'Agent' getting error when using 'bind' with Langchain's Chat Model using Hierarchical Process

[alvarod91100]

Trying to use the hierarchical process with a crew while using Langchain's implementation of OpenAI Chat (langchain_openai.ChatOpenAI) but keep encountering the following error:

  File ".../.../.../lib/python3.12/site-packages/crewai/agent.py", line 131, in __init__
    super().__init__(**config, **data)
  File ".../.../.../lib/python3.12/site-packages/pydantic/main.py", line 171, in __init__
    self.__pydantic_validator__.validate_python(data, self_instance=self)
  File ".../.../.../lib/python3.12/site-packages/crewai/agent.py", line 172, in set_agent_executor
    self.set_cache_handler(self.cache_handler)
  File ".../.../.../lib/python3.12/site-packages/crewai/agent.py", line 244, in set_cache_handler
    self.create_agent_executor()
  File ".../.../.../lib/python3.12/site-packages/crewai/agent.py", line 303, in create_agent_executor
    bind = self.llm.bind(stop=[self.i18n.slice("observation")])
           ^^^^^^^^^^^^^
  File ".../.../.../lib/python3.12/site-packages/pydantic/main.py", line 767, in __getattr__
    raise AttributeError(f'{type(self).__name__!r} object has no attribute {item!r}')
AttributeError: 'Agent' object has no attribute 'bind'

Double-checked and ChatOpenAI does have attribute defined, as mentioned in langchain's documentation and manually checking the library's code locally.

Code used is the following:

from crewai import Agent, Task, Crew, Process
from langchain_openai import ChatOpenAI

connectionLLM = ChatOpenAI(
    api_key="------"
)

manager = Agent(
    role='Project Manager',
    goal='Coordinate the project to ensure a seamless integration of research findings into compelling narratives',
    verbose=True,
    backstory="""With a strategic mindset and a knack for leadership, you excel at guiding teams towards
    their goals, ensuring projects not only meet but exceed expectations.""",
    allow_delegation=True,
    llm = connectionLLM
)

researcher = Agent(
    role='Senior Researcher',
    goal=f'Uncover groundbreaking technologies around {topic}',
    verbose=True,
    backstory="""Driven by curiosity, you're at the forefront of innovation, eager to explore and share
    knowledge that could change the world.""", 
    llm = connectionLLM
)

# Define the writer agent
writer = Agent(
    role='Writer',
    goal=f'Narrate compelling tech stories around {topic}',
    verbose=True,
    backstory="""With a flair for simplifying complex topics, you craft engaging narratives that captivate
    and educate, bringing new discoveries to light in an accessible manner.""", 
    llm = connectionLLM
)

list_ideas = Task(
    description="List of 5 interesting ideas to explore for an article about {topic}.",
    expected_output="Bullet point list of 5 ideas for an article.",
    tools=[search_tool],  
    agent=researcher,
    async_execution=True
)

list_important_history = Task(
    description="Research the history of {topic} and identify the 5 most important events.",
    expected_output="Bullet point list of 5 important events.",
    tools=[search_tool],
    agent=researcher,
    async_execution=True
)

write_article = Task(
    description=f"Compose an insightful article on {topic}, including its history and the latest interesting ideas.",
    expected_output="A 4 paragraph article about AI in healthcare.",
    tools=[search_tool],  
    agent=writer,
    context=[list_ideas, list_important_history],  # Depends on the completion of the two asynchronous tasks
)

manager_task = Task(
    description=f"""Oversee the integration of research findings and narrative development to produce a final comprehensive
    report on {topic}. Ensure the research is accurately represented and the narrative is engaging and informative.""",
    expected_output=f'A final comprehensive report that combines the research findings and narrative on {topic}.',
    agent=manager
)

crew = Crew(
    agents=[manager, researcher, writer],
    tasks=[list_ideas, list_important_history, write_article, manager_task],
    process=Process.hierarchical, 
    manager_llm= manager
)

results = crew.kickoff()

error persists in Python version is 3.11.0 and 3.12 with the following langchain and crewai versions:

crewai==0.28.8
langchain==0.1.16      
langchain-community==0.0.34
langchain-core==0.1.45
langchain-experimental==0.0.57
langchain-openai==0.1.3

Using sequential process does not throw the error.