notebook/agentchat_human_feedback.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/agentchat_human_feedback.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Auto Generated Agent Chat: Task Solving with Code Generation, Execution, Debugging & Human Feedback\n",
    "\n",
    "AutoGen offers conversable agents powered by LLM, tool or human, which can be used to perform tasks collectively via automated chat. This framwork allows tool use and human participance through multi-agent conversation.\n",
    "Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
    "\n",
    "In this notebook, we demonstrate how to use `AssistantAgent` and `UserProxyAgent` to solve a challenging math problem with human feedback. Here `AssistantAgent` is an LLM-based agent that can write Python code (in a Python coding block) for a user to execute for a given task. `UserProxyAgent` is an agent which serves as a proxy for a user to execute the code written by `AssistantAgent`. By setting `human_input_mode` properly, the `UserProxyAgent` can also prompt the user for feedback to `AssistantAgent`. For example, when `human_input_mode` is set to \"ALWAYS\", the `UserProxyAgent` will always prompt the user for feedback. When user feedback is provided, the `UserProxyAgent` will directly pass the feedback to `AssistantAgent`. When no user feedback is provided, the `UserProxyAgent` will execute the code written by `AssistantAgent` and return the execution results (success or failure and corresponding outputs) to `AssistantAgent`.\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": {
    "execution": {
     "iopub.execute_input": "2023-02-13T23:40:52.317406Z",
     "iopub.status.busy": "2023-02-13T23:40:52.316561Z",
     "iopub.status.idle": "2023-02-13T23:40:52.321193Z",
     "shell.execute_reply": "2023-02-13T23:40:52.320628Z"
    }
   },
   "outputs": [],
   "source": [
    "# %pip install pyautogen~=0.1.0"
   ]
  },
  {
   "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": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import autogen\n",
    "\n",
    "config_list = autogen.config_list_from_json(\"OAI_CONFIG_LIST\")"
   ]
  },
  {
   "attachments": {},
   "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\".\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",
    "    },  # OpenAI API endpoint for gpt-4\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your first Azure OpenAI API key here>',\n",
    "        'api_base': '<your first Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },  # Azure OpenAI API endpoint for gpt-4\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your second Azure OpenAI API key here>',\n",
    "        'api_base': '<your second Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },  # another Azure OpenAI API endpoint for gpt-4\n",
    "    {\n",
    "        'model': 'gpt-3.5-turbo',\n",
    "        'api_key': '<your OpenAI API key here>',\n",
    "    },  # OpenAI API endpoint for gpt-3.5-turbo\n",
    "    {\n",
    "        'model': 'gpt-3.5-turbo',\n",
    "        'api_key': '<your first Azure OpenAI API key here>',\n",
    "        'api_base': '<your first Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },  # Azure OpenAI API endpoint for gpt-3.5-turbo\n",
    "    {\n",
    "        'model': 'gpt-3.5-turbo',\n",
    "        'api_key': '<your second Azure OpenAI API key here>',\n",
    "        'api_base': '<your second Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },  # another Azure OpenAI API endpoint for gpt-3.5-turbo\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 choose \"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."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Construct Agents\n",
    "\n",
    "We construct the assistant agent and the user proxy agent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create an AssistantAgent instance named \"assistant\"\n",
    "assistant = autogen.AssistantAgent(\n",
    "    name=\"assistant\",\n",
    "    llm_config={\n",
    "        \"seed\": 41,\n",
    "        \"config_list\": config_list,\n",
    "    }\n",
    ")\n",
    "# create a UserProxyAgent instance named \"user_proxy\"\n",
    "user_proxy = autogen.UserProxyAgent(\n",
    "    name=\"user_proxy\",\n",
    "    human_input_mode=\"ALWAYS\",\n",
    "    is_termination_msg=lambda x: x.get(\"content\", \"\").rstrip().endswith(\"TERMINATE\"),\n",
    ")\n",
    "\n",
    "# the purpose of the following line is to log the conversation history\n",
    "autogen.ChatCompletion.start_logging()\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Perform a task\n",
    "\n",
    "We invoke the `initiate_chat()` method of the user proxy agent to start the conversation. When you run the cell below, you will be prompted to provide feedback after receving a message from the assistant agent. If you don't provide any feedback (by pressing Enter directly), the user proxy agent will try to execute the code suggested by the assistant agent on behalf of you, or terminate if the assistant agent sends a \"TERMINATE\" signal in the end of the message."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
      "\n",
      "\n",
      "Find $a + b + c$, given that $x+y \\neq -1$ and \n",
      "\\begin{align}\n",
      "\tax + by + c & = x + 7,\\\n",
      "\ta + bx + cy & = 2x + 6y,\\\n",
      "\tay + b + cx & = 4x + y.\n",
      "\\end{align}.\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
      "\n",
      "To solve the system of linear equations, I will use NumPy library in Python to calculate the coefficients and constants and then use the linalg.solve() function to find the values of a, b, and c. Finally, I will add them up to find $a + b + c$.\n",
      "\n",
      "Step 1: Define the coefficients and constants\n",
      "\n",
      "Step 2: Solve the system of equations using NumPy\n",
      "\n",
      "Step 3: Calculate the sum of a, b, and c\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
      "\n",
      "use sympy\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
      "\n",
      "Sure, I will use Sympy to solve the system of linear equations.\n",
      "\n",
      "Step 1: Import Sympy library and define the symbols\n",
      "``` python\n",
      "from sympy import symbols, Eq, solve\n",
      "\n",
      "a, b, c, x, y = symbols('a b c x y')\n",
      "```\n",
      "\n",
      "Step 2: Define the equations\n",
      "``` python\n",
      "eq1 = Eq(a * x + b * y + c, x + 7)\n",
      "eq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\n",
      "eq3 = Eq(a * y + b + c * x, 4 * x + y)\n",
      "```\n",
      "\n",
      "Step 3: Solve the system of equations\n",
      "``` python\n",
      "solutions = solve((eq1, eq2, eq3), (a, b, c))\n",
      "```\n",
      "\n",
      "Step 4: Calculate the sum of a, b, and c\n",
      "``` python\n",
      "a_value, b_value, c_value = solutions[a], solutions[b], solutions[c]\n",
      "sum_abc = a_value + b_value + c_value\n",
      "```\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> NO HUMAN INPUT RECEIVED.\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
      "\n",
      "exitcode: 1 (execution failed)\n",
      "Code output: \n",
      "  File \"\", line 2\n",
      "    Step 2: Define the equations\n",
      "         ^\n",
      "SyntaxError: invalid syntax\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
      "\n",
      "Apologies for the confusion. I should have provided the code in a single block without the step-by-step comments. Here is the code to solve the system of linear equations using Sympy:\n",
      "\n",
      "```python\n",
      "from sympy import symbols, Eq, solve\n",
      "\n",
      "a, b, c, x, y = symbols('a b c x y')\n",
      "\n",
      "eq1 = Eq(a * x + b * y + c, x + 7)\n",
      "eq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\n",
      "eq3 = Eq(a * y + b + c * x, 4 * x + y)\n",
      "\n",
      "solutions = solve((eq1, eq2, eq3), (a, b, c))\n",
      "\n",
      "a_value, b_value, c_value = solutions[a], solutions[b], solutions[c]\n",
      "sum_abc = a_value + b_value + c_value\n",
      "print(sum_abc)\n",
      "```\n",
      "\n",
      "Please run the provided code to find the sum of a, b, and c.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> NO HUMAN INPUT RECEIVED.\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: \n",
      "(2*x**2 - 3*x + y)/(x**2 - x*y - x + y**2 - y + 1) + (x**2 - 3*x*y + 2*x + y**2 - y)/(x**2 - x*y - x + y**2 - y + 1) + (4*x**2 - 4*x*y - 6*x + 6*y**2 - 7*y + 7)/(x**2 - x*y - x + y**2 - y + 1)\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
      "\n",
      "I apologize for the confusion. The code provided the sum of a, b, and c in a symbolic representation. To get an answer, we need to put some constraints on x and y for which x + y is not equal to -1.\n",
      "\n",
      "We can choose any values for x and y that don't satisfy x + y = -1, and then substitute them into the equation to find the corresponding sum of a, b, and c. Let's use x = 1 and y = 0, which satisfy the given condition.\n",
      "\n",
      "Here is the updated code with the chosen values for x and y:\n",
      "\n",
      "```python\n",
      "from sympy import symbols, Eq, solve\n",
      "\n",
      "a, b, c, x, y = symbols('a b c x y')\n",
      "\n",
      "eq1 = Eq(a * x + b * y + c, x + 7)\n",
      "eq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\n",
      "eq3 = Eq(a * y + b + c * x, 4 * x + y)\n",
      "\n",
      "solutions = solve((eq1, eq2, eq3), (a, b, c))\n",
      "\n",
      "chosen_x = 1\n",
      "chosen_y = 0\n",
      "\n",
      "a_value, b_value, c_value = solutions[a].subs(x, chosen_x).subs(y, chosen_y), solutions[b].subs(x, chosen_x).subs(y, chosen_y), solutions[c].subs(x, chosen_x).subs(y, chosen_y)\n",
      "sum_abc = a_value + b_value + c_value\n",
      "print(sum_abc)\n",
      "```\n",
      "\n",
      "Please run the provided code again to find the sum of a, b, and c.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> NO HUMAN INPUT RECEIVED.\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: \n",
      "7\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
      "\n",
      "Great! Now we have the sum of a, b, and c. The answer is:\n",
      "\n",
      "$$a + b + c = 7$$\n",
      "\n",
      "TERMINATE\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> NO HUMAN INPUT RECEIVED.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "math_problem_to_solve = \"\"\"\n",
    "Find $a + b + c$, given that $x+y \\\\neq -1$ and \n",
    "\\\\begin{align}\n",
    "\tax + by + c & = x + 7,\\\\\n",
    "\ta + bx + cy & = 2x + 6y,\\\\\n",
    "\tay + b + cx & = 4x + y.\n",
    "\\\\end{align}.\n",
    "\"\"\"\n",
    "\n",
    "# the assistant receives a message from the user, which contains the task description\n",
    "user_proxy.initiate_chat(assistant, message=math_problem_to_solve)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Analyze the conversation\n",
    "\n",
    "The human user can provide feedback at each step. When the human user didn't provide feedback, the code was executed. The executed results and error messages are returned to the assistant, and the assistant was able to modify the code based on the feedback. In the end, the task is complete and a \"TERMINATE\" signal is sent from the assistant. The user skipped feedback in the end and the conversation is finished.\n",
    "\n",
    "After the conversation is finished, we can save the log of the conversation between the two agents. The log can be accessed from `autogen.ChatCompletion.logged_history`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'[{\"content\": \"You are a helpful AI assistant.\\\\nSolve tasks using your coding and language skills.\\\\nIn the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.\\\\n    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.\\\\n    2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.\\\\nSolve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.\\\\nWhen using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can\\'t modify your code. So do not suggest incomplete code which requires users to modify. Don\\'t use a code block if it\\'s not intended to be executed by the user.\\\\nIf you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don\\'t include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use \\'print\\' function for the output when relevant. Check the execution result returned by the user.\\\\nIf the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can\\'t be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.\\\\nWhen you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.\\\\nReply \\\\\"TERMINATE\\\\\" in the end when everything is done.\\\\n    \", \"role\": \"system\"}, {\"content\": \"\\\\nFind $a + b + c$, given that $x+y \\\\\\\\neq -1$ and \\\\n\\\\\\\\begin{align}\\\\n\\\\tax + by + c & = x + 7,\\\\\\\\\\\\n\\\\ta + bx + cy & = 2x + 6y,\\\\\\\\\\\\n\\\\tay + b + cx & = 4x + y.\\\\n\\\\\\\\end{align}.\\\\n\", \"role\": \"user\"}, {\"content\": \"To solve the system of linear equations, I will use NumPy library in Python to calculate the coefficients and constants and then use the linalg.solve() function to find the values of a, b, and c. Finally, I will add them up to find $a + b + c$.\\\\n\\\\nStep 1: Define the coefficients and constants\\\\n\\\\nStep 2: Solve the system of equations using NumPy\\\\n\\\\nStep 3: Calculate the sum of a, b, and c\", \"role\": \"assistant\"}, {\"content\": \"use sympy\", \"role\": \"user\"}, {\"content\": \"Sure, I will use Sympy to solve the system of linear equations.\\\\n\\\\nStep 1: Import Sympy library and define the symbols\\\\n``` python\\\\nfrom sympy import symbols, Eq, solve\\\\n\\\\na, b, c, x, y = symbols(\\'a b c x y\\')\\\\n```\\\\n\\\\nStep 2: Define the equations\\\\n``` python\\\\neq1 = Eq(a * x + b * y + c, x + 7)\\\\neq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\\\\neq3 = Eq(a * y + b + c * x, 4 * x + y)\\\\n```\\\\n\\\\nStep 3: Solve the system of equations\\\\n``` python\\\\nsolutions = solve((eq1, eq2, eq3), (a, b, c))\\\\n```\\\\n\\\\nStep 4: Calculate the sum of a, b, and c\\\\n``` python\\\\na_value, b_value, c_value = solutions[a], solutions[b], solutions[c]\\\\nsum_abc = a_value + b_value + c_value\\\\n```\\\\n\\\\n\", \"role\": \"assistant\"}, {\"content\": \"exitcode: 1 (execution failed)\\\\nCode output: \\\\n  File \\\\\"\\\\\", line 2\\\\n    Step 2: Define the equations\\\\n         ^\\\\nSyntaxError: invalid syntax\\\\n\", \"role\": \"user\"}, {\"content\": \"Apologies for the confusion. I should have provided the code in a single block without the step-by-step comments. Here is the code to solve the system of linear equations using Sympy:\\\\n\\\\n```python\\\\nfrom sympy import symbols, Eq, solve\\\\n\\\\na, b, c, x, y = symbols(\\'a b c x y\\')\\\\n\\\\neq1 = Eq(a * x + b * y + c, x + 7)\\\\neq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\\\\neq3 = Eq(a * y + b + c * x, 4 * x + y)\\\\n\\\\nsolutions = solve((eq1, eq2, eq3), (a, b, c))\\\\n\\\\na_value, b_value, c_value = solutions[a], solutions[b], solutions[c]\\\\nsum_abc = a_value + b_value + c_value\\\\nprint(sum_abc)\\\\n```\\\\n\\\\nPlease run the provided code to find the sum of a, b, and c.\", \"role\": \"assistant\"}, {\"content\": \"exitcode: 0 (execution succeeded)\\\\nCode output: \\\\n(2*x**2 - 3*x + y)/(x**2 - x*y - x + y**2 - y + 1) + (x**2 - 3*x*y + 2*x + y**2 - y)/(x**2 - x*y - x + y**2 - y + 1) + (4*x**2 - 4*x*y - 6*x + 6*y**2 - 7*y + 7)/(x**2 - x*y - x + y**2 - y + 1)\\\\n\", \"role\": \"user\"}, {\"content\": \"I apologize for the confusion. The code provided the sum of a, b, and c in a symbolic representation. To get an answer, we need to put some constraints on x and y for which x + y is not equal to -1.\\\\n\\\\nWe can choose any values for x and y that don\\'t satisfy x + y = -1, and then substitute them into the equation to find the corresponding sum of a, b, and c. Let\\'s use x = 1 and y = 0, which satisfy the given condition.\\\\n\\\\nHere is the updated code with the chosen values for x and y:\\\\n\\\\n```python\\\\nfrom sympy import symbols, Eq, solve\\\\n\\\\na, b, c, x, y = symbols(\\'a b c x y\\')\\\\n\\\\neq1 = Eq(a * x + b * y + c, x + 7)\\\\neq2 = Eq(a + b * x + c * y, 2 * x + 6 * y)\\\\neq3 = Eq(a * y + b + c * x, 4 * x + y)\\\\n\\\\nsolutions = solve((eq1, eq2, eq3), (a, b, c))\\\\n\\\\nchosen_x = 1\\\\nchosen_y = 0\\\\n\\\\na_value, b_value, c_value = solutions[a].subs(x, chosen_x).subs(y, chosen_y), solutions[b].subs(x, chosen_x).subs(y, chosen_y), solutions[c].subs(x, chosen_x).subs(y, chosen_y)\\\\nsum_abc = a_value + b_value + c_value\\\\nprint(sum_abc)\\\\n```\\\\n\\\\nPlease run the provided code again to find the sum of a, b, and c.\", \"role\": \"assistant\"}, {\"content\": \"exitcode: 0 (execution succeeded)\\\\nCode output: \\\\n7\\\\n\", \"role\": \"user\"}, {\"content\": \"Great! Now we have the sum of a, b, and c. The answer is:\\\\n\\\\n$$a + b + c = 7$$\\\\n\\\\nTERMINATE\", \"role\": \"assistant\"}]': {'created_at': [0, 1, 2, 3, 4], 'cost': [0.022019999999999998, 0.03305999999999999, 0.04019999999999999, 0.058589999999999996, 0.050969999999999994]}}\n"
     ]
    }
   ],
   "source": [
    "print(autogen.ChatCompletion.logged_history)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "\n",
    "json.dump(autogen.ChatCompletion.logged_history, open(\"conversations.json\", \"w\"), indent=2)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.17"
  },
  "vscode": {
   "interpreter": {
    "hash": "949777d72b0d2535278d3dc13498b2535136f6dfe0678499012e853ee9abcab1"
   }
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {
     "2d910cfd2d2a4fc49fc30fbbdc5576a7": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "2.0.0",
      "model_name": "LayoutModel",
      "state": {
       "_model_module": "@jupyter-widgets/base",
       "_model_module_version": "2.0.0",
       "_model_name": "LayoutModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "LayoutView",
       "align_content": null,
       "align_items": null,
       "align_self": null,
       "border_bottom": null,
       "border_left": null,
       "border_right": null,
       "border_top": null,
       "bottom": null,
       "display": null,
       "flex": null,
       "flex_flow": null,
       "grid_area": null,
       "grid_auto_columns": null,
       "grid_auto_flow": null,
       "grid_auto_rows": null,
       "grid_column": null,
       "grid_gap": null,
       "grid_row": null,
       "grid_template_areas": null,
       "grid_template_columns": null,
       "grid_template_rows": null,
       "height": null,
       "justify_content": null,
       "justify_items": null,
       "left": null,
       "margin": null,
       "max_height": null,
       "max_width": null,
       "min_height": null,
       "min_width": null,
       "object_fit": null,
       "object_position": null,
       "order": null,
       "overflow": null,
       "padding": null,
       "right": null,
       "top": null,
       "visibility": null,
       "width": null
      }
     },
     "454146d0f7224f038689031002906e6f": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "HBoxModel",
      "state": {
       "_dom_classes": [],
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "HBoxModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/controls",
       "_view_module_version": "2.0.0",
       "_view_name": "HBoxView",
       "box_style": "",
       "children": [
        "IPY_MODEL_e4ae2b6f5a974fd4bafb6abb9d12ff26",
        "IPY_MODEL_577e1e3cc4db4942b0883577b3b52755",
        "IPY_MODEL_b40bdfb1ac1d4cffb7cefcb870c64d45"
       ],
       "layout": "IPY_MODEL_dc83c7bff2f241309537a8119dfc7555",
       "tabbable": null,
       "tooltip": null
      }
     },
     "577e1e3cc4db4942b0883577b3b52755": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "FloatProgressModel",
      "state": {
       "_dom_classes": [],
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "FloatProgressModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/controls",
       "_view_module_version": "2.0.0",
       "_view_name": "ProgressView",
       "bar_style": "success",
       "description": "",
       "description_allow_html": false,
       "layout": "IPY_MODEL_2d910cfd2d2a4fc49fc30fbbdc5576a7",
       "max": 1,
       "min": 0,
       "orientation": "horizontal",
       "style": "IPY_MODEL_74a6ba0c3cbc4051be0a83e152fe1e62",
       "tabbable": null,
       "tooltip": null,
       "value": 1
      }
     },
     "6086462a12d54bafa59d3c4566f06cb2": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "2.0.0",
      "model_name": "LayoutModel",
      "state": {
       "_model_module": "@jupyter-widgets/base",
       "_model_module_version": "2.0.0",
       "_model_name": "LayoutModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "LayoutView",
       "align_content": null,
       "align_items": null,
       "align_self": null,
       "border_bottom": null,
       "border_left": null,
       "border_right": null,
       "border_top": null,
       "bottom": null,
       "display": null,
       "flex": null,
       "flex_flow": null,
       "grid_area": null,
       "grid_auto_columns": null,
       "grid_auto_flow": null,
       "grid_auto_rows": null,
       "grid_column": null,
       "grid_gap": null,
       "grid_row": null,
       "grid_template_areas": null,
       "grid_template_columns": null,
       "grid_template_rows": null,
       "height": null,
       "justify_content": null,
       "justify_items": null,
       "left": null,
       "margin": null,
       "max_height": null,
       "max_width": null,
       "min_height": null,
       "min_width": null,
       "object_fit": null,
       "object_position": null,
       "order": null,
       "overflow": null,
       "padding": null,
       "right": null,
       "top": null,
       "visibility": null,
       "width": null
      }
     },
     "74a6ba0c3cbc4051be0a83e152fe1e62": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "ProgressStyleModel",
      "state": {
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "ProgressStyleModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "StyleView",
       "bar_color": null,
       "description_width": ""
      }
     },
     "7d3f3d9e15894d05a4d188ff4f466554": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "HTMLStyleModel",
      "state": {
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "HTMLStyleModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "StyleView",
       "background": null,
       "description_width": "",
       "font_size": null,
       "text_color": null
      }
     },
     "b40bdfb1ac1d4cffb7cefcb870c64d45": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "HTMLModel",
      "state": {
       "_dom_classes": [],
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "HTMLModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/controls",
       "_view_module_version": "2.0.0",
       "_view_name": "HTMLView",
       "description": "",
       "description_allow_html": false,
       "layout": "IPY_MODEL_f1355871cc6f4dd4b50d9df5af20e5c8",
       "placeholder": "​",
       "style": "IPY_MODEL_ca245376fd9f4354af6b2befe4af4466",
       "tabbable": null,
       "tooltip": null,
       "value": " 1/1 [00:00&lt;00:00, 44.69it/s]"
      }
     },
     "ca245376fd9f4354af6b2befe4af4466": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "HTMLStyleModel",
      "state": {
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "HTMLStyleModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "StyleView",
       "background": null,
       "description_width": "",
       "font_size": null,
       "text_color": null
      }
     },
     "dc83c7bff2f241309537a8119dfc7555": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "2.0.0",
      "model_name": "LayoutModel",
      "state": {
       "_model_module": "@jupyter-widgets/base",
       "_model_module_version": "2.0.0",
       "_model_name": "LayoutModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "LayoutView",
       "align_content": null,
       "align_items": null,
       "align_self": null,
       "border_bottom": null,
       "border_left": null,
       "border_right": null,
       "border_top": null,
       "bottom": null,
       "display": null,
       "flex": null,
       "flex_flow": null,
       "grid_area": null,
       "grid_auto_columns": null,
       "grid_auto_flow": null,
       "grid_auto_rows": null,
       "grid_column": null,
       "grid_gap": null,
       "grid_row": null,
       "grid_template_areas": null,
       "grid_template_columns": null,
       "grid_template_rows": null,
       "height": null,
       "justify_content": null,
       "justify_items": null,
       "left": null,
       "margin": null,
       "max_height": null,
       "max_width": null,
       "min_height": null,
       "min_width": null,
       "object_fit": null,
       "object_position": null,
       "order": null,
       "overflow": null,
       "padding": null,
       "right": null,
       "top": null,
       "visibility": null,
       "width": null
      }
     },
     "e4ae2b6f5a974fd4bafb6abb9d12ff26": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "2.0.0",
      "model_name": "HTMLModel",
      "state": {
       "_dom_classes": [],
       "_model_module": "@jupyter-widgets/controls",
       "_model_module_version": "2.0.0",
       "_model_name": "HTMLModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/controls",
       "_view_module_version": "2.0.0",
       "_view_name": "HTMLView",
       "description": "",
       "description_allow_html": false,
       "layout": "IPY_MODEL_6086462a12d54bafa59d3c4566f06cb2",
       "placeholder": "​",
       "style": "IPY_MODEL_7d3f3d9e15894d05a4d188ff4f466554",
       "tabbable": null,
       "tooltip": null,
       "value": "100%"
      }
     },
     "f1355871cc6f4dd4b50d9df5af20e5c8": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "2.0.0",
      "model_name": "LayoutModel",
      "state": {
       "_model_module": "@jupyter-widgets/base",
       "_model_module_version": "2.0.0",
       "_model_name": "LayoutModel",
       "_view_count": null,
       "_view_module": "@jupyter-widgets/base",
       "_view_module_version": "2.0.0",
       "_view_name": "LayoutView",
       "align_content": null,
       "align_items": null,
       "align_self": null,
       "border_bottom": null,
       "border_left": null,
       "border_right": null,
       "border_top": null,
       "bottom": null,
       "display": null,
       "flex": null,
       "flex_flow": null,
       "grid_area": null,
       "grid_auto_columns": null,
       "grid_auto_flow": null,
       "grid_auto_rows": null,
       "grid_column": null,
       "grid_gap": null,
       "grid_row": null,
       "grid_template_areas": null,
       "grid_template_columns": null,
       "grid_template_rows": null,
       "height": null,
       "justify_content": null,
       "justify_items": null,
       "left": null,
       "margin": null,
       "max_height": null,
       "max_width": null,
       "min_height": null,
       "min_width": null,
       "object_fit": null,
       "object_position": null,
       "order": null,
       "overflow": null,
       "padding": null,
       "right": null,
       "top": null,
       "visibility": null,
       "width": null
      }
     }
    },
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}