How to add human-in-the-loop processes to the prebuilt ReAct agent

Contents

How to add human-in-the-loop processes to the prebuilt ReAct agent#

Prerequisites

This guide assumes familiarity with the following:

This guide will show how to add human-in-the-loop processes to the prebuilt ReAct agent. Please see this tutorial for how to get started with the prebuilt ReAct agent

You can add a a breakpoint before tools are called by passing interrupt_before=["tools"] to create_react_agent. Note that you need to be using a checkpointer for this to work.

Setup#

First, let’s install the required packages and set our API keys

%%capture --no-stderr
%pip install -U langgraph langchain-openai

import getpass
import os


def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("OPENAI_API_KEY")

Set up LangSmith for LangGraph development

Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started here.

Code#

# First we initialize the model we want to use.
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o", temperature=0)

# For this tutorial we will use custom tool that returns pre-defined values for weather in two cities (NYC & SF)

from langchain_core.tools import tool


@tool
def get_weather(location: str):
    """Use this to get weather information from a given location."""
    if location.lower() in ["nyc", "new york"]:
        return "It might be cloudy in nyc"
    elif location.lower() in ["sf", "san francisco"]:
        return "It's always sunny in sf"
    else:
        raise AssertionError("Unknown Location")


tools = [get_weather]

# We need a checkpointer to enable human-in-the-loop patterns
# Using Redis checkpointer for persistence
from langgraph.checkpoint.redis import RedisSaver
from langgraph.checkpoint.redis.version import __version__
print(__version__)

# Set up Redis connection
REDIS_URI = "redis://redis:6379"
memory = None
with RedisSaver.from_conn_string(REDIS_URI) as cp:
    cp.setup()
    memory = cp

# Define the graph

from langgraph.prebuilt import create_react_agent

graph = create_react_agent(
    model, tools=tools, interrupt_before=["tools"], checkpointer=memory
)

0.2.0
20:54:48 langgraph.checkpoint.redis INFO   Redis client is a standalone client

/tmp/ipykernel_196/104821471.py:41: LangGraphDeprecatedSinceV10: create_react_agent has been moved to `langchain.agents`. Please update your import to `from langchain.agents import create_agent`. Deprecated in LangGraph V1.0 to be removed in V2.0.
  graph = create_react_agent(

Usage#

def print_stream(stream):
    """A utility to pretty print the stream."""
    for s in stream:
        message = s["messages"][-1]
        if isinstance(message, tuple):
            print(message)
        else:
            message.pretty_print()

import uuid

config = {"configurable": {"thread_id": str(uuid.uuid4())}}
inputs = {"messages": [("user", "what is the weather in SF, CA?")]}

print_stream(graph.stream(inputs, config, stream_mode="values"))

================================ Human Message =================================

what is the weather in SF, CA?
20:54:49 httpx INFO   HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
================================== Ai Message ==================================
Tool Calls:
  get_weather (call_JQR9gMUJPiZEZ1HgkJsUYIYA)
 Call ID: call_JQR9gMUJPiZEZ1HgkJsUYIYA
  Args:
    location: SF, CA

We can verify that our graph stopped at the right place:

snapshot = graph.get_state(config)
print("Next step: ", snapshot.next)

20:54:49 langgraph WARNING   Ignoring invalid packet type <class 'dict'> in pending sends
Next step:  ()

Now we can either approve or edit the tool call before proceeding to the next node. If we wanted to approve the tool call, we would simply continue streaming the graph with None input. If we wanted to edit the tool call we need to update the state to have the correct tool call, and then after the update has been applied we can continue.

We can try resuming and we will see an error arise:

print_stream(graph.stream(None, config, stream_mode="values"))

20:54:49 langgraph WARNING   Ignoring invalid packet type <class 'dict'> in pending sends
================================== Ai Message ==================================
Tool Calls:
  get_weather (call_JQR9gMUJPiZEZ1HgkJsUYIYA)
 Call ID: call_JQR9gMUJPiZEZ1HgkJsUYIYA
  Args:
    location: SF, CA

This error arose because our tool argument of “San Francisco, CA” is not a location our tool recognizes.

Let’s show how we would edit the tool call to search for “San Francisco” instead of “San Francisco, CA” - since our tool as written treats “San Francisco, CA” as an unknown location. We will update the state and then resume streaming the graph and should see no errors arise:

state = graph.get_state(config)

last_message = state.values["messages"][-1]
last_message.tool_calls[0]["args"] = {"location": "San Francisco"}

graph.update_state(config, {"messages": [last_message]})

20:54:49 langgraph WARNING   Ignoring invalid packet type <class 'dict'> in pending sends
20:54:49 langgraph WARNING   Ignoring invalid packet type <class 'dict'> in pending sends

{'configurable': {'thread_id': '18c43cd5-0bf0-40dd-a7f2-316450e0022e',
  'checkpoint_ns': '',
  'checkpoint_id': '1f0c3f7a-8519-617a-8002-a6eecd3547b9'}}

print_stream(graph.stream(None, config, stream_mode="values"))

20:54:49 langgraph WARNING   Ignoring invalid packet type <class 'dict'> in pending sends
================================== Ai Message ==================================
Tool Calls:
  get_weather (call_JQR9gMUJPiZEZ1HgkJsUYIYA)
 Call ID: call_JQR9gMUJPiZEZ1HgkJsUYIYA
  Args:
    location: San Francisco

Fantastic! Our graph updated properly to query the weather in San Francisco and got the correct “It’s always sunny in sf” response from the tool, and then responded to the user accordingly.

Contents