crewAI: [BUG] After upgrading to latest version of crewAI the code doesn't work anymore.

Description

I’m using Colab to test crewAI and after upgrading to 0.60.0 using the following code:

!pip install 'crewai[tools]'==0.60.0

The following code does not work anymore:

import os
from crewai import Agent, Task, Crew, Process
# from crewai_tools import SerperDevTool

os.environ["OPENAI_API_KEY"] = "xxxxxxxxxxxxxxxxx"
os.environ["OPENAI_API_BASE"] = 'https://api.sambanova.ai/v1/'
os.environ["OPENAI_MODEL_NAME"] = 'Meta-Llama-3.1-8B-Instruct'

researcher = Agent(
  role='Senior Research Analyst',
  goal='Uncover cutting-edge developments in AI and data science',
  backstory="""You work at a leading tech think tank.
  Your expertise lies in identifying emerging trends.
  You have a knack for dissecting complex data and presenting actionable insights.""",
  verbose=True,
  allow_delegation=False,
)

writer = Agent(
  role='Tech Content Strategist',
  goal='Craft compelling content on tech advancements',
  backstory="""You are a renowned Content Strategist, known for your insightful and engaging articles.
  You transform complex concepts into compelling narratives.""",
  verbose=True,
  allow_delegation=True
)

task1 = Task(
  description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
  Identify key trends, breakthrough technologies, and potential industry impacts.""",
  expected_output="Full analysis report in bullet points",
  agent=researcher
)

task2 = Task(
  description="""Using the insights provided, develop an engaging blog
  post that highlights the most significant AI advancements.
  Your post should be informative yet accessible, catering to a tech-savvy audience.
  Make it sound cool, avoid complex words so it doesn't sound like AI.""",
  expected_output="Full blog post of at least 4 paragraphs",
  agent=writer
)

crew = Crew(
  agents=[researcher, writer],
  tasks=[task1, task2],
  verbose=True,
  process = Process.sequential
)

result = crew.kickoff()

print("######################")
print(result)

The code was working perfectly fine before upgrading to this version (tonight).

Steps to Reproduce

N/A

Expected behavior

N/A

Screenshots/Code snippets

BadRequestError: litellm.BadRequestError: OpenAIException - Unknown model: gpt-4o

Operating System

Other (specify in additional context)

Python Version

3.10

crewAI Version

0.60.0

crewAI Tools Version

0.60.0

Virtual Environment

Venv

Evidence

I’m encountering the following error:

# Agent: Senior Research Analyst
## Task: Conduct a comprehensive analysis of the latest advancements in AI in 2024.
  Identify key trends, breakthrough technologies, and potential industry impacts.

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

# Agent: Senior Research Analyst
## Task: Conduct a comprehensive analysis of the latest advancements in AI in 2024.
  Identify key trends, breakthrough technologies, and potential industry impacts.

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

# Agent: Senior Research Analyst
## Task: Conduct a comprehensive analysis of the latest advancements in AI in 2024.
  Identify key trends, breakthrough technologies, and potential industry impacts.

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

---------------------------------------------------------------------------
BadRequestError                           Traceback (most recent call last)
[/usr/local/lib/python3.10/dist-packages/litellm/llms/OpenAI/openai.py](https://localhost:8080/#) in completion(self, model_response, timeout, optional_params, logging_obj, model, messages, print_verbose, api_key, api_base, acompletion, litellm_params, logger_fn, headers, custom_prompt_dict, client, organization, custom_llm_provider, drop_params)
    906                     else:
--> 907                         raise e
    908         except OpenAIError as e:

43 frames
[/usr/local/lib/python3.10/dist-packages/litellm/llms/OpenAI/openai.py](https://localhost:8080/#) in completion(self, model_response, timeout, optional_params, logging_obj, model, messages, print_verbose, api_key, api_base, acompletion, litellm_params, logger_fn, headers, custom_prompt_dict, client, organization, custom_llm_provider, drop_params)
    824                         headers, response = (
--> 825                             self.make_sync_openai_chat_completion_request(
    826                                 openai_client=openai_client,

[/usr/local/lib/python3.10/dist-packages/litellm/llms/OpenAI/openai.py](https://localhost:8080/#) in make_sync_openai_chat_completion_request(self, openai_client, data, timeout)
    682         except Exception as e:
--> 683             raise e
    684 

[/usr/local/lib/python3.10/dist-packages/litellm/llms/OpenAI/openai.py](https://localhost:8080/#) in make_sync_openai_chat_completion_request(self, openai_client, data, timeout)
    671         try:
--> 672             raw_response = openai_client.chat.completions.with_raw_response.create(
    673                 **data, timeout=timeout

[/usr/local/lib/python3.10/dist-packages/openai/_legacy_response.py](https://localhost:8080/#) in wrapped(*args, **kwargs)
    349 
--> 350         return cast(LegacyAPIResponse[R], func(*args, **kwargs))
    351 

[/usr/local/lib/python3.10/dist-packages/openai/_utils/_utils.py](https://localhost:8080/#) in wrapper(*args, **kwargs)
    273                 raise TypeError(msg)
--> 274             return func(*args, **kwargs)
    275 

[/usr/local/lib/python3.10/dist-packages/openai/resources/chat/completions.py](https://localhost:8080/#) in create(self, messages, model, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, n, parallel_tool_calls, presence_penalty, response_format, seed, service_tier, stop, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)
    703         validate_response_format(response_format)
--> 704         return self._post(
    705             "/chat/completions",

[/usr/local/lib/python3.10/dist-packages/openai/_base_client.py](https://localhost:8080/#) in post(self, path, cast_to, body, options, files, stream, stream_cls)
   1259         )
-> 1260         return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
   1261 

[/usr/local/lib/python3.10/dist-packages/openai/_base_client.py](https://localhost:8080/#) in request(self, cast_to, options, remaining_retries, stream, stream_cls)
    936     ) -> ResponseT | _StreamT:
--> 937         return self._request(
    938             cast_to=cast_to,

[/usr/local/lib/python3.10/dist-packages/openai/_base_client.py](https://localhost:8080/#) in _request(self, cast_to, options, remaining_retries, stream, stream_cls)
   1040             log.debug("Re-raising status error")
-> 1041             raise self._make_status_error_from_response(err.response) from None
   1042 

BadRequestError: Unknown model: gpt-4o

During handling of the above exception, another exception occurred:

OpenAIError                               Traceback (most recent call last)
[/usr/local/lib/python3.10/dist-packages/litellm/main.py](https://localhost:8080/#) in completion(model, messages, timeout, temperature, top_p, n, stream, stream_options, stop, max_completion_tokens, max_tokens, presence_penalty, frequency_penalty, logit_bias, user, response_format, seed, tools, tool_choice, logprobs, top_logprobs, parallel_tool_calls, deployment_id, extra_headers, functions, function_call, base_url, api_version, api_key, model_list, **kwargs)
   1395                 )
-> 1396                 raise e
   1397 

[/usr/local/lib/python3.10/dist-packages/litellm/main.py](https://localhost:8080/#) in completion(model, messages, timeout, temperature, top_p, n, stream, stream_options, stop, max_completion_tokens, max_tokens, presence_penalty, frequency_penalty, logit_bias, user, response_format, seed, tools, tool_choice, logprobs, top_logprobs, parallel_tool_calls, deployment_id, extra_headers, functions, function_call, base_url, api_version, api_key, model_list, **kwargs)
   1368             try:
-> 1369                 response = openai_chat_completions.completion(
   1370                     model=model,

[/usr/local/lib/python3.10/dist-packages/litellm/llms/OpenAI/openai.py](https://localhost:8080/#) in completion(self, model_response, timeout, optional_params, logging_obj, model, messages, print_verbose, api_key, api_base, acompletion, litellm_params, logger_fn, headers, custom_prompt_dict, client, organization, custom_llm_provider, drop_params)
    913             error_text = getattr(e, "text", str(e))
--> 914             raise OpenAIError(
    915                 status_code=status_code, message=error_text, headers=error_headers

OpenAIError: Unknown model: gpt-4o

During handling of the above exception, another exception occurred:

BadRequestError                           Traceback (most recent call last)
[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in wrapper(*args, **kwargs)
    979             # MODEL CALL
--> 980             result = original_function(*args, **kwargs)
    981             end_time = datetime.datetime.now()

[/usr/local/lib/python3.10/dist-packages/litellm/main.py](https://localhost:8080/#) in completion(model, messages, timeout, temperature, top_p, n, stream, stream_options, stop, max_completion_tokens, max_tokens, presence_penalty, frequency_penalty, logit_bias, user, response_format, seed, tools, tool_choice, logprobs, top_logprobs, parallel_tool_calls, deployment_id, extra_headers, functions, function_call, base_url, api_version, api_key, model_list, **kwargs)
   2823         ## Map to OpenAI Exception
-> 2824         raise exception_type(
   2825             model=model,

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in exception_type(model, original_exception, custom_llm_provider, completion_kwargs, extra_kwargs)
   8195             setattr(e, "litellm_response_headers", litellm_response_headers)
-> 8196             raise e
   8197         else:

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in exception_type(model, original_exception, custom_llm_provider, completion_kwargs, extra_kwargs)
   6521                         exception_mapping_worked = True
-> 6522                         raise BadRequestError(
   6523                             message=f"{exception_provider} - {message}",

BadRequestError: litellm.BadRequestError: OpenAIException - Unknown model: gpt-4o

During handling of the above exception, another exception occurred:

BadRequestError                           Traceback (most recent call last)
[<ipython-input-2-cebbbee08ec0>](https://localhost:8080/#) in <cell line: 76>()
     74 
     75 # Get your crew to work!
---> 76 result = crew.kickoff()
     77 
     78 print("######################")

[/usr/local/lib/python3.10/dist-packages/crewai/crew.py](https://localhost:8080/#) in kickoff(self, inputs)
    464 
    465         if self.process == Process.sequential:
--> 466             result = self._run_sequential_process()
    467         elif self.process == Process.hierarchical:
    468             result = self._run_hierarchical_process()

[/usr/local/lib/python3.10/dist-packages/crewai/crew.py](https://localhost:8080/#) in _run_sequential_process(self)
    572     def _run_sequential_process(self) -> CrewOutput:
    573         """Executes tasks sequentially and returns the final output."""
--> 574         return self._execute_tasks(self.tasks)
    575 
    576     def _run_hierarchical_process(self) -> CrewOutput:

[/usr/local/lib/python3.10/dist-packages/crewai/crew.py](https://localhost:8080/#) in _execute_tasks(self, tasks, start_index, was_replayed)
    669 
    670                 context = self._get_context(task, task_outputs)
--> 671                 task_output = task.execute_sync(
    672                     agent=agent_to_use,
    673                     context=context,

[/usr/local/lib/python3.10/dist-packages/crewai/task.py](https://localhost:8080/#) in execute_sync(self, agent, context, tools)
    189     ) -> TaskOutput:
    190         """Execute the task synchronously."""
--> 191         return self._execute_core(agent, context, tools)
    192 
    193     @property

[/usr/local/lib/python3.10/dist-packages/crewai/task.py](https://localhost:8080/#) in _execute_core(self, agent, context, tools)
    245         self.processed_by_agents.add(agent.role)
    246 
--> 247         result = agent.execute_task(
    248             task=self,
    249             context=context,

[/usr/local/lib/python3.10/dist-packages/crewai/agent.py](https://localhost:8080/#) in execute_task(self, task, context, tools)
    192             if self._times_executed > self.max_retry_limit:
    193                 raise e
--> 194             result = self.execute_task(task, context, tools)
    195 
    196         if self.max_rpm and self._rpm_controller:

[/usr/local/lib/python3.10/dist-packages/crewai/agent.py](https://localhost:8080/#) in execute_task(self, task, context, tools)
    192             if self._times_executed > self.max_retry_limit:
    193                 raise e
--> 194             result = self.execute_task(task, context, tools)
    195 
    196         if self.max_rpm and self._rpm_controller:

[/usr/local/lib/python3.10/dist-packages/crewai/agent.py](https://localhost:8080/#) in execute_task(self, task, context, tools)
    191             self._times_executed += 1
    192             if self._times_executed > self.max_retry_limit:
--> 193                 raise e
    194             result = self.execute_task(task, context, tools)
    195 

[/usr/local/lib/python3.10/dist-packages/crewai/agent.py](https://localhost:8080/#) in execute_task(self, task, context, tools)
    180 
    181         try:
--> 182             result = self.agent_executor.invoke(
    183                 {
    184                     "input": task_prompt,

[/usr/local/lib/python3.10/dist-packages/crewai/agents/crew_agent_executor.py](https://localhost:8080/#) in invoke(self, inputs)
     87 
     88         self.ask_for_human_input = bool(inputs.get("ask_for_human_input", False))
---> 89         formatted_answer = self._invoke_loop()
     90 
     91         if self.ask_for_human_input:

[/usr/local/lib/python3.10/dist-packages/crewai/agents/crew_agent_executor.py](https://localhost:8080/#) in _invoke_loop(self, formatted_answer)
    160                 return self._invoke_loop(formatted_answer)
    161             else:
--> 162                 raise e
    163 
    164         self._show_logs(formatted_answer)

[/usr/local/lib/python3.10/dist-packages/crewai/agents/crew_agent_executor.py](https://localhost:8080/#) in _invoke_loop(self, formatted_answer)
    109                         stop=self.stop if self.use_stop_words else None,
    110                         callbacks=self.callbacks,
--> 111                     ).call(self.messages)
    112 
    113                     if not self.use_stop_words:

[/usr/local/lib/python3.10/dist-packages/crewai/llm.py](https://localhost:8080/#) in call(self, messages)
     11 
     12     def call(self, messages: List[Dict[str, str]]) -> Dict[str, Any]:
---> 13         response = completion(
     14             stop=self.stop, model=self.model, messages=messages, num_retries=5
     15         )

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in wrapper(*args, **kwargs)
   1065                     ):
   1066                         kwargs["num_retries"] = num_retries
-> 1067                         return litellm.completion_with_retries(*args, **kwargs)
   1068                 elif (
   1069                     isinstance(e, litellm.exceptions.ContextWindowExceededError)

[/usr/local/lib/python3.10/dist-packages/litellm/main.py](https://localhost:8080/#) in completion_with_retries(*args, **kwargs)
   2855             reraise=True,
   2856         )
-> 2857     return retryer(original_function, *args, **kwargs)
   2858 
   2859 

[/usr/local/lib/python3.10/dist-packages/tenacity/__init__.py](https://localhost:8080/#) in __call__(self, fn, *args, **kwargs)
    473         retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs)
    474         while True:
--> 475             do = self.iter(retry_state=retry_state)
    476             if isinstance(do, DoAttempt):
    477                 try:

[/usr/local/lib/python3.10/dist-packages/tenacity/__init__.py](https://localhost:8080/#) in iter(self, retry_state)
    374         result = None
    375         for action in self.iter_state.actions:
--> 376             result = action(retry_state)
    377         return result
    378 

[/usr/local/lib/python3.10/dist-packages/tenacity/__init__.py](https://localhost:8080/#) in exc_check(rs)
    416                 retry_exc = self.retry_error_cls(fut)
    417                 if self.reraise:
--> 418                     raise retry_exc.reraise()
    419                 raise retry_exc from fut.exception()
    420 

[/usr/local/lib/python3.10/dist-packages/tenacity/__init__.py](https://localhost:8080/#) in reraise(self)
    183     def reraise(self) -> t.NoReturn:
    184         if self.last_attempt.failed:
--> 185             raise self.last_attempt.result()
    186         raise self
    187 

[/usr/lib/python3.10/concurrent/futures/_base.py](https://localhost:8080/#) in result(self, timeout)
    449                     raise CancelledError()
    450                 elif self._state == FINISHED:
--> 451                     return self.__get_result()
    452 
    453                 self._condition.wait(timeout)

[/usr/lib/python3.10/concurrent/futures/_base.py](https://localhost:8080/#) in __get_result(self)
    401         if self._exception:
    402             try:
--> 403                 raise self._exception
    404             finally:
    405                 # Break a reference cycle with the exception in self._exception

[/usr/local/lib/python3.10/dist-packages/tenacity/__init__.py](https://localhost:8080/#) in __call__(self, fn, *args, **kwargs)
    476             if isinstance(do, DoAttempt):
    477                 try:
--> 478                     result = fn(*args, **kwargs)
    479                 except BaseException:  # noqa: B902
    480                     retry_state.set_exception(sys.exc_info())  # type: ignore[arg-type]

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in wrapper(*args, **kwargs)
   1090                     ):  # make it easy to get to the debugger logs if you've initialized it
   1091                         e.message += f"\n Check the log in your dashboard - {liteDebuggerClient.dashboard_url}"
-> 1092             raise e
   1093 
   1094     @wraps(original_function)

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in wrapper(*args, **kwargs)
    978                     print_verbose(f"Error while checking max token limit: {str(e)}")
    979             # MODEL CALL
--> 980             result = original_function(*args, **kwargs)
    981             end_time = datetime.datetime.now()
    982             if "stream" in kwargs and kwargs["stream"] is True:

[/usr/local/lib/python3.10/dist-packages/litellm/main.py](https://localhost:8080/#) in completion(model, messages, timeout, temperature, top_p, n, stream, stream_options, stop, max_completion_tokens, max_tokens, presence_penalty, frequency_penalty, logit_bias, user, response_format, seed, tools, tool_choice, logprobs, top_logprobs, parallel_tool_calls, deployment_id, extra_headers, functions, function_call, base_url, api_version, api_key, model_list, **kwargs)
   2822     except Exception as e:
   2823         ## Map to OpenAI Exception
-> 2824         raise exception_type(
   2825             model=model,
   2826             custom_llm_provider=custom_llm_provider,

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in exception_type(model, original_exception, custom_llm_provider, completion_kwargs, extra_kwargs)
   8194         if exception_mapping_worked:
   8195             setattr(e, "litellm_response_headers", litellm_response_headers)
-> 8196             raise e
   8197         else:
   8198             for error_type in litellm.LITELLM_EXCEPTION_TYPES:

[/usr/local/lib/python3.10/dist-packages/litellm/utils.py](https://localhost:8080/#) in exception_type(model, original_exception, custom_llm_provider, completion_kwargs, extra_kwargs)
   6520                     if original_exception.status_code == 400:
   6521                         exception_mapping_worked = True
-> 6522                         raise BadRequestError(
   6523                             message=f"{exception_provider} - {message}",
   6524                             llm_provider=custom_llm_provider,

BadRequestError: litellm.BadRequestError: OpenAIException - Unknown model: gpt-4o

Possible Solution

Downgrade to the previous version.

Additional context

N/A

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Comments: 19 (2 by maintainers)

Most upvoted comments

@olafgeibig This is a good suggestion, we can still add support to LangChain Model definition without need to bring back their executor now, so this is good, I’m already working on it.

Hey @Kingbadger3d appreciate the messages, I’m sorry you are experiment so much pain from the upgrade. If you want, it might be easier to hold on upgrading while we bring more providers including langchain for model connections. We needed to remove this because langchain was slowing down our ability to add some major new features and would break on some of their updates.

new version is out v0.63.1 env vars should work again, also ability to control all different attribute for the LLM using the LLM class, if this is still an issue let us know and we can re-open it 😃

@TarcisioAmaral your problem seems to be unrelated, but looking at the error message, it indicates a problem with character encoding when trying to read a YAML file.

In an attempt to fix it I push a change to master that forcer the utf-8 encoding and it will be live in the next version, it should help with it.

But I also recommend checking the YAML file for any unusual or non-printable characters. You might need to remove or replace problematic characters.