langchain/docs/modules/agents/getting_started.ipynb

Getting Started

Agents use an LLM to determine which actions to take and in what order. An action can either be using a tool and observing its output, or returning to the user.

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.

In order to load agents, you should understand the following concepts:

• 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.
• LLM: The language model powering the agent.
• 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).

Agents: For a list of supported agents and their specifications, see here.

Tools: For a list of predefined tools and their specifications, see here.

In [1]:

from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI

First, let's load the language model we're going to use to control the agent.

In [2]:

llm = OpenAI(temperature=0)

Next, let's load some tools to use. Note that the llm-math tool uses an LLM, so we need to pass that in.

In [3]:

tools = load_tools(["serpapi", "llm-math"], llm=llm)

Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.

In [6]:

agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)

Now let's test it out!

In [13]:

agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")

Out [13]:

> Entering new AgentExecutor chain...
 I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.
Action: Search
Action Input: "Leo DiCaprio girlfriend"
Observation: Camila Morrone
Thought: I need to find out Camila Morrone's age
Action: Search
Action Input: "Camila Morrone age"
Observation: 25 years
Thought: I need to calculate 25 raised to the 0.43 power
Action: Calculator
Action Input: 25^0.43
Observation: Answer: 3.991298452658078

Thought: I now know the final answer
Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.

> Finished chain.

"Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078."

In [ ]: