Agent react cannot accept gpt4 or gpt 4o as input model

[HelloWorldLTY]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

The mimial reproduce code is:

from langchain import hub
from langchain.agents import AgentExecutor, create_react_agent
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_openai import OpenAI

tools = []

# Get the prompt to use - you can modify this!
prompt = hub.pull("hwchase17/react")

# Choose the LLM to use
llm = ChatOpenAI(temperature=0, model="gpt-4o")

# Construct the ReAct agent
agent = create_react_agent(llm, tools, prompt)



# Create an agent executor by passing in the agent and tools
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

agent_executor.invoke({"input": "what is LangChain?"})

Error Message and Stack Trace (if applicable)

ile /home/tl688/.conda/envs/cell2sentence/lib/python3.10/site-packages/langchain/agents/output_parsers/react_single_input.py:75, in ReActSingleInputOutputParser.parse(self, text)
74 if not re.search(r"Action\s*\d*\s*:[\s](.?)", text, re.DOTALL):
---> 75 raise OutputParserException(
76 f"Could not parse LLM output: {text}",
77 observation=MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
78 llm_output=text,
79 send_to_llm=True,
80 )
81 elif not re.search(
82 r"[\s]Action\s\d*\sInput\s\d*\s*:[\s](.)", text, re.DOTALL
83 ):

OutputParserException: Could not parse LLM output: LangChain is a framework designed to facilitate the development of applications powered by language models. It provides a suite of tools and components that help developers build applications that can interact with language models in a structured and efficient manner. LangChain is particularly useful for creating applications that require complex language processing tasks, such as chatbots, virtual assistants, and other AI-driven communication tools. It supports integration with various language models and offers features for managing conversations, handling inputs and outputs, and maintaining context across interactions.
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/OUTPUT_PARSING_FAILURE

Description

This error only happended in gpt4 and gpt4o model, not in 3.5. Replacing it with OpenAI can work.

System Info

The updated version of langchain.

[keenborder786]

@HelloWorldLTY, which version of langchain are you using. Can you uprade to the latest version. Since I tested the same code and everything seems to be working.

[keenborder786]

But @HelloWorldLTY if you are facing this error then do the following:

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

Making handle_parsing_errors=True will make sure that agent executor takes care of any parsing error by feeding the parsing error back to llm.

[HelloWorldLTY]

Hi, I have tried handle_parsing_errors=True but it will repeat error information for me. I think I have updated my longchain. Here is my info:

kiwisolver==1.4.7
langchain==0.3.7
langchain-anthropic==0.3.0
langchain-community==0.3.5
langchain-core==0.3.24
langchain-experimental==0.3.3
langchain-huggingface==0.1.2
langchain-ollama==0.2.0
langchain-openai==0.2.5
langchain-text-splitters==0.3.2
langgraph==0.2.44
langgraph-checkpoint==2.0.2
langgraph-sdk==0.1.35
langsmith==0.1.139

[HelloWorldLTY]

Hi, does it mean I can try reactgpt4 or gpt4o with the referred comments? Thanks.