Skip to main content

How to migrate from legacy LangChain agents to LangGraph

Prerequisites

This guide assumes familiarity with the following concepts:

Here we focus on how to move from legacy LangChain agents to more flexible LangGraph agents. LangChain agents (the AgentExecutor in particular) have multiple configuration parameters. In this notebook we will show how those parameters map to the LangGraph react agent executor using the create_react_agent prebuilt helper method.

note

In LangGraph, the graph replaces LangChain's agent executor. It manages the agent's cycles and tracks the scratchpad as messages within its state. The LangChain "agent" corresponds to the state_modifier and LLM you've provided.

Prerequisites​

This how-to guide uses OpenAI as the LLM. Install the dependencies to run.

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

Then, set your OpenAI API key.

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API key:\n")

Basic Usage​

For basic creation and usage of a tool-calling ReAct-style agent, the functionality is the same. First, let's define a model and tool(s), then we'll use those to create an agent.

from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o")


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2


tools = [magic_function]


query = "what is the value of magic_function(3)?"
API Reference:tool | ChatOpenAI

For the LangChain AgentExecutor, we define a prompt with a placeholder for the agent's scratchpad. The agent can be invoked as follows:

from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant"),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)


agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

agent_executor.invoke({"input": query})
{'input': 'what is the value of magic_function(3)?',
'output': 'The value of `magic_function(3)` is 5.'}

LangGraph's react agent executor manages a state that is defined by a list of messages. It will continue to process the list until there are no tool calls in the agent's output. To kick it off, we input a list of messages. The output will contain the entire state of the graph-- in this case, the conversation history.

from langgraph.prebuilt import create_react_agent

langgraph_agent_executor = create_react_agent(model, tools)


messages = langgraph_agent_executor.invoke({"messages": [("human", query)]})
{
"input": query,
"output": messages["messages"][-1].content,
}
API Reference:create_react_agent
{'input': 'what is the value of magic_function(3)?',
'output': 'The value of `magic_function(3)` is 5.'}
message_history = messages["messages"]

new_query = "Pardon?"

messages = langgraph_agent_executor.invoke(
{"messages": message_history + [("human", new_query)]}
)
{
"input": new_query,
"output": messages["messages"][-1].content,
}
{'input': 'Pardon?',
'output': 'The value returned by `magic_function` when the input is 3 is 5.'}

Prompt Templates​

With legacy LangChain agents you have to pass in a prompt template. You can use this to control the agent.

With LangGraph react agent executor, by default there is no prompt. You can achieve similar control over the agent in a few ways:

  1. Pass in a system message as input
  2. Initialize the agent with a system message
  3. Initialize the agent with a function to transform messages before passing to the model.

Let's take a look at all of these below. We will pass in custom instructions to get the agent to respond in Spanish.

First up, using AgentExecutor:

prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant. Respond only in Spanish."),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)


agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

agent_executor.invoke({"input": query})
{'input': 'what is the value of magic_function(3)?',
'output': 'El valor de `magic_function(3)` es 5.'}

Now, let's pass a custom system message to react agent executor.

LangGraph's prebuilt create_react_agent does not take a prompt template directly as a parameter, but instead takes a state_modifier parameter. This modifies the graph state before the llm is called, and can be one of four values:

  • A SystemMessage, which is added to the beginning of the list of messages.
  • A string, which is converted to a SystemMessage and added to the beginning of the list of messages.
  • A Callable, which should take in full graph state. The output is then passed to the language model.
  • Or a Runnable, which should take in full graph state. The output is then passed to the language model.

Here's how it looks in action:

from langchain_core.messages import SystemMessage
from langgraph.prebuilt import create_react_agent

system_message = "You are a helpful assistant. Respond only in Spanish."
# This could also be a SystemMessage object
# system_message = SystemMessage(content="You are a helpful assistant. Respond only in Spanish.")

langgraph_agent_executor = create_react_agent(
model, tools, state_modifier=system_message
)


messages = langgraph_agent_executor.invoke({"messages": [("user", query)]})

We can also pass in an arbitrary function. This function should take in a list of messages and output a list of messages. We can do all types of arbitrary formatting of messages here. In this cases, let's just add a SystemMessage to the start of the list of messages.

from langgraph.prebuilt import create_react_agent
from langgraph.prebuilt.chat_agent_executor import AgentState

prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant. Respond only in Spanish."),
("placeholder", "{messages}"),
]
)


def _modify_state_messages(state: AgentState):
return prompt.invoke({"messages": state["messages"]}).to_messages() + [
("user", "Also say 'Pandamonium!' after the answer.")
]


langgraph_agent_executor = create_react_agent(
model, tools, state_modifier=_modify_state_messages
)


messages = langgraph_agent_executor.invoke({"messages": [("human", query)]})
print(
{
"input": query,
"output": messages["messages"][-1].content,
}
)
API Reference:create_react_agent
{'input': 'what is the value of magic_function(3)?', 'output': 'The value of magic_function(3) is 5. Β‘Pandamonium!'}

Memory​

In LangChain​

With LangChain's AgentExecutor, you could add chat Memory so it can engage in a multi-turn conversation.

from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.chat_history import InMemoryChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o")
memory = InMemoryChatMessageHistory(session_id="test-session")
prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant."),
# First put the history
("placeholder", "{chat_history}"),
# Then the new input
("human", "{input}"),
# Finally the scratchpad
("placeholder", "{agent_scratchpad}"),
]
)


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2


tools = [magic_function]


agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

agent_with_chat_history = RunnableWithMessageHistory(
agent_executor,
# This is needed because in most real world scenarios, a session id is needed
# It isn't really used here because we are using a simple in memory ChatMessageHistory
lambda session_id: memory,
input_messages_key="input",
history_messages_key="chat_history",
)

config = {"configurable": {"session_id": "test-session"}}
print(
agent_with_chat_history.invoke(
{"input": "Hi, I'm polly! What's the output of magic_function of 3?"}, config
)["output"]
)
print("---")
print(agent_with_chat_history.invoke({"input": "Remember my name?"}, config)["output"])
print("---")
print(
agent_with_chat_history.invoke({"input": "what was that output again?"}, config)[
"output"
]
)
Hi Polly! The output of applying the magic function to the input 3 is 5.
---
Yes, you mentioned your name is Polly.
---
The output of applying the magic function to the input 3 is 5.

In LangGraph​

Memory is just persistence, aka checkpointing.

Add a checkpointer to the agent and you get chat memory for free.

from langgraph.checkpoint.memory import MemorySaver  # an in-memory checkpointer
from langgraph.prebuilt import create_react_agent

system_message = "You are a helpful assistant."
# This could also be a SystemMessage object
# system_message = SystemMessage(content="You are a helpful assistant. Respond only in Spanish.")

memory = MemorySaver()
langgraph_agent_executor = create_react_agent(
model, tools, state_modifier=system_message, checkpointer=memory
)

config = {"configurable": {"thread_id": "test-thread"}}
print(
langgraph_agent_executor.invoke(
{
"messages": [
("user", "Hi, I'm polly! What's the output of magic_function of 3?")
]
},
config,
)["messages"][-1].content
)
print("---")
print(
langgraph_agent_executor.invoke(
{"messages": [("user", "Remember my name?")]}, config
)["messages"][-1].content
)
print("---")
print(
langgraph_agent_executor.invoke(
{"messages": [("user", "what was that output again?")]}, config
)["messages"][-1].content
)
Hi Polly! The output of applying the magic function to the input 3 is 5.
---
Yes, your name is Polly!
---
The output of applying the magic function to the input 3 was 5.

Iterating through steps​

In LangChain​

With LangChain's AgentExecutor, you could iterate over the steps using the stream (or async astream) methods or the iter method. LangGraph supports stepwise iteration using stream

from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o")


prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant."),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2


tools = [magic_function]

agent = create_tool_calling_agent(model, tools, prompt=prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

for step in agent_executor.stream({"input": query}):
print(step)
{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log="\nInvoking: `magic_function` with `{'input': 3}`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c9aa9c0491'}, id='run-dc7ce17d-02fd-4fdb-be82-7c902410b6b7', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{"input":3}', 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_gNzQT96XWoyZqVl1jI1yMnjy')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c9aa9c0491'}, id='run-dc7ce17d-02fd-4fdb-be82-7c902410b6b7', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{"input":3}', 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'index': 0, 'type': 'tool_call_chunk'}])]}
{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log="\nInvoking: `magic_function` with `{'input': 3}`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c9aa9c0491'}, id='run-dc7ce17d-02fd-4fdb-be82-7c902410b6b7', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{"input":3}', 'id': 'call_gNzQT96XWoyZqVl1jI1yMnjy', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_gNzQT96XWoyZqVl1jI1yMnjy'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}
{'output': 'The value of `magic_function(3)` is 5.', 'messages': [AIMessage(content='The value of `magic_function(3)` is 5.')]}

In LangGraph​

In LangGraph, things are handled natively using stream or the asynchronous astream method.

from langgraph.prebuilt import create_react_agent
from langgraph.prebuilt.chat_agent_executor import AgentState

prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant."),
("placeholder", "{messages}"),
]
)


def _modify_state_messages(state: AgentState):
return prompt.invoke({"messages": state["messages"]}).to_messages()


langgraph_agent_executor = create_react_agent(
model, tools, state_modifier=_modify_state_messages
)

for step in langgraph_agent_executor.stream(
{"messages": [("human", query)]}, stream_mode="updates"
):
print(step)
API Reference:create_react_agent
{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_I0nztlIcc0e9ry5dn53YLZUM', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 61, 'total_tokens': 75}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-5f9bd87d-3692-4d13-8d27-1859e13e2156-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_I0nztlIcc0e9ry5dn53YLZUM', 'type': 'tool_call'}], usage_metadata={'input_tokens': 61, 'output_tokens': 14, 'total_tokens': 75})]}}
{'tools': {'messages': [ToolMessage(content='5', name='magic_function', tool_call_id='call_I0nztlIcc0e9ry5dn53YLZUM')]}}
{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 84, 'total_tokens': 98}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'stop', 'logprobs': None}, id='run-f6015ca6-93e5-45e8-8b28-b3f0a8d203dc-0', usage_metadata={'input_tokens': 84, 'output_tokens': 14, 'total_tokens': 98})]}}

return_intermediate_steps​

In LangChain​

Setting this parameter on AgentExecutor allows users to access intermediate_steps, which pairs agent actions (e.g., tool invocations) with their outcomes.

agent_executor = AgentExecutor(agent=agent, tools=tools, return_intermediate_steps=True)
result = agent_executor.invoke({"input": query})
print(result["intermediate_steps"])
[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log="\nInvoking: `magic_function` with `{'input': 3}`\n\n\n", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_wjaAyTjI2LSYOq7C8QZYSxEs', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c9aa9c0491'}, id='run-99e06b70-1ef6-4761-834b-87b6c5252e20', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_wjaAyTjI2LSYOq7C8QZYSxEs', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{"input":3}', 'id': 'call_wjaAyTjI2LSYOq7C8QZYSxEs', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_wjaAyTjI2LSYOq7C8QZYSxEs'), 5)]

In LangGraph​

By default the react agent executor in LangGraph appends all messages to the central state. Therefore, it is easy to see any intermediate steps by just looking at the full state.

from langgraph.prebuilt import create_react_agent

langgraph_agent_executor = create_react_agent(model, tools=tools)

messages = langgraph_agent_executor.invoke({"messages": [("human", query)]})

messages
API Reference:create_react_agent
{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='2d369331-8052-4167-bd85-9f6d8ad021ae'),
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_oXiSQSe6WeWj7XIKXxZrO2IC', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-297e7fc9-726f-46a0-8c67-dc28ed1724d0-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_oXiSQSe6WeWj7XIKXxZrO2IC', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}),
ToolMessage(content='5', name='magic_function', id='46370faf-9598-423c-b94b-aca8cb4f035d', tool_call_id='call_oXiSQSe6WeWj7XIKXxZrO2IC'),
AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 78, 'total_tokens': 92}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'stop', 'logprobs': None}, id='run-f48efaff-0c2c-4632-bbf9-7ee626f73d02-0', usage_metadata={'input_tokens': 78, 'output_tokens': 14, 'total_tokens': 92})]}

max_iterations​

In LangChain​

AgentExecutor implements a max_iterations parameter, allowing users to abort a run that exceeds a specified number of iterations.

@tool
def magic_function(input: str) -> str:
"""Applies a magic function to an input."""
return "Sorry, there was an error. Please try again."


tools = [magic_function]
prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant. Respond only in Spanish."),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)

agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(
agent=agent,
tools=tools,
verbose=True,
max_iterations=3,
)

agent_executor.invoke({"input": query})


> Entering new AgentExecutor chain...

Invoking: `magic_function` with `{'input': '3'}`


Sorry, there was an error. Please try again.Hubo un error al intentar obtener el valor de `magic_function(3)`. ΒΏPodrΓ­as intentarlo de nuevo o proporcionar mΓ‘s detalles?

> Finished chain.
{'input': 'what is the value of magic_function(3)?',
'output': 'Hubo un error al intentar obtener el valor de `magic_function(3)`. ΒΏPodrΓ­as intentarlo de nuevo o proporcionar mΓ‘s detalles?'}

In LangGraph​

In LangGraph this is controlled via recursion_limit configuration parameter.

Note that in AgentExecutor, an "iteration" includes a full turn of tool invocation and execution. In LangGraph, each step contributes to the recursion limit, so we will need to multiply by two (and add one) to get equivalent results.

If the recursion limit is reached, LangGraph raises a specific exception type, that we can catch and manage similarly to AgentExecutor.

from langgraph.errors import GraphRecursionError
from langgraph.prebuilt import create_react_agent

RECURSION_LIMIT = 2 * 3 + 1

langgraph_agent_executor = create_react_agent(model, tools=tools)

try:
for chunk in langgraph_agent_executor.stream(
{"messages": [("human", query)]},
{"recursion_limit": RECURSION_LIMIT},
stream_mode="values",
):
print(chunk["messages"][-1])
except GraphRecursionError:
print({"input": query, "output": "Agent stopped due to max iterations."})
API Reference:create_react_agent
content='what is the value of magic_function(3)?' id='fe74bb30-45b8-4a40-a5ed-fd6678da5428'
content='' additional_kwargs={'tool_calls': [{'id': 'call_TNKfNy6fgZNdJAvHUMXwtp8f', 'function': {'arguments': '{"input":"3"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-dad8bfc1-477c-40d2-9016-243d25c0dd13-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_TNKfNy6fgZNdJAvHUMXwtp8f', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}
content='Sorry, there was an error. Please try again.' name='magic_function' id='653226e0-3187-40be-a774-4c7c2612239e' tool_call_id='call_TNKfNy6fgZNdJAvHUMXwtp8f'
content='It looks like there was an issue with processing the request. Let me try that again.' additional_kwargs={'tool_calls': [{'id': 'call_K0wJ8fQLYGv8fYXY1Uo5U5sG', 'function': {'arguments': '{"input":"3"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 33, 'prompt_tokens': 88, 'total_tokens': 121}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-d4c85437-6625-4e57-81f9-86de6842be7b-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_K0wJ8fQLYGv8fYXY1Uo5U5sG', 'type': 'tool_call'}] usage_metadata={'input_tokens': 88, 'output_tokens': 33, 'total_tokens': 121}
content='Sorry, there was an error. Please try again.' name='magic_function' id='9b530d03-95df-401e-bb4f-5cada1195033' tool_call_id='call_K0wJ8fQLYGv8fYXY1Uo5U5sG'
content='It seems that there is a persistent issue with processing the request. Let me attempt it one more time.' additional_kwargs={'tool_calls': [{'id': 'call_7ECwwNBDo4SH56oczErZJVRT', 'function': {'arguments': '{"input":"3"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 36, 'prompt_tokens': 143, 'total_tokens': 179}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-9f3f651e-a641-4112-99ed-d1ac11169582-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_7ECwwNBDo4SH56oczErZJVRT', 'type': 'tool_call'}] usage_metadata={'input_tokens': 143, 'output_tokens': 36, 'total_tokens': 179}
content='Sorry, there was an error. Please try again.' name='magic_function' id='e4cd152b-4eb1-47df-ac76-f88e79adbe19' tool_call_id='call_7ECwwNBDo4SH56oczErZJVRT'
content="It seems there is a consistent issue with processing the request for the magic function. Let's try using a different approach to resolve this." additional_kwargs={'tool_calls': [{'id': 'call_DMAL0UwBRijzuPjCTSwR2r17', 'function': {'arguments': '{"input":"three"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 41, 'prompt_tokens': 201, 'total_tokens': 242}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c9aa9c0491', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-cd9f4e5c-f881-462c-abe3-890e73f46a01-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 'three'}, 'id': 'call_DMAL0UwBRijzuPjCTSwR2r17', 'type': 'tool_call'}] usage_metadata={'input_tokens': 201, 'output_tokens': 41, 'total_tokens': 242}
{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}

max_execution_time​

In LangChain​

AgentExecutor implements a max_execution_time parameter, allowing users to abort a run that exceeds a total time limit.

import time


@tool
def magic_function(input: str) -> str:
"""Applies a magic function to an input."""
time.sleep(2.5)
return "Sorry, there was an error. Please try again."


tools = [magic_function]

agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(
agent=agent,
tools=tools,
max_execution_time=2,
verbose=True,
)

agent_executor.invoke({"input": query})


> Entering new AgentExecutor chain...

Invoking: `magic_function` with `{'input': '3'}`


Sorry, there was an error. Please try again.

> Finished chain.
{'input': 'what is the value of magic_function(3)?',
'output': 'Agent stopped due to max iterations.'}

In LangGraph​

With LangGraph's react agent, you can control timeouts on two levels.

You can set a step_timeout to bound each step:

from langgraph.prebuilt import create_react_agent

langgraph_agent_executor = create_react_agent(model, tools=tools)
# Set the max timeout for each step here
langgraph_agent_executor.step_timeout = 2

try:
for chunk in langgraph_agent_executor.stream({"messages": [("human", query)]}):
print(chunk)
print("------")
except TimeoutError:
print({"input": query, "output": "Agent stopped due to a step timeout."})
API Reference:create_react_agent
{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_o8Ym0u9UfzArhIm1lV7O0CXF', 'function': {'arguments': '{"input":"3"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d9faf125-1ff8-4de2-a75b-97e07d28dc4d-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_o8Ym0u9UfzArhIm1lV7O0CXF', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}
------
{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to a step timeout.'}

The other way to set a single max timeout for an entire run is to directly use the python stdlib asyncio library.

import asyncio

from langgraph.prebuilt import create_react_agent

langgraph_agent_executor = create_react_agent(model, tools=tools)


async def stream(langgraph_agent_executor, inputs):
async for chunk in langgraph_agent_executor.astream(
{"messages": [("human", query)]}
):
print(chunk)
print("------")


try:
task = asyncio.create_task(
stream(langgraph_agent_executor, {"messages": [("human", query)]})
)
await asyncio.wait_for(task, timeout=3)
except TimeoutError:
print("Task Cancelled.")
API Reference:create_react_agent
{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_gsGzyhyvR25iNV6W9VR2TIdQ', 'function': {'arguments': '{"input":"3"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-9ad8f834-06c5-41cf-9eec-6b7e0f5e777e-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_gsGzyhyvR25iNV6W9VR2TIdQ', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}
------
Task Cancelled.

early_stopping_method​

In LangChain​

With LangChain's AgentExecutor, you could configure an early_stopping_method to either return a string saying "Agent stopped due to iteration limit or time limit." ("force") or prompt the LLM a final time to respond ("generate").

from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o")


prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant."),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return "Sorry there was an error, please try again."


tools = [magic_function]

agent = create_tool_calling_agent(model, tools, prompt=prompt)
agent_executor = AgentExecutor(
agent=agent, tools=tools, early_stopping_method="force", max_iterations=1
)

result = agent_executor.invoke({"input": query})
print("Output with early_stopping_method='force':")
print(result["output"])
Output with early_stopping_method='force':
Agent stopped due to max iterations.

In LangGraph​

In LangGraph, you can explicitly handle the response behavior outside the agent, since the full state can be accessed.

from langgraph.errors import GraphRecursionError
from langgraph.prebuilt import create_react_agent

RECURSION_LIMIT = 2 * 1 + 1

langgraph_agent_executor = create_react_agent(model, tools=tools)

try:
for chunk in langgraph_agent_executor.stream(
{"messages": [("human", query)]},
{"recursion_limit": RECURSION_LIMIT},
stream_mode="values",
):
print(chunk["messages"][-1])
except GraphRecursionError:
print({"input": query, "output": "Agent stopped due to max iterations."})
API Reference:create_react_agent
content='what is the value of magic_function(3)?' id='6487a942-0a9a-4e8a-9556-553a45fa9c5a'
content='' additional_kwargs={'tool_calls': [{'id': 'call_pe5KVY5No9iT4JWqrm5MwL1D', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-04147325-fb72-462a-a1d9-6aa4e86e3d8a-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_pe5KVY5No9iT4JWqrm5MwL1D', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}
content='Sorry there was an error, please try again.' name='magic_function' id='bc0bf58f-7c6c-42ed-a96d-a2afa79f16a9' tool_call_id='call_pe5KVY5No9iT4JWqrm5MwL1D'
content="It seems there was an issue with processing the request. I'll try again." additional_kwargs={'tool_calls': [{'id': 'call_5rV7k3g7oW38bD9KUTsSxK8l', 'function': {'arguments': '{"input":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 30, 'prompt_tokens': 87, 'total_tokens': 117}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-6e43ffd4-fb6f-4222-8503-a50ae268c0be-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_5rV7k3g7oW38bD9KUTsSxK8l', 'type': 'tool_call'}] usage_metadata={'input_tokens': 87, 'output_tokens': 30, 'total_tokens': 117}
{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}

trim_intermediate_steps​

In LangChain​

With LangChain's AgentExecutor, you could trim the intermediate steps of long-running agents using trim_intermediate_steps, which is either an integer (indicating the agent should keep the last N steps) or a custom function.

For instance, we could trim the value so the agent only sees the most recent intermediate step.

from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o")


prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant."),
("human", "{input}"),
# Placeholders fill up a **list** of messages
("placeholder", "{agent_scratchpad}"),
]
)


magic_step_num = 1


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
global magic_step_num
print(f"Call number: {magic_step_num}")
magic_step_num += 1
return input + magic_step_num


tools = [magic_function]

agent = create_tool_calling_agent(model, tools, prompt=prompt)


def trim_steps(steps: list):
# Let's give the agent amnesia
return []


agent_executor = AgentExecutor(
agent=agent, tools=tools, trim_intermediate_steps=trim_steps
)


query = "Call the magic function 4 times in sequence with the value 3. You cannot call it multiple times at once."

for step in agent_executor.stream({"input": query}):
pass
Call number: 1
Call number: 2
Call number: 3
Call number: 4
Call number: 5
Call number: 6
Call number: 7
Call number: 8
Call number: 9
Call number: 10
Call number: 11
Call number: 12
Call number: 13
Call number: 14
``````output
Stopping agent prematurely due to triggering stop condition
``````output
Call number: 15

In LangGraph​

We can use the state_modifier just as before when passing in prompt templates.

from langgraph.errors import GraphRecursionError
from langgraph.prebuilt import create_react_agent
from langgraph.prebuilt.chat_agent_executor import AgentState

magic_step_num = 1


@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
global magic_step_num
print(f"Call number: {magic_step_num}")
magic_step_num += 1
return input + magic_step_num


tools = [magic_function]


def _modify_state_messages(state: AgentState):
# Give the agent amnesia, only keeping the original user query
return [("system", "You are a helpful assistant"), state["messages"][0]]


langgraph_agent_executor = create_react_agent(
model, tools, state_modifier=_modify_state_messages
)

try:
for step in langgraph_agent_executor.stream(
{"messages": [("human", query)]}, stream_mode="updates"
):
pass
except GraphRecursionError as e:
print("Stopping agent prematurely due to triggering stop condition")
API Reference:create_react_agent
Call number: 1
Call number: 2
Call number: 3
Call number: 4
Call number: 5
Call number: 6
Call number: 7
Call number: 8
Call number: 9
Call number: 10
Call number: 11
Call number: 12
Stopping agent prematurely due to triggering stop condition

Next steps​

You've now learned how to migrate your LangChain agent executors to LangGraph.

Next, check out other LangGraph how-to guides.


Was this page helpful?


You can also leave detailed feedback on GitHub.