Open lapups opened 2 months ago
I have also started seeing this error a lot. I've been running my crews for several months now and have never seen this until a couple of days ago.
There is an OpenAI forum post that talks about using tools correctly with the API. I wonder if there is some problem with either CrewAI or LangChain in how they are passing tool information to OpenAI.
I will add that this started coming back as an error often during the last 24 hours. Probably 50% of complex runs.
Seeing this same issue as well, using
llm = ChatOpenAI(
model="gpt-4o",
api_key=os.getenv("OPENAI_API_KEY")
)
It seems like gpt-4o is more strict regarding function calling. Could it be how crewai is passing function to the API?
Possibly -- but I've been using gpt4o for several weeks now. The issues just started in the last 24-48hrs. Possible that OpenAI changed something on their end as well
@greg80303 Yeah it's finicky. Just started using crewAI, so I'm new to the way things work. But, from my tests, it seems like I get the above error ~40-50% of the time
Same here!
Same here. I have a feature using langchain react agent (with tools) + gpt-4o. From my LangSmith I started to see this error since ~Jun 23rd.
I have a sequence of 3 seemingly simple agents and 3 seemingly simple tasks with one agent per task. The program seems to randomly fail on different agents in the sequence on different runs with:
openai.APIError: The model produced invalid content. Consider modifying your prompt if you are seeing this error persistently.
Update: I consistently get this error when using the agents with model 'gpt-4o'. However, changing the agent's model to 'gpt-3.5-turbo' all works well. And progresses through the sequence much faster.
Same here.
More observations here - might be related to openai (4o ) failed to extract the correct parameters.
Guys, did anyone find how to solve this issue. I'm unable to proceed without getting this issue resolved. Any help is much appreciated. Thanks in advance!
@Karl60
Update: I consistently get this error when using the agents with model 'gpt-4o'. However, changing the agent's model to 'gpt-3.5-turbo' all works well. And progresses through the sequence much faster.
Same for me. Switching from 'gpt-4o' to 'gpt-3.5-turbo' at least gives a temporary workaround to resolve the issue, but I haven't been able to figure out specifically why 'gpt-4o' isn't working.
Hello, guys. Is there any update on this issue? Because I have also faced the same issue.
I am facing the same issue, have you guys tried gpt-4 or gpt-4o-mini as well-?
I am facing the same issue, have you guys tried gpt-4 or gpt-4o-mini as well-?
Yess
Same issue here too.
One piece of information that may be useful.
I changed the model from gpt-4o
to gpt-4o-mini
and the error no longer occurs.
I am trying to use small summarizer as a tool for my task. But at the > Entering new CrewAgentExecutor chain...
I am getting provided error 8 of 10 times (which is also weird):
Upade using the Claude 3 models as a tool also raises the same error