File size: 3,105 Bytes
acc4ffe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
{
"cells": [
{
"cell_type": "markdown",
"id": "5371a9bb",
"metadata": {},
"source": [
"# Tracing Walkthrough"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "17c04cc6-c93d-4b6c-a033-e897577f4ed1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\"\n",
"\n",
"## Uncomment this if using hosted setup.\n",
"\n",
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://langchain-api-gateway-57eoxz8z.uc.gateway.dev\" \n",
"\n",
"## Uncomment this if you want traces to be recorded to \"my_session\" instead of default.\n",
"\n",
"# os.environ[\"LANGCHAIN_SESSION\"] = \"my_session\" \n",
"\n",
"## Better to set this environment variable in the terminal\n",
"## Uncomment this if using hosted version. Replace \"my_api_key\" with your actual API Key.\n",
"\n",
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"my_api_key\" \n",
"\n",
"import langchain\n",
"from langchain.agents import Tool, initialize_agent, load_tools\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
"metadata": {
"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: 2^.123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\n",
"\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": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"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)\n",
"agent = initialize_agent(\n",
" tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
")\n",
"\n",
"agent.run(\"What is 2 raised to .123243 power?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "25addd7f",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|