langchain/docs/getting_started/agents.ipynb
2022-12-19 20:59:34 -05:00

183 lines
5.4 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "5436020b",
"metadata": {},
"source": [
"# Agents\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](../explanation/agents.md).\n",
"\n",
"**Tools**: For a list of predefined tools and their specifications, see [here](../explanation/tools.md)."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d01216c0",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"from langchain.agents import initialize_agent\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": null,
"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": 1,
"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": 2,
"id": "03208e2b",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "markdown",
"id": "373361d5",
"metadata": {},
"source": [
"Now let's test it out!"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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 Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
"Action: Search\n",
"Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m47 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 47 raised to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 47^0.23\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e7776981",
"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": "3.10.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}