app.py

gistfile1.txt

import autogen

config_list = [
    {
        'model': 'gpt-4',
        'api_key': 'API_KEY'
    }
]

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

assistant = autogen.AssistantAgent(
    name="CTO",
    llm_config=llm_config,
    system_message="Chief technical officer of a tech company"
)

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={"work_dir": "web"},
    llm_config=llm_config,
    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 = """
Write python code to output numbers 1 to 100, and then store the code in a file
"""

user_proxy.initiate_chat(
    assistant,
    message=task
)

task2 = """
Change the code in the file you just created to instead output numbers 1 to 200
"""

user_proxy.initiate_chat(
    assistant,
    message=task2
)

Me too keep having endless loop :( Anyone solved?

I'm getting error, please advise: Traceback (most recent call last): File "c:\Users\GuestUser\vsCode\autogen\app.py", line 17, in assistant = autogen.AssistantAgent( ^^^^^^^^^^^^^^^^^^^^^^ AttributeError: module 'autogen' has no attribute 'AssistantAgent'

try
python -m pip install autogen

assistant = autogen.AssistantAgent(
AttributeError: partially initialized module 'autogen' has no attribute 'AssistantAgent' (most likely due to a circular import)

My python environments has only pyautogen==0.1.14, no autogen But this error still appear.
The funny thing is, I have a ubuntu and a win11, this error does not appear in win11, only appear in ubuntu.

According to BARD AI to fix the loop you need to: "Another way to fix the problem is to change the code so that the user proxy will only automatically reply to messages that are not completed. You can do this by changing the max_consecutive_auto_reply setting to 0. This will ensure that the user proxy will only automatically reply to the first message in a conversation." - tested stopped looping

I am using assistants to calculate today's date based on your video. But it gives out this response : As an AI, I don't have real-time capabilities or access to current data, including today's date or the latest stock market figures. To find out today's date, please check your computer or smartphone's clock.

Anyone trying this on Ubuntu and getting various errors. I have it working. First make sure to use "use_docker" as adnansalamat mentioned. Make sure you have the python:3 image pulled from Docker registry. Also, if you are using Docker Desktop, use the locate command to search for your socket. If it is outside of /var/run you need to make a link from the location to /var/run/docker.sock

I'm getting this error: TypeError: Completions.create() got an unexpected keyword argument 'request_timeout'

Anyone experience this?

Using pyautogen on python 3.11.6 in a virtual environment.

I'm getting this error: TypeError: Completions.create() got an unexpected keyword argument 'request_timeout'

Anyone experience this?

Using pyautogen on python 3.11.6 in a virtual environment.

Found the solution here
Change...

llm_config={
    "request_timeout": 600,

to...

 llm_config = {
        "timeout": 600,

1. autogen.AssistantAgent error fix:
   pip uninstall autogen pyautogen
   pip install pyautogen
2. request_timeout issue:
   "timeout": 600
3. Infinte loop issue:
   in the user_proxy set the max_consecutive_auto_reply=0
4. Stopping a session
   ctrl + c

For me it seems when ever I get a ''' in the LLM response autogen stops with "Process finished with exit code 0"

Example LLM Output:
`CTO (to user_proxy):

def get_numbers():
    return list(range(1, 201))
with open("generated.py", "w") as f:
    f.write('''print(*get_numbers())''')

---

Process finished with exit code 0`

Here is the complete code. Am using text gen web UI local model not Run Pod using Mistral 7B instruct Q8 GGUF. Be sure to enable openai and gallery extensions and api and listen Under Sessions tab on Text Gen Web UI

import autogen

config_list = [
{
"base_url": "http://localhost:5000/v1",
"api_key": "NULL",
}
]

llm_config={
"timeout": 600,
"seed": 42,
"config_list": config_list,
}

USE_MEMGPT = True

assistant = autogen.AssistantAgent(
name="CTO",
llm_config=llm_config,
system_message="Chief technical officer of a tech company"
)

user_proxy = autogen.UserProxyAgent(
name="user_proxy",
human_input_mode="NEVER",
max_consecutive_auto_reply=0,
is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
code_execution_config={"work_dir": "web"},
llm_config=llm_config,
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 = """
Write python code to output numbers 1 to 100, and then store the code in a file
"""

user_proxy.initiate_chat(
assistant,
message=task
)

task2 = """
Change the code in the file you just created to instead output numbers 1 to 200
"""

user_proxy.initiate_chat(
assistant,
message=task2
)

I'm getting stuck on the following error:
raise self._make_status_error_from_response(err.response) from None
openai.RateLimitError: Error code: 429 - {'error': {'message': 'Rate limit reached for gpt-4 in organization org-ehVxQx3I1TFqEcMydXbUkFUz on tokens per min (TPM): Limit 10000, Used 9343, Requested 1103. Please try again in 2.676s. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}
what can i do with the rate-limiting error?