AttributeError: 'str' object has no attribute 'get' after the task is finished

[I4mCh40s]

Hi! First, thank you to all the devs who made autogen, it is so cool!

Unfortunately I have a persistent error (AttributeError: 'str' object has no attribute 'get')

It pops up sometimes before the Assistant is finished (when it writes python code for example), but when the task is primitive ( "come up with 5 possible names for SMMA that helps companies get leads") it manages to get it done and then spits out this error.

`user_proxy (to assistant):

come up with 5 possible names for SMMA that helps companies get leads

---

assistant (to user_proxy):

1. Lead Generation Machine
2. Lead Generator
3. Sales Leads Machine
4. Business Leads Generator
5. Lead Finder

---

Traceback (most recent call last):
File "c:\Users\ihasdslr\Documents\auto_gen\autogen_init.py", line 36, in
user_proxy.initiate_chat(
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 531, in initiate_chat
self.send(self.generate_init_message(**context), recipient, silent=silent)
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 334, in send
recipient.receive(message, self, request_reply, silent)
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 464, in receive
self.send(reply, sender, silent=silent)
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 334, in send
recipient.receive(message, self, request_reply, silent)
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 462, in receive
reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 781, in generate_reply
final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 606, in generate_oai_reply
response = oai.ChatCompletion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 799, in create
response = cls.create(
^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 830, in create
return cls._get_response(params, raise_on_ratelimit_or_timeout=raise_on_ratelimit_or_timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 218, in _get_response
response = openai_completion.create(**config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 155, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 299, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 710, in _interpret_response
self._interpret_response_line(
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 775, in _interpret_response_line
raise self.handle_error_response(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 428, in handle_error_response
error_code=error_data.get("code"),
^^^^^^^^^^^^^^
AttributeError: 'str' object has no attribute 'get'`

I run the server with local LLMs via the LM studio. During this error my server logs say
[ERROR] Error: 'messages' array must only contain objects with a 'content' field that is not empty.

pls help!

[CCMKCCMK]

Ihave the similar issue

[sonichi]

Try setting default_reply of UserProxyAgent to a non-empty str.

[I4mCh40s]

Try setting default_reply of UserProxyAgent to a non-empty str.

Unfortunately still the same error:

Traceback (most recent call last):
  File "c:\Users\ihasdslr\Documents\auto_gen\autogen_init.py", line 37, in <module>
    user_proxy.initiate_chat(
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 531, in initiate_chat
    self.send(self.generate_init_message(**context), recipient, silent=silent)
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 334, in send
    recipient.receive(message, self, request_reply, silent)
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 464, in receive
    self.send(reply, sender, silent=silent)
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 334, in send
    recipient.receive(message, self, request_reply, silent)
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 462, in receive
    reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 781, in generate_reply
    final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 606, in generate_oai_reply
    response = oai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 799, in create
    response = cls.create(
               ^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 830, in create
    return cls._get_response(params, raise_on_ratelimit_or_timeout=raise_on_ratelimit_or_timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\autogen\oai\completion.py", line 218, in _get_response
    response = openai_completion.create(**config)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 155, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 299, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 710, in _interpret_response
    self._interpret_response_line(
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 775, in _interpret_response_line
    raise self.handle_error_response(
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ihasdslr\anaconda3\envs\auto_gen\Lib\site-packages\openai\api_requestor.py", line 428, in handle_error_response
    error_code=error_data.get("code"),
               ^^^^^^^^^^^^^^
AttributeError: 'str' object has no attribute 'get'

My current UserProxy definition now looks like this:

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
    default_auto_reply="default_auto_reply",
    max_consecutive_auto_reply=10,
    code_execution_config={"work_dir": "result"},
    llm_config=llm_config,
)

[sonichi]

Do you intend for the user proxy agent to use llm-based reply? If not, please remove llm_config from its constructor.

[I4mCh40s]

Do you intend for the user proxy agent to use llm-based reply? If not, please remove llm_config from its constructor.

Thanks so much for the help! It worked! Both assistants are now in an infinite loop sending the same code to each other :D But the error is gone. Thank you!

[sonichi]

The user proxy agent is not supposed to send code. It will use default_auto_reply when no code is in the received msg.

[stefan-wiesner]

Ihave the similar issue

Same.

From the API I get the error:

[ERROR] Error: 'messages' array must only contain objects with a 'content' field that is not empty.

And I can see that the repsonse contains multiple content fields which are empty:

, { "content": "```", "role": "user", "name": "Planner" }, { "content": "", "role": "user", "name": "Executor" }, { "role": "system", "content": "Read the above conversation. Then select the next role from ['Admin', 'Engineer', 'Planner', 'Executor', 'Critic'] to play. Only return the role." }

[Terristen]

I'm getting this error trying to run the official example for visualizations with no substantial code changes.
example

The only difference is that I'm using an LLM running on the local network rather than OAI.
config_list_gpt4 = [ { "api_type": "open_ai", "api_base": "http://###.###.##.##:1234/v1", "api_key": "NULL" } ]

The LLM is receiving requests and returning results. This error seems to hit after the first cycle through the group.

[sonichi]

Same reason as I said above. The local LLM doesn't allow empty content. The workaround is to set default_auto_reply to a non empty str.

[POWERFULMOVES]

can you write example? im new at this lol

[POWERFULMOVES]

heres what i got rom autogen import AssistantAgent, UserProxyAgent

Load LLM inference endpoints from an env variable or a file

See https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints

and OAI_CONFIG_LIST_sample

config_list = [
{
"api_type": "openai",
"api_base": "http://localhost:5001/v1",
"api_key": "NULL",
}
]

llm_config={
"request_timeout": 600,
'seed': 42,
"config_list": config_list,
"temperature": 0
}

assistant = AssistantAgent(
name="assistant",
llm_config=llm_config
)
user_proxy = UserProxyAgent(
name="User_proxy",
human_input_mode="TERMINATE",
max_consecutive_auto_reply=10,
is_termination_msg=lambda x: x.get("content","").rstrip().endswith("TERMINATE"),
code_execution_config={"work_dir": "web"},
system_message="""Reply TERMINATE if the task has been solved at full satisfaction.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet."""
)

task = """
plot the stock price of apple for the past 5 days using python
"""

user_proxy.initiate_chat(
assistant,
message=task
)

[sonichi]

@POWERFULMOVES You can add llm_config=llm_config in the constructor of UserProxyAgent if you intend to use llm-based reply for the UserProxyAgent.

[MikeyBeez]

This is a string error. There's something completely wrong with the line: is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),

[MikeyBeez]

import json and do this: # create a UserProxyAgent instance named "user_proxy"
user_proxy = autogen.UserProxyAgent(
name="user_proxy",
human_input_mode="NEVER",
max_consecutive_auto_reply=100,
default_auto_reply="default_auto_reply",

is_termination_msg = lambda x: (

False if x.get("content") is None else

x.get("content", "").rstrip().endswith("TERMINATE")

if isinstance(x.get("content"), str) else

False

),

is_termination_msg = lambda x: (
False if x.get("content") is None else
x.get("content", "").rstrip().endswith("TERMINATE")
if isinstance(json.loads(x.get("content")), dict) else
False
),

code_execution_config={
    "work_dir": "coding",
    "use_docker": True,  # set to True or image name like "python:3" to use docker
},

)

autogen.ChatCompletion.start_logging()

research_problem_to_solve = {
"sender": "user",
"content": json.dumps({
"text": "Get YTD returns for the top 5 performing stocks and plot their prices"
})
}

[MikeyBeez]

This seems to work, although I'm getting a new error. I'm running LM Studio with a local server: raise error.Timeout("Request timed out: {}".format(e)) from e
openai.error.Timeout: Request timed out: HTTPConnectionPool(host='localhost', port=1234): Read timed out. (read timeout=60) In any case, I think I've stopped getting the str error.