Spaces:
Sleeping
Sleeping
File size: 5,547 Bytes
cfd3735 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 |
{
"cells": [
{
"cell_type": "markdown",
"id": "5436020b",
"metadata": {},
"source": [
"# Getting Started\n",
"\n",
"Agents use an LLM to determine which actions to take and in what order.\n",
"An action can either be using a tool and observing its output, or returning to the user.\n",
"\n",
"When used correctly agents can be extremely powerful. The purpose of this notebook is to show you how to easily use agents through the simplest, highest level API."
]
},
{
"cell_type": "markdown",
"id": "3c6226b9",
"metadata": {},
"source": [
"In order to load agents, you should understand the following concepts:\n",
"\n",
"- Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
"- LLM: The language model powering the agent.\n",
"- Agent: The agent to use. This should be a string that references a support agent class. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon).\n",
"\n",
"**Agents**: For a list of supported agents and their specifications, see [here](agents.md).\n",
"\n",
"**Tools**: For a list of predefined tools and their specifications, see [here](tools.md)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "d01216c0",
"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": "markdown",
"id": "ef965094",
"metadata": {},
"source": [
"First, let's load the language model we're going to use to control the agent."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "0728f0d9",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "fb29d592",
"metadata": {},
"source": [
"Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ba4e7618",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
]
},
{
"cell_type": "markdown",
"id": "0b50fc9b",
"metadata": {},
"source": [
"Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "03208e2b",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "markdown",
"id": "373361d5",
"metadata": {},
"source": [
"Now let's test it out!"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "244ee75c",
"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 find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
"Action: Search\n",
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mCamila Morrone\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Camila Morrone's age\n",
"Action: Search\n",
"Action Input: \"Camila Morrone age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m25 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.43 power\n",
"Action: Calculator\n",
"Action Input: 25^0.43\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.\""
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5901695b",
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|