langchain/docs/extras/integrations/providers/agent_with_wandb_tracing.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5371a9bb",
   "metadata": {},
   "source": [
    "# WandB Tracing\n",
    "\n",
    "There are two recommended ways to trace your LangChains:\n",
    "\n",
    "1. Setting the `LANGCHAIN_WANDB_TRACING` environment variable to \"true\".\n",
    "1. Using a context manager with tracing_enabled() to trace a particular block of code.\n",
    "\n",
    "**Note** if the environment variable is set, all code will be traced, regardless of whether or not it's within the context manager."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "17c04cc6-c93d-4b6c-a033-e897577f4ed1",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-18T12:47:46.580776Z",
     "start_time": "2023-05-18T12:47:46.577833Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "os.environ[\"LANGCHAIN_WANDB_TRACING\"] = \"true\"\n",
    "\n",
    "# wandb documentation to configure wandb using env variables\n",
    "# https://docs.wandb.ai/guides/track/advanced/environment-variables\n",
    "# here we are configuring the wandb project name\n",
    "os.environ[\"WANDB_PROJECT\"] = \"langchain-tracing\"\n",
    "\n",
    "from langchain.agents import initialize_agent, load_tools\n",
    "from langchain.agents import AgentType\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.callbacks import wandb_tracing_enabled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1b62cd48",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-18T12:47:47.445229Z",
     "start_time": "2023-05-18T12:47:47.436424Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "tools = load_tools([\"llm-math\"], llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-18T12:48:01.816137Z",
     "start_time": "2023-05-18T12:47:49.109574Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "agent = initialize_agent(\n",
    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
    ")\n",
    "\n",
    "agent.run(\"What is 2 raised to .123243 power?\")  # this should be traced\n",
    "# A url with for the trace sesion like the following should print in your console:\n",
    "# https://wandb.ai/<wandb_entity>/<wandb_project>/runs/<run_id>\n",
    "# The url can be used to view the trace session in wandb."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fe833c33-033f-4806-be0c-cc3d147db13d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-18T12:48:25.909223Z",
     "start_time": "2023-05-18T12:48:09.657895Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
      "Action: Calculator\n",
      "Action Input: 5^.123243\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
      "Final Answer: 1.2193914912400514\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
      "Action: Calculator\n",
      "Action Input: 2^.123243\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
      "Final Answer: 1.0891804557407723\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'1.0891804557407723'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now, we unset the environment variable and use a context manager.\n",
    "if \"LANGCHAIN_WANDB_TRACING\" in os.environ:\n",
    "    del os.environ[\"LANGCHAIN_WANDB_TRACING\"]\n",
    "\n",
    "# enable tracing using a context manager\n",
    "with wandb_tracing_enabled():\n",
    "    agent.run(\"What is 5 raised to .123243 power?\")  # this should be traced\n",
    "\n",
    "agent.run(\"What is 2 raised to .123243 power?\")  # this should not be traced"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "438fd64d",
   "metadata": {},
   "source": [
    "**Here's a view of wandb dashboard for the above tracing session:**\n",
    "\n",
    "\n",
    "![](data:image/png;base64,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
    "\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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}