ReAct

This walkthrough showcases using an agent to implement the ReAct logic.

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.

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.

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

Using LCEL

We will first show how to create the agent using LCEL

from langchain.tools.render import render_text_description
from langchain.agents.output_parsers import ReActSingleInputOutputParser
from langchain.agents.format_scratchpad import format_log_to_str
from langchain import hub

prompt = hub.pull("hwchase17/react")
prompt = prompt.partial(
    tools=render_text_description(tools),
    tool_names=", ".join([t.name for t in tools]),
)

llm_with_stop = llm.bind(stop=["\nObservation"])

agent = (
    {
        "input": lambda x: x["input"],
        "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
    }
    | prompt
    | llm_with_stop
    | ReActSingleInputOutputParser()
)

from langchain.agents import AgentExecutor

agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

agent_executor.invoke(
    {
        "input": "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
    }
)

    
    
    > 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"model Vittoria Ceretti I need to find out Vittoria Ceretti's age
    Action: Search
    Action Input: "Vittoria Ceretti age"25 years I need to calculate 25 raised to the 0.43 power
    Action: Calculator
    Action Input: 25^0.43Answer: 3.991298452658078 I now know the final answer
    Final Answer: Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.
    
    > Finished chain.





    {'input': "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?",
     'output': "Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078."}

Using ZeroShotReactAgent

We will now show how to use the agent with an off-the-shelf agent implementation

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

agent_executor.invoke(
    {
        "input": "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
    }
)

    
    
    > 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: model Vittoria Ceretti
    Thought: I need to find out Vittoria Ceretti's age
    Action: Search
    Action Input: "Vittoria Ceretti 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: Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.
    
    > Finished chain.





    {'input': "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?",
     'output': "Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078."}

Using chat models

You can also create ReAct agents that use chat models instead of LLMs as the agent driver.

The main difference here is a different prompt. We will use JSON to encode the agent's actions (chat models are a bit tougher to steet, so using JSON helps to enforce the output format).

from langchain.chat_models import ChatOpenAI

chat_model = ChatOpenAI(temperature=0)

prompt = hub.pull("hwchase17/react-json")
prompt = prompt.partial(
    tools=render_text_description(tools),
    tool_names=", ".join([t.name for t in tools]),
)

chat_model_with_stop = chat_model.bind(stop=["\nObservation"])

from langchain.agents.output_parsers import ReActJsonSingleInputOutputParser

agent = (
    {
        "input": lambda x: x["input"],
        "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
    }
    | prompt
    | chat_model_with_stop
    | ReActJsonSingleInputOutputParser()
)

agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

agent_executor.invoke(
    {
        "input": "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
    }
)

We can also use an off-the-shelf agent class

agent = initialize_agent(
    tools, chat_model, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)
agent.run(
    "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
)