Spaces:
Runtime error
Runtime error
File size: 3,882 Bytes
eefd46e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"from langchain.agents import initialize_agent\n",
"from langchain.agents import AgentType\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0, model_name='text-davinci-002')\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"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 know who the current CEO of TikTok is, and then I need to do some math.\n",
"Action: Search\n",
"Action Input: \"TikTok CEO\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mShou Chew\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to know how old Shou Chew is.\n",
"Action: Search\n",
"Action Input: \"Shou Chew age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m40 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to do some math.\n",
"Action: Calculator\n",
"Action Input: 40+10\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 50\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The current CEO of TikTok is Shou Chew, and he is 50 years old.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
}
],
"source": [
"response = agent({\"input\":\"抖音现任的CEO是谁？他年龄加10岁等于多少？\"})"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[\n",
" [\n",
" [\n",
" \"Search\",\n",
" \"TikTok CEO\",\n",
" \" I need to know who the current CEO of TikTok is, and then I need to do some math.\\nAction: Search\\nAction Input: \\\"TikTok CEO\\\"\"\n",
" ],\n",
" \"Shou Chew\"\n",
" ],\n",
" [\n",
" [\n",
" \"Search\",\n",
" \"Shou Chew age\",\n",
" \" I need to know how old Shou Chew is.\\nAction: Search\\nAction Input: \\\"Shou Chew age\\\"\"\n",
" ],\n",
" \"40 years\"\n",
" ],\n",
" [\n",
" [\n",
" \"Calculator\",\n",
" \"40+10\",\n",
" \" I need to do some math.\\nAction: Calculator\\nAction Input: 40+10\"\n",
" ],\n",
" \"Answer: 50\"\n",
" ]\n",
"]\n"
]
}
],
"source": [
"# The actual return type is a NamedTuple for the agent action, and then an observation\n",
"# print(response[\"intermediate_steps\"])\n",
"\n",
"import json\n",
"print(json.dumps(response[\"intermediate_steps\"], indent=2))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.10.10"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|