6BxXcW7D8Padewa08NNHXasI/wA5VvMfwDHcWm562Wmnp6nTd7JcDJNp8XOOJdp9GqxX+N5PEXopmZ7bR6yWhDdlmzqejqoshvEJgqg0iionjuoA4EGR/wAT3NJAb/VaTrxcQ3qSIvk8pyivKsScTE5fLsBERdUEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERAREQEREBERB/9k=\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "graph.invoke({\"name\": \"test\"}, debug=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YXHhT4t29twu",
        "outputId": "20671d77-8526-46e6-fde9-9619197a74e8"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[36;1m\u001b[1;3m[0:tasks]\u001b[0m \u001b[1mStarting step 0 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3m__start__\u001b[0m -> {'name': 'test'}\n",
            "\u001b[36;1m\u001b[1;3m[0:writes]\u001b[0m \u001b[1mFinished step 0 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mname\u001b[0m -> 'test'\n",
            "\u001b[36;1m\u001b[1;3m[1:tasks]\u001b[0m \u001b[1mStarting step 1 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mgrandparent\u001b[0m -> {'name': 'test', 'path': []}\n",
            "\u001b[36;1m\u001b[1;3m[1:writes]\u001b[0m \u001b[1mFinished step 1 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['grandparent']\n",
            "\u001b[36;1m\u001b[1;3m[2:tasks]\u001b[0m \u001b[1mStarting step 2 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mparent\u001b[0m -> {'name': 'test', 'path': ['grandparent']}\n",
            "\u001b[36;1m\u001b[1;3m[2:writes]\u001b[0m \u001b[1mFinished step 2 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['parent']\n",
            "\u001b[36;1m\u001b[1;3m[3:tasks]\u001b[0m \u001b[1mStarting step 3 with 2 tasks:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mchild\u001b[0m -> {'name': 'test', 'path': ['grandparent', 'parent']}\n",
            "- \u001b[32;1m\u001b[1;3msibling\u001b[0m -> {'name': 'test', 'path': ['grandparent', 'parent']}\n",
            "\u001b[36;1m\u001b[1;3m[3:writes]\u001b[0m \u001b[1mFinished step 3 with writes to 2 channels:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mname\u001b[0m -> 'test'\n",
            "- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['grandparent', 'parent', 'child_start', 'child_middle', 'child_end'], ['sibling']\n",
            "\u001b[36;1m\u001b[1;3m[4:tasks]\u001b[0m \u001b[1mStarting step 4 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mfin\u001b[0m -> {'name': 'test',\n",
            " 'path': ['grandparent',\n",
            "          'parent',\n",
            "          'grandparent',\n",
            "          'parent',\n",
            "          'child_start',\n",
            "          'child_middle',\n",
            "          'child_end',\n",
            "          'sibling']}\n",
            "\u001b[36;1m\u001b[1;3m[4:writes]\u001b[0m \u001b[1mFinished step 4 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['fin']\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'name': 'test',\n",
              " 'path': ['grandparent',\n",
              "  'parent',\n",
              "  'grandparent',\n",
              "  'parent',\n",
              "  'child_start',\n",
              "  'child_middle',\n",
              "  'child_end',\n",
              "  'sibling',\n",
              "  'fin']}"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import uuid\n",
        "\n",
        "\n",
        "def reduce_list(left: list | None, right: list | None) -> list:\n",
        "    \"\"\"Append the right-hand list, replacing any elements with the same id in the left-hand list.\"\"\"\n",
        "    if not left:\n",
        "        left = []\n",
        "    if not right:\n",
        "        right = []\n",
        "    left_, right_ = [], []\n",
        "    for orig, new in [(left, left_), (right, right_)]:\n",
        "        for val in orig:\n",
        "            if not isinstance(val, dict):\n",
        "                val = {\"val\": val}\n",
        "            if \"id\" not in val:\n",
        "                val[\"id\"] = str(uuid.uuid4())\n",
        "            new.append(val)\n",
        "    # Merge the two lists\n",
        "    left_idx_by_id = {val[\"id\"]: i for i, val in enumerate(left_)}\n",
        "    merged = left_.copy()\n",
        "    for val in right_:\n",
        "        if (existing_idx := left_idx_by_id.get(val[\"id\"])) is not None:\n",
        "            merged[existing_idx] = val\n",
        "        else:\n",
        "            merged.append(val)\n",
        "    return merged\n",
        "\n",
        "\n",
        "class ChildState(TypedDict):\n",
        "    name: str\n",
        "    path: Annotated[list[str], reduce_list]\n",
        "\n",
        "\n",
        "class ParentState(TypedDict):\n",
        "    name: str\n",
        "    path: Annotated[list[str], reduce_list]"
      ],
      "metadata": {
        "id": "6AeJfHHq9wgu"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "child_builder = StateGraph(ChildState)\n",
        "\n",
        "child_builder.add_node(\"child_start\", lambda state: {\"path\": [\"child_start\"]})\n",
        "child_builder.add_edge(START, \"child_start\")\n",
        "child_builder.add_node(\"child_middle\", lambda state: {\"path\": [\"child_middle\"]})\n",
        "child_builder.add_node(\"child_end\", lambda state: {\"path\": [\"child_end\"]})\n",
        "child_builder.add_edge(\"child_start\", \"child_middle\")\n",
        "child_builder.add_edge(\"child_middle\", \"child_end\")\n",
        "child_builder.add_edge(\"child_end\", END)\n",
        "\n",
        "builder = StateGraph(ParentState)\n",
        "\n",
        "builder.add_node(\"grandparent\", lambda state: {\"path\": [\"grandparent\"]})\n",
        "builder.add_edge(START, \"grandparent\")\n",
        "builder.add_node(\"parent\", lambda state: {\"path\": [\"parent\"]})\n",
        "builder.add_node(\"child\", child_builder.compile())\n",
        "builder.add_node(\"sibling\", lambda state: {\"path\": [\"sibling\"]})\n",
        "builder.add_node(\"fin\", lambda state: {\"path\": [\"fin\"]})\n",
        "\n",
        "# Add connections\n",
        "builder.add_edge(\"grandparent\", \"parent\")\n",
        "builder.add_edge(\"parent\", \"child\")\n",
        "builder.add_edge(\"parent\", \"sibling\")\n",
        "builder.add_edge(\"child\", \"fin\")\n",
        "builder.add_edge(\"sibling\", \"fin\")\n",
        "builder.add_edge(\"fin\", END)\n",
        "graph = builder.compile()"
      ],
      "metadata": {
        "id": "fzb4Uf0A96pF"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import Image, display\n",
        "\n",
        "# Setting xray to 1 will show the internal structure of the nested graph\n",
        "display(Image(graph.get_graph(xray=1).draw_mermaid_png()))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 707
        },
        "id": "8ZGf0h5x99hb",
        "outputId": "083ba039-2c8f-461f-eb1f-78e00e7133c1"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/jpeg": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "graph.invoke({\"name\": \"test\"}, debug=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lUnHe7wQ-Bqi",
        "outputId": "591fe860-8e91-4147-bdcd-5fc1c4273151"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[36;1m\u001b[1;3m[0:tasks]\u001b[0m \u001b[1mStarting step 0 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3m__start__\u001b[0m -> {'name': 'test'}\n",
            "\u001b[36;1m\u001b[1;3m[0:writes]\u001b[0m \u001b[1mFinished step 0 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mname\u001b[0m -> 'test'\n",
            "\u001b[36;1m\u001b[1;3m[1:tasks]\u001b[0m \u001b[1mStarting step 1 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mgrandparent\u001b[0m -> {'name': 'test', 'path': []}\n",
            "\u001b[36;1m\u001b[1;3m[1:writes]\u001b[0m \u001b[1mFinished step 1 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['grandparent']\n",
            "\u001b[36;1m\u001b[1;3m[2:tasks]\u001b[0m \u001b[1mStarting step 2 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mparent\u001b[0m -> {'name': 'test',\n",
            " 'path': [{'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688', 'val': 'grandparent'}]}\n",
            "\u001b[36;1m\u001b[1;3m[2:writes]\u001b[0m \u001b[1mFinished step 2 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['parent']\n",
            "\u001b[36;1m\u001b[1;3m[3:tasks]\u001b[0m \u001b[1mStarting step 3 with 2 tasks:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mchild\u001b[0m -> {'name': 'test',\n",
            " 'path': [{'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688', 'val': 'grandparent'},\n",
            "          {'id': '77acd0c3-dbbf-4931-a50c-33dc0b63889e', 'val': 'parent'}]}\n",
            "- \u001b[32;1m\u001b[1;3msibling\u001b[0m -> {'name': 'test',\n",
            " 'path': [{'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688', 'val': 'grandparent'},\n",
            "          {'id': '77acd0c3-dbbf-4931-a50c-33dc0b63889e', 'val': 'parent'}]}\n",
            "\u001b[36;1m\u001b[1;3m[3:writes]\u001b[0m \u001b[1mFinished step 3 with writes to 2 channels:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mname\u001b[0m -> 'test'\n",
            "- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> [{'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688', 'val': 'grandparent'},\n",
            " {'id': '77acd0c3-dbbf-4931-a50c-33dc0b63889e', 'val': 'parent'},\n",
            " {'id': 'ad96568f-e756-4b03-91a8-681774f20edc', 'val': 'child_start'},\n",
            " {'id': '14ce7513-d32f-4c7b-b1b4-d04b9c5d2ae9', 'val': 'child_middle'},\n",
            " {'id': '2e34890d-61b5-4311-bccb-3fd6ee7e08ac', 'val': 'child_end'}], ['sibling']\n",
            "\u001b[36;1m\u001b[1;3m[4:tasks]\u001b[0m \u001b[1mStarting step 4 with 1 task:\n",
            "\u001b[0m- \u001b[32;1m\u001b[1;3mfin\u001b[0m -> {'name': 'test',\n",
            " 'path': [{'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688', 'val': 'grandparent'},\n",
            "          {'id': '77acd0c3-dbbf-4931-a50c-33dc0b63889e', 'val': 'parent'},\n",
            "          {'id': 'ad96568f-e756-4b03-91a8-681774f20edc', 'val': 'child_start'},\n",
            "          {'id': '14ce7513-d32f-4c7b-b1b4-d04b9c5d2ae9', 'val': 'child_middle'},\n",
            "          {'id': '2e34890d-61b5-4311-bccb-3fd6ee7e08ac', 'val': 'child_end'},\n",
            "          {'id': '50601ccc-3af7-47dc-a2fe-5cc3374e4d6d', 'val': 'sibling'}]}\n",
            "\u001b[36;1m\u001b[1;3m[4:writes]\u001b[0m \u001b[1mFinished step 4 with writes to 1 channel:\n",
            "\u001b[0m- \u001b[33;1m\u001b[1;3mpath\u001b[0m -> ['fin']\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'name': 'test',\n",
              " 'path': [{'val': 'grandparent', 'id': 'd0b7899b-2e66-45f5-936f-30de5f14e688'},\n",
              "  {'val': 'parent', 'id': '77acd0c3-dbbf-4931-a50c-33dc0b63889e'},\n",
              "  {'val': 'child_start', 'id': 'ad96568f-e756-4b03-91a8-681774f20edc'},\n",
              "  {'val': 'child_middle', 'id': '14ce7513-d32f-4c7b-b1b4-d04b9c5d2ae9'},\n",
              "  {'val': 'child_end', 'id': '2e34890d-61b5-4311-bccb-3fd6ee7e08ac'},\n",
              "  {'val': 'sibling', 'id': '50601ccc-3af7-47dc-a2fe-5cc3374e4d6d'},\n",
              "  {'val': 'fin', 'id': 'a10684c5-e6e5-45c3-bd06-d49f5758958e'}]}"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "pnCrymem-E8q"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}