autogen/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Auto Generated Agent Chat: Graph Modeling Language with using select_speaker\n",
    "\n",
    "AutoGen offers conversable agents powered by LLM, tool, or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
    "Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
    "\n",
    "This notebook is about using graphs to define the transition paths amongst speakers.\n",
    "\n",
    "Benefits\n",
    "- This contribution fills the gap between the current modes of GroupChat Class (auto, manual, round_robin) and an expressive directed graph. See Motivation for more detailed discussion.\n",
    "\n",
    "\n",
    "## Requirements\n",
    "\n",
    "AutoGen requires `Python>=3.8`. To run this notebook example, please install:\n",
    "```bash\n",
    "pip install pyautogen\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%capture --no-stderr\n",
    "# %pip install \"pyautogen>=0.2.3\"\n",
    "%pip install pyautogen[graph]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random  # noqa E402\n",
    "\n",
    "import matplotlib.pyplot as plt  # noqa E402\n",
    "import networkx as nx  # noqa E402\n",
    "\n",
    "import autogen  # noqa E402\n",
    "from autogen.agentchat.conversable_agent import ConversableAgent  # noqa E402\n",
    "from autogen.agentchat.assistant_agent import AssistantAgent  # noqa E402\n",
    "from autogen.agentchat.groupchat import GroupChat  # noqa E402\n",
    "from autogen.graph_utils import visualize_speaker_transitions_dict  # noqa E402"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.2.5\n"
     ]
    }
   ],
   "source": [
    "print(autogen.__version__)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Motivation\n",
    "\n",
    "\n",
    "The current GroupChat class allows transition to any agent (without or without the decision of LLM), some use case might demand for more control over transition. A graph is a possible way to control the transition paths, where each node represents an agent and each directed edge represent possible transition path. Let's illustrate the current transition paths for a GroupChat with five agents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The default config list in notebook.\n",
    "config_list_gpt4 = autogen.config_list_from_json(\n",
    "    \"OAI_CONFIG_LIST\",\n",
    "    filter_dict={\n",
    "        \"model\": [\"gpt-4\", \"gpt-4-0314\", \"gpt4\", \"gpt-4-32k\", \"gpt-4-32k-0314\", \"gpt-4-32k-v0314\"],\n",
    "    },\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "agents = [ConversableAgent(name=f\"Agent{i}\", llm_config=False) for i in range(5)]\n",
    "allowed_speaker_transitions_dict = {agent: [other_agent for other_agent in agents] for agent in agents}\n",
    "\n",
    "visualize_speaker_transitions_dict(allowed_speaker_transitions_dict, agents)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Possibly interesting transition paths\n",
    "1. Hub and Spoke\n",
    "2. Sequential Team Operations\n",
    "3. Think aloud and debate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "agents = [ConversableAgent(name=f\"Agent{i}\", llm_config=False) for i in range(5)]\n",
    "allowed_speaker_transitions_dict = {\n",
    "    agents[0]: [agents[1], agents[2], agents[3], agents[4]],\n",
    "    agents[1]: [agents[0]],\n",
    "    agents[2]: [agents[0]],\n",
    "    agents[3]: [agents[0]],\n",
    "    agents[4]: [agents[0]],\n",
    "}\n",
    "\n",
    "visualize_speaker_transitions_dict(allowed_speaker_transitions_dict, agents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<autogen.agentchat.agent.Agent object at 0x7fbf958831c0>\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAApQAAAHzCAYAAACe1o1DAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAACdWUlEQVR4nOzdd1gUx+MG8HfvDo7emyigCGLv2Bt6aOzRaOwxReM3xfxMT0wxVVNMNMZUE6NRE1ssMTEWFBUbYseGoDRF6SBwcHV/fyCnJ0XK0d/P8/CE2zI7S3R9mdmZEURRFEFEREREVEmS2q4AEREREdVvDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlDJREREREVCUMlERERERUJQyURERERFQlstquAN2Tp9IiLj0Paq0e5jIJmjtbw1rO/0VERERUtzGt1LLo5BysC09AaFQKEjKUEO/bJwDwdrJCUIAbpvX0hr+7bW1Vk4iIiKhUgiiK4sMPI1NLzFBi/tZIhMWkQSoRoNOX/r+haH9/PxcsHNcBXk5WNVhTIiIiorIxUNaC9REJWPD3RWj1YplB8kFSiQCZRMCHY9phcqB3NdaQiIiIqPwYKGvY8tBoLN5ztcrlvDa0FV4M8jdBjYiIiIiqhqO8a9D6iASThEkAWLznKjZEJJikLCIiIqKqYAtlDUnMUEKx5CBUWj306gLknt0F5dVj0KQlQK8pgNTGCeYu3rBqMwDWbfpB1GqQeWAV1ElR0N5JhV6VB0FmDjOnprBq1Qe2gWNhaWmJkJcH8p1KIiIiqlUMlDVkxq/hOHo9Hfkp8Ujd/BG0WbdLPbbJU8sgsbTDze+fLPUYixZd4DnlE/TxdcaaZ3pWQ42JiIiIyofTBtWA6OQchMWkQZefg5SNC6C7kwoAkNo4wa7nYzBz9YGozkdBwgXkRoYAAASpFFat+sCiRRfI7N0AUUTe5TDkXdgHACiIPYOC1ESE6UXEpOTAz41TChEREVHtYKCsAevCEyCVCMg8scUQJgW5NTxmfg2ZrYvhOKtWvWHfeyIgkUJqaQvX8fONyrFs2R350cehV+UBAPTqfEglAtYeT8AHY9rV3A0RERER3YeDcmpAaFQKdHoRysthhm12gWONwmQRqbUDpJbFWxv1BbnIObfbECYlVg4wc/GGTi8i9GpK9VWeiIiI6CHYQlnNclVaJGQooVfnG703KW9WvhbFzAOrcOf4ZqNtZq7N4Tx8LiRmcgBAQroSeSotl2kkIiKiWsEWymoWn54HETC0LBaR2TpVukxBagZRrzd8FgHEpeeVfgIRERFRNWKgrGZqbWHwk8itjbZrczLKdb5tlxFwn/YZXMe/A+t2QYVl3o5Gyob3oMvNLHYdIiIioprGQFnNzGWFP2KJuSVkDh6G7aqbl8p1vszeDRZe7WHVqjdcRr8KuVd7AICoKYAyJrzYdYiIiIhqGlNINWvubA3h7vdWbfobtuec2AZtTnqx43V5WdDl50CvUT20bH1BLgBAuHsdAMjLy0NkZCS2b9+O7777DsnJyVW+ByIiIqKycBRHNbOWy+DtZIX4DCXseoxH3sUD0N1d+eb276/Crsc4mLk2vzsPZSRyI0PgMXUR7pzaAV1uBqz8ekDm4AFRp4Xy6jGoEi8Yyjb38AMAaLNuo3mzJtBoNMjOzja6vr29PaZPn14j95qn0iIuPQ9qrR7mMgmaO1tzoBAREVEjwH/ta0BQgBvWhMcDlrZwe/xDw0o5upw0ZO5bUfJJej0Krp9CwfVTJe62atMfls07Q4AI5bWTyEhLK3aMRCLB0KFDTXkrxUQn52BdeAJCo1KQkKHE/csuCQC8nawQFOCGaT294e/OydeJiIgaIi69WAOik3MQvPSQ4fO9tbyPQpOWCL0mH1JrR5g5e8G67UBYtx2AgvjzyD0fAvXtGOiUWRC1akgsbWHu5gvrdoNg3W4QBKHwjYU/Z7TFxKH9kZSUhPv/d5qbm+PFF1/EO++8Ayenyo8qL0lihhLzt0YiLCYNUokAnb70P0ZF+/v7uWDhuA5ce5yIiKiBYaCsIUVreZcVvCpKKhEMa3knJSWhX79+SEhIgE6nAwCYmZlBo9EAAJo3b44ZM2bg9ddfh61t8ZZCjUaDLVu2YNy4cTA3Ny/zuusjErDg74vQ6sUK3Y9UIkAmEfDhmHaYHOhdgTslIiKiuoyDcmrIwnEdIJMIDz+wAmQSAQvHdQAAeHp64tChQ2jatGnhPpkMycnJ2L17NwYPHoxbt27h448/hr29PVq1aoVFixahoKDAUNa6deswefJkPP7444YQWpLlodF4a0skVFp9hcOxTi9CpdXjrS2RWB4aXYk7JiIiorqIgbKG5KUkAKc2mrTMj8a0M+o+btasGcLCwtCsWTOMHTsWjo6OGDp0KPbt24eCggJs2bIFffr0QVxcHObPnw8rKyu0b98ey5Ytw9q1ayEIAv7++29MnjwZWq222PXWRyRg8Z6rJqn74j1XsSEiwSRlERERUe1il3c1unPnDrZt24aVK1fi4MGDAIA3Vu3Dhiv5VShVBCDg9aEBeCHIr8QjVCoVRFGEhYVFifv1ej3+/PNPfPPNNzh9+rShi7yIIAiYOHEi1q1bB5mscNxWYoYSiiUHodLq73sH9Bg0aQnQawogtXGCuYs3rNoMgHWbfhCkZgCAvMuHkHNyB9QpsQAAc7cWsO0+BtZt+kMukyDk5YF8p5KIiKieY6CsBn///TdWr16Nf/75B2q12rC9Y8eOOHfuXKXfQYSoh16rQUf1ZWxZ/PpD33UsD61Wi5kzZ+KPP/4otq9Pnz44cOAAzMzMDO+A5qfEG0apl6bJU8tg7u6LrLB1yD7yZ4nH2PefDuf+UwzvgBIREVH9xWmDTOz69esYO3YsBEHAg1n99ddfBwBMDvRG35YuFR4l3cXTCv+8Pw2J2cnw3/4zvvrqKzz22GMQhMq/mymTyZCYmFhifY8ePQpXV1e89tFihN1qAl1+DlI2LoDuTmphvWycYNfzMZi5+tydR/MCciNDAADq5OvIProBACCYW8JJ8SwAICPkZ4jqfGQf/gNW/j0RphcRk5IDPzdOKURERFRfsYWyGnz66ad49913jbZJpVKkpqbC0dHRaHvRPI5/HDgLlbm9UTgUAHg7WyGolRum9/KGr4s1zM3NjbqoAwMDsWTJEvTt27dSdRVFEfb29sjJyYGtrS1atGiB1q1bw8vLC/Hx8ZBIJEh064VkuwCkha7CnWObCusmt4bnrO8gs3UxKk+XlwVIpMg6tAa5Z3YCABwGzoR974kAgOxjm5B1cDUAwLbrKLg+8hxm9PTBB2PaVar+REREVPsYKKuBWq2Gu7s7srKyABROMD548GDs3bu3xONTU1Ph7u4OyOQ4fTURokRa6kozrVu3RlRUlOGzVCqFTqfD8uXL8cILL1SqvmlpaZBKpcXCbpGBX4YiPkOJmz/OMnR12/ebCod+U0stM+nXF6FJjQMAuE/9DBbehWuQFyRcQPIfbwEAzNxawPPpb+HjbIWDrwVVqu5ERERU+zjK28S0Wi3atGmDrKwsDBkyBEDhIJjHHnus1HOee+45iKIIUVOAhPNH0cXbEe087UtctrB169ZGn0VRhLu7O3r2rPx7iC4uLqWGyVyVFgkZSujV+UbvTcqbld2iqM2+t4a41Nrhvu/tix2TkK5Enqr4qHIiIiKqHxgoTUir1aJ9+/a4fv065s6di5CQEPz0009o3rw5xo0bV+I5mzZtwl9
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Sequential Team Operations\n",
    "# Create an empty directed graph\n",
    "\n",
    "speaker_transitions_dict = {}\n",
    "teams = [\"A\", \"B\", \"C\"]\n",
    "team_size = 5\n",
    "\n",
    "\n",
    "def get_agent_of_name(agents, name) -> ConversableAgent:\n",
    "    for agent in agents:\n",
    "        if agent.name == name:\n",
    "            return agent\n",
    "\n",
    "\n",
    "# Create a list of 15 agents 3 teams x 5 agents\n",
    "agents = [ConversableAgent(name=f\"{team}{i}\", llm_config=False) for team in teams for i in range(team_size)]\n",
    "\n",
    "# Loop through each team and add members and their connections\n",
    "for team in teams:\n",
    "    for i in range(team_size):\n",
    "        member = f\"{team}{i}\"\n",
    "        # Connect each member to other members of the same team\n",
    "        speaker_transitions_dict[get_agent_of_name(agents, member)] = [\n",
    "            get_agent_of_name(agents, name=f\"{team}{j}\") for j in range(team_size) if j != i\n",
    "        ]\n",
    "\n",
    "# Team leaders connection\n",
    "print(get_agent_of_name(agents, name=\"B0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"A0\")].append(get_agent_of_name(agents, name=\"B0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"B0\")].append(get_agent_of_name(agents, name=\"C0\"))\n",
    "\n",
    "visualize_speaker_transitions_dict(speaker_transitions_dict, agents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAApQAAAHzCAYAAACe1o1DAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABKKklEQVR4nO3deVzUBf7H8TeIiIBoHoCAt2aeqWkqA4i3oZmprWZp2bFrtba1XW79WnU73K382VbrZltmat6aZ6CAcpuSiuJ9oCAgqKCiIuAw8/ujjZ+mmcjxnYHX8/HwseMc33nDmr75fGa+42C1Wq0CAAAA7pCj0QEAAABg3yiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAIAyoVACAACgTCiUAAAAKBMKJQAAAMqEQgkAAKqd3NxcBQYGaubMmbp8+bLRceyeg9VqtRodAgAAoDLt3LlT9913nySpfv36evPNNzVp0iS5ubkZnMw+MaEEAADVWm5url577TU1adJEf/vb35SXl6f8/Hzl5OTowoULys/PV1FRkZjB/TomlAAAoMrKycnRgQMHlJGRofT09JJfhw4dUnJy8k0f065dO2VmZurChQvXXV+rVi35+PjI19dXvr6+11329fVV27Zt5enpWRlfls2hUAIAgCrBarUqNTVVsbGxiouLU2xsrA4cOFByu7u7u/z8/OTn56fatWtr3bp1Jbc5OjrKYrHI399fM2fOVM2aNZWWliaz2Vzy6/z588rIyCj5lZmZqYyMDF26dKnkOK1atZLJZJK/v79MJpPat28vR8eqvxCmUAIAALtVXFyssLAwLVq0SNHR0crIyJAktW/fXoGBgQoICFDXrl3VpEkTeXh4lDzu59dQOjo6ymq1atSoUZo6dao6duxY6gx5eXnKyMjQnj17FB8fr4SEBCUlJam4uFh169ZV7969NXz4cD366KOqV69eeX3pNoVCCQAA7E5aWpq++uorzZ07V+np6ercubMGDx6sgIAAmUwmNWjQ4JaPT09PV6tWrTR8+PA7LpK3cunSJSUmJio+Pl4xMTHavHmznJycNHLkSD311FPq169flZpcUigBAIDdiIiI0P/+7/8qLCxMbm5uGjdunJ599lndd999cnBwKNWxrFZrqR9zp06dOqUFCxbo66+/1sGDB9W0aVNNnDhRL7/8surWrVspGSoShRIAANi89PR0vfzyy1qxYoW6d++uSZMmacyYMXJ3dzc6WqlYrVb98MMP+vrrr/Xtt9/K3d1dM2bM0JNPPmnXE0sKJQAAsFlXr17VJ598oqlTp6pOnTqaOXOmHn300UqbLFakjIwMvfHGG/r222/Vo0cPffrpp+rZs6fRse6I/VZhAABQpaWlpal79+56/fXX9fTTT+vgwYMaN25clSiTkuTr66uFCxcqNjZWZrNZvXr10uTJk2U2m42OVmpMKAEAgM05ePCgBg4cqJo1a2rlypXq2rWr0ZEqVHFxsWbPnq2XX35ZQ4cO1eLFi+Xq6mp0rNtGoQQAADZl586dGjx4sDw9PRUeHi4fHx+jI1Wa0NBQjR49Wl26dNG6detUv359oyPdFgolAACwGbt371ZQUJDatm2r0NDQ3zz9T1W0fft2DR06VI0aNVJCQoJdnLuSQgkAAGzC1atXdf/996u4uFjx8fGqU6eO0ZEMc/jwYfXo0UMjRozQN998Y3Sc38SbcgAAgE2YOXOm9uzZo7lz51brMilJd999tz755BPNnz9fq1evNjrOb2JCCQAADHf48GF17txZL774oj744AOj49gEq9Wqhx9+WFu3btXevXvVqFEjoyP9KiaUAADAcP/85z/VsGFDTZs2zegoNsPBwUFz5sxRfn6+5syZY3ScW6JQAgAAQ1mtVq1bt04jR460q1PlVAYvLy8NHTpUK1euNDrKLVEoAQCAoZKTk3Xy5EkNGzbM6Cg2adSoUUpKSlJKSorRUX4VhRIAABhq48aNcnNzU58+fYyOYpNCQkLk4uKitWvXGh3lV1EoAQCAofLy8tSgQQPVqlXL6Cg2yc3NTZ6ensrNzTU6yq+iUAIAAEPVrFlTV69eNToGyoBCCQAADOXs7EyhtHMUSgAAYKj69evr/PnzOn/+vNFRbFJBQYFycnJs+mTvFEoAAGCoYcOGqbi42C4+EcYI4eHhunz5soYOHWp0lF/FJ+UAAADDBQcHy8XFRWFhYUZHsTlPPvmktm/frv379xsd5VcxoQQAAIYbM2aMIiIilJqaanQUm3L+/HmtWbNGo0aNMjrKLTGhBAAAhsvLy1OnTp3UsmVLRUZGytHRuJnX5UKzTuRcVpHZImcnRzVv4Ca3Wk6GZHniiSe0evVq7d27V02aNDEkw+0w5rsDAABwDQ8PD82bN0/9+vXTxx9/rD//+c+V+vxHsi/q221p2nLotNJy83XttM1BUtP6rurb1lOP9WyqNl6V8+aY1atXa/78+Zo3b55Nl0mJCSUAALAhr7zyij777DNt3bpV3bp1q/DnO5mbrze/S1bs0bOq4eigYsuv16Kfbw9s3VDvP9xJTepX3OeOZ2RkqFu3burdu7e+++47OTg4VNhzlQcKJQAAsBkFBQUKDAzU4cOHtXr1avXt27fCnmtJYpqmrt0ns8V6yyL5SzUcHeTk6KDpwztobI+m5Z7r0KFDGjx4sIqLi/Xjjz/Ky8ur3J+jvPGmHAAAYDNcXFwUGRmp+++/X0OGDNHSpUsr5Hk+23JEU1Ylq9BsKVWZlKRii1WFZoumrErWZ1uOlGuurVu3yt/fX+7u7kpISLCLMilRKAEAgI3x8PDQhg0bNGbMGI0dO1YzZsyQ2Wwut+MvSUzTR5sOl8uxPtp0WEsT08p8HKvVqqVLl6p///7q0KGDYmNjbf51k9di5Q0AAGyS1WrV22+/rffee++662fMmKEpU6bc0TFP5uZrwKxoFZot5RFRklTLyVERL/cpeU1lUlJSyUnag4ODFRwcfMNj8vLy9N5772nFihU6efKkHBwcVFRUpAceeEArV65U7dq1yy1fZaBQAgAAm3X16lU1atRIFy5cKLmuXbt2d3yS7/FfbVNCSk6p19y3UsPRQf4tG2jB0z0lSfPmzdPEiRMlSVOnTtW0adOuu39eXp4CAwO1Z8+eG4511113KTo6Wp06dSq3fJWBlTcAALBZ4eHh15VJSTpw4IDGjBmj7du3qzRzsSPZFxV79Gy5lknpp9dUxh49q6OnL97W/V966aWSMuno6Kjx48frmWeekSSdO3dOTz/9dLnmqwxMKAEAgM2aMGGCFixYIEkaO3aslixZIkmqU6eOLl68qPbt2+upp57S448/rtjYWE2bNk1Hjx5V69at9de//lX79+/X9OnTJUkPvfiukt27lhTKotPHdWHrchWmJav4ykXVcPVQ7ZbdVTdgnJw8GpZkOB/7rS7EL5YkNQj5kyyF+bq4Y73MF8+oZn0/3dX/Wbm37KLxPZtp3otDf/XTfh566CHl5OQoLi6u5LodO3aoW7duslqtat++vQ4ePChJ+vHHH3XfffeV83ez4jChBAAANqmgoKDktYiNGjXSxx9/LCennz6TxcfHR2FhYerUqZPefPNN+fj46JFHHtG+fftUWFioffv2acyYMSWPl6QDWXklZfLKsR916ps/K/9AjIovn5MsZhVfytWlPZuU9c3Luno+66aZLiQs1bnI/8h8/pRUbNbVMyd0ZtW7Ksq/qC2HT9/y61mzZo0KCwtLft+iRYuSc206ODiod+/eJbfFxsaW+vtlJAolAACwSevXr9fFiz+tkUeMGCEvL6+SN7gcOnRInp6eWrJkidLT01W3bt3rHluzZk35+Pho9+7dJdflXCqSJFmuFujshllS8VXJsYbqBU2Q55h35NHzp8/LLr58Trmb/n3
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "agents = [ConversableAgent(name=f\"Agent{i}\", llm_config=False) for i in range(2)]\n",
    "allowed_speaker_transitions_dict = {\n",
    "    agents[0]: [agents[0], agents[1]],\n",
    "    agents[1]: [agents[0], agents[1]],\n",
    "}\n",
    "\n",
    "visualize_speaker_transitions_dict(allowed_speaker_transitions_dict, agents)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Set your API Endpoint\n",
    "\n",
    "The [`config_list_from_json`](https://microsoft.github.io/autogen/docs/reference/oai/openai_utils#config_list_from_json) function loads a list of configurations from an environment variable or a json file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The default config list in notebook.\n",
    "config_list = autogen.config_list_from_json(\n",
    "    \"OAI_CONFIG_LIST\",\n",
    "    file_location=\".\",\n",
    "    filter_dict={\n",
    "        \"model\": [\"gpt-3.5-turbo\", \"gpt-35-turbo\", \"gpt-35-turbo-0613\", \"gpt-4\", \"gpt4\", \"gpt-4-32k\"],\n",
    "    },\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It first looks for environment variable \"OAI_CONFIG_LIST\" which needs to be a valid json string. If that variable is not found, it then looks for a json file named \"OAI_CONFIG_LIST\". It filters the configs by models (you can filter by other keys as well). Only the gpt-4 models are kept in the list based on the filter condition.\n",
    "\n",
    "The config list looks like the following:\n",
    "```python\n",
    "config_list = [\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your OpenAI API key here>',\n",
    "    },\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your Azure OpenAI API key here>',\n",
    "        'base_url': '<your Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },\n",
    "    {\n",
    "        'model': 'gpt-4-32k',\n",
    "        'api_key': '<your Azure OpenAI API key here>',\n",
    "        'base_url': '<your Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },\n",
    "]\n",
    "```\n",
    "\n",
    "If you open this notebook in colab, you can upload your files by clicking the file icon on the left panel and then choosing \"upload file\" icon.\n",
    "\n",
    "You can set the value of config_list in other ways you prefer, e.g., loading from a YAML file."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Demonstration"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`GroupChat` now takes in two optional arguments.\n",
    "- speaker_transitions_dict: a dictionary of keys and list as values. The keys are the names of the agents, and the values are the agents that the key agent can transition to. Default is None, in which case a fully connected graph is assumed.\n",
    "- is_allowed_graph: whether the speaker_transitions_dict is a list of allowed agents or disallowed agents. Default is True, in which case the speaker_transitions_dict is a list of allowed agents. If set to False, then the speaker_transitions_dict is a list of disallowed agents."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Team Operations\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 1200x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# llm config\n",
    "llm_config = {\"config_list\": config_list_gpt4, \"cache_seed\": 100}\n",
    "\n",
    "# Create an empty directed graph\n",
    "agents = []\n",
    "speaker_transitions_dict = {}\n",
    "secret_values = {}\n",
    "\n",
    "# Outer loop for prefixes 'A', 'B', 'C'\n",
    "for prefix in [\"A\", \"B\", \"C\"]:\n",
    "    # Add 3 nodes with each prefix to the graph using a for loop\n",
    "    for i in range(3):\n",
    "        node_id = f\"{prefix}{i}\"\n",
    "        secret_value = random.randint(1, 5)  # Generate a random secret value\n",
    "        secret_values[node_id] = secret_value\n",
    "\n",
    "        # Create an AssistantAgent for each node (assuming AssistantAgent is a defined class)\n",
    "        agents.append(\n",
    "            AssistantAgent(\n",
    "                name=node_id,\n",
    "                system_message=f\"\"\"Your name is {node_id}.\n",
    "                                          Do not respond as the speaker named in the NEXT tag if your name is not in the NEXT tag. Instead, suggest a relevant team leader to handle the mis-tag, with the NEXT: tag.\n",
    "\n",
    "                                          You have {secret_value} chocolates.\n",
    "\n",
    "                                          The list of players are [A0, A1, A2, B0, B1, B2, C0, C1, C2].\n",
    "\n",
    "                                            Your first character of your name is your team, and your second character denotes that you are a team leader if it is 0.\n",
    "                                            CONSTRAINTS: Team members can only talk within the team, whilst team leader can talk to team leaders of other teams but not team members of other teams.\n",
    "\n",
    "                                            You can use NEXT: to suggest the next speaker. You have to respect the CONSTRAINTS, and can only suggest one player from the list of players, i.e., do not suggest A3 because A3 is not from the list of players.\n",
    "                                            Team leaders must make sure that they know the sum of the individual chocolate count of all three players in their own team, i.e., A0 is responsible for team A only.\n",
    "\n",
    "                                          Keep track of the player's tally using a JSON format so that others can check the total tally. Use\n",
    "                                          A0:?, A1:?, A2:?,\n",
    "                                          B0:?, B1:?, B2:?,\n",
    "                                          C0:?, C1:?, C2:?\n",
    "\n",
    "                                          If you are the team leader, you should aggregate your team's total chocolate count to cooperate.\n",
    "                                          Once the team leader know their team's tally, they can suggest another team leader for them to find their team tally, because we need all three team tallys to succeed.\n",
    "                                          Use NEXT: to suggest the next speaker, e.g., NEXT: A0.\n",
    "\n",
    "                                          Once we have the total tally from all nine players, sum up all three teams' tally, then terminate the discussion using TERMINATE.\n",
    "\n",
    "                                          \"\"\",\n",
    "                llm_config=llm_config,\n",
    "            )\n",
    "        )\n",
    "        speaker_transitions_dict[agents[-1]] = []\n",
    "\n",
    "    # Add edges between nodes with the same prefix using a nested for loop\n",
    "    for source_node in range(3):\n",
    "        source_id = f\"{prefix}{source_node}\"\n",
    "        for target_node in range(3):\n",
    "            target_id = f\"{prefix}{target_node}\"\n",
    "            if source_node != target_node:  # To avoid self-loops\n",
    "                speaker_transitions_dict[get_agent_of_name(agents, source_id)].append(\n",
    "                    get_agent_of_name(agents, name=target_id)\n",
    "                )\n",
    "\n",
    "\n",
    "# Adding edges between teams\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"A0\")].append(get_agent_of_name(agents, name=\"B0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"A0\")].append(get_agent_of_name(agents, name=\"C0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"B0\")].append(get_agent_of_name(agents, name=\"A0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"B0\")].append(get_agent_of_name(agents, name=\"C0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"C0\")].append(get_agent_of_name(agents, name=\"A0\"))\n",
    "speaker_transitions_dict[get_agent_of_name(agents, \"C0\")].append(get_agent_of_name(agents, name=\"B0\"))\n",
    "\n",
    "\n",
    "# Visualization only\n",
    "\n",
    "graph = nx.DiGraph()\n",
    "\n",
    "# Add nodes\n",
    "graph.add_nodes_from([agent.name for agent in agents])\n",
    "\n",
    "# Add edges\n",
    "for key, value in speaker_transitions_dict.items():\n",
    "    for agent in value:\n",
    "        graph.add_edge(key.name, agent.name)\n",
    "\n",
    "# Visualize\n",
    "\n",
    "\n",
    "# Draw the graph with secret values annotated\n",
    "plt.figure(figsize=(12, 10))\n",
    "pos = nx.spring_layout(graph)  # positions for all nodes\n",
    "\n",
    "# Draw nodes with their colors\n",
    "nx.draw(graph, pos, with_labels=True, font_weight=\"bold\")\n",
    "\n",
    "# Annotate secret values\n",
    "for node, (x, y) in pos.items():\n",
    "    secret_value = secret_values[node]\n",
    "    plt.text(x, y + 0.1, s=f\"Secret: {secret_value}\", horizontalalignment=\"center\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Termination message detection\n",
    "\n",
    "\n",
    "def is_termination_msg(content) -> bool:\n",
    "    have_content = content.get(\"content\", None) is not None\n",
    "    if have_content and \"TERMINATE\" in content[\"content\"]:\n",
    "        return True\n",
    "    return False\n",
    "\n",
    "\n",
    "# Terminates the conversation when TERMINATE is detected.\n",
    "user_proxy = autogen.UserProxyAgent(\n",
    "    name=\"User_proxy\",\n",
    "    system_message=\"Terminator admin.\",\n",
    "    code_execution_config=False,\n",
    "    is_termination_msg=is_termination_msg,\n",
    "    human_input_mode=\"NEVER\",\n",
    ")\n",
    "\n",
    "agents.append(user_proxy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:Warning: There are agents in self.agents not in graph.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mA0\u001b[0m (to chat_manager):\n",
      "\n",
      "\n",
      "                        There are 9 players in this game, split equally into Teams A, B, C. Therefore each team has 3 players, including the team leader.\n",
      "                        The task is to find out the sum of chocolate count from all nine players. I will now start with my team.\n",
      "                        NEXT: A1\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mA1\u001b[0m (to chat_manager):\n",
      "\n",
      "Sure, I, A1, have 3 chocolates. NEXT: A2\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mA2\u001b[0m (to chat_manager):\n",
      "\n",
      "As A2, I have 5 chocolates.\n",
      "\n",
      "So currently our tally is:\n",
      "A0:?, A1:3, A2:5, B0:?, B1:?, B2:?, C0:?, C1:?, C2:?\n",
      "  \n",
      "NEXT: A0\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mA0\u001b[0m (to chat_manager):\n",
      "\n",
      "Okay, as A0, I have 1 chocolate.\n",
      "\n",
      "Therefore, total chocolate count of team A is: \n",
      "1 (A0's chocolates) + 3 (A1's chocolates) + 5 (A2's chocolates) = 9 chocolates \n",
      "\n",
      "The running tally is:\n",
      "A0:1, A1:3, A2:5, \n",
      "B0:?, B1:?, B2:?, \n",
      "C0:?, C1:?, C2:?\n",
      "\n",
      "I suggest we move on to the next team. \n",
      "\n",
      "NEXT: B0\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mB0\u001b[0m (to chat_manager):\n",
      "\n",
      "As B0, I need to gather the count from my team members. \n",
      "\n",
      "NEXT: B1\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mB1\u001b[0m (to chat_manager):\n",
      "\n",
      "As B1, I have 1 chocolate. \n",
      "\n",
      "NEXT: B2\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mB2\u001b[0m (to chat_manager):\n",
      "\n",
      "As B2, I have 4 chocolates. \n",
      "\n",
      "So currently, our team B tally is:\n",
      "B0:?, B1:1, B2:4 \n",
      "\n",
      "NEXT: B0\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mB0\u001b[0m (to chat_manager):\n",
      "\n",
      "As B0, I have 1 chocolate. So, the total chocolate count for team B is:\n",
      "1 (B0's chocolates) + 1 (B1's chocolates) + 4 (B2's chocolates) = 6 chocolates.\n",
      "\n",
      "The updated tally is:\n",
      "A0:1, A1:3, A2:5, \n",
      "B0:1, B1:1, B2:4, \n",
      "C0:?, C1:?, C2:?\n",
      "\n",
      "I suggest we move on to the next team.\n",
      "\n",
      "NEXT: C0\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mC0\u001b[0m (to chat_manager):\n",
      "\n",
      "As C0, I will now gather the count from my team members. \n",
      "\n",
      "NEXT: C1\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mC1\u001b[0m (to chat_manager):\n",
      "\n",
      "As C1, I have 2 chocolates.\n",
      "\n",
      "NEXT: C2\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mC2\u001b[0m (to chat_manager):\n",
      "\n",
      "As C2, I have 1 chocolate.\n",
      "\n",
      "So currently, our team C tally is:\n",
      "C0:?, C1:2, C2:1\n",
      "\n",
      "NEXT: C0\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mC0\u001b[0m (to chat_manager):\n",
      "\n",
      "As C0, I'm the team leader and I have 1 chocolate. So, the total chocolate count for team C is:\n",
      "1 (C0's chocolates) + 2 (C1's chocolates) + 1 (C2's chocolates) = 4 chocolates.\n",
      "\n",
      "The final tally is:\n",
      "A0:1, A1:3, A2:5, \n",
      "B0:1, B1:1, B2:4, \n",
      "C0:1, C1:2, C2:1\n",
      "\n",
      "Now, the sum of chocolates from all nine players is:\n",
      "9 (team A's chocolates) + 6 (team B's chocolates) + 4 (team C's chocolates) = 19 chocolates.\n",
      "\n",
      "TERMINATE.\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "group_chat = GroupChat(\n",
    "    agents=agents,\n",
    "    messages=[],\n",
    "    max_round=20,\n",
    "    allowed_or_disallowed_speaker_transitions=speaker_transitions_dict,\n",
    "    speaker_transitions_type=\"allowed\",\n",
    ")\n",
    "\n",
    "\n",
    "# Create the manager\n",
    "manager = autogen.GroupChatManager(\n",
    "    groupchat=group_chat, llm_config=llm_config, code_execution_config=False, is_termination_msg=is_termination_msg\n",
    ")\n",
    "\n",
    "\n",
    "# Initiates the chat with Alice\n",
    "agents[0].initiate_chat(\n",
    "    manager,\n",
    "    message=\"\"\"\n",
    "                        There are 9 players in this game, split equally into Teams A, B, C. Therefore each team has 3 players, including the team leader.\n",
    "                        The task is to find out the sum of chocolate count from all nine players. I will now start with my team.\n",
    "                        NEXT: A1\"\"\",\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}