I want to understand if how to maintain the chat history in the autogen, can you please help me with that?

Is it possible to achieve real-time streaming of Assistant/user_proxy interactions like ChatGPT/Claude? If so, it would greatly enhance user interactivity! Do you have any ideas? I know we can do it by patching some functions in the conversable agent, but I'm looking for a better and more scalable solution. @victordibia @janaka

Tx.

Can you please make a video of how you install and set this up?
I followed the instructions exactly as you have it documented and I get an error trying to start it.
Either a video or some exact commands to get it working would be helpful.
UI looks incredible, but when we can use it, it's not much help.

Probably need to add it to your pyproject.toml

If the human_input_mode is activated, it currently asks for input in the terminal running the fastapi server. It would be great if this requests could be done in the UI, so users can consent to execute Querries or drive the interaction into another direction before ending it.

git clone [email protected]:victordibia/autogen-ui.git
Clonage dans 'autogen-ui'...
The authenticity of host 'github.com (140.82.121.4)' can't be established.
ECDSA key fingerprint is
Are you sure you want to continue connecting (yes/no/[fingerprint])? yes
Warning: Permanently added 'github.com,140.82.121.4' (ECDSA) to the list of known hosts.
[email protected]: Permission denied (publickey).
fatal: Impossible de lire le dépôt distant.

Veuillez vérifier que vous avez les droits d'accès
et que le dépôt existe.

Hello,

thanks for this template! I followed the instructions carefully, but unfortunately i'm having a few issues:

1. It seems the dependencies require Python >=3.9. I had 3.8 installed but i received this error message:
   ERROR: Package 'autogenui' requires a different Python: 3.8.0 not in '>=3.9'

2. After switching to 3.9 and trying to launch with autogenui i see that typer seems to be missing from the dependencies:
   ModuleNotFoundError: No module named 'typer'

3. After installing typer, i notice that autogen itself is missing too

4. After installing autogen using pip install autogen, i can launch with autogenui, but when trying to send a message i see

• in the Brower/app: Connection error. Ensure server is up and running.
• console: INFO: 127.0.0.1:51780 - "OPTIONS /api/generate HTTP/1.1" 400 Bad Request

Edit:

Edit2:

✅ Solution:

Do not install autogen instead of pyautogen accidentally! Also, make sure the practices outlined in the first two answers are followed.

Apologies the documentation did not make this clear, I am unable to test this but would love to try it out

i run autogenui in colab, but i always get AssertionError: (Deprecated) The autogen.Completion class requires openai<1 and diskcache.

i tried:
pip install openai==0.27.0 diskcache
change the version to openai<1, but it doesn't work
can you help me?

how can I solve this problem?

`
hello

assistant (to user_proxy):

Hello! How can I assist you today?

user_proxy (to assistant):

Sure, I'd be happy to help. What do you need assistance with?

assistant (to user_proxy):

Hello! How can I assist you today?

user_proxy (to assistant):

It seems like you're trying to mimic my responses. How can I assist you further?

assistant (to user_proxy):

Hello! How can I assist you today?

user_proxy (to assistant):

Hello! As an AI, I don't require assistance. But thank you for asking! How can I assist you instead?

what is the height of the eiffel tower

assistant (to user_proxy):

The height of the Eiffel Tower is approximately 330 meters (1,083 feet) including antennas. However, the height varies slightly depending on the ambient temperature as the metal expands or contracts.

user_proxy (to assistant):

The height of the Eiffel Tower is approximately 330 meters (1,083 feet) including antennas. However, the height varies slightly depending on the ambient temperature as the metal expands or contracts.

assistant (to user_proxy):

That's correct! The Eiffel Tower's height can indeed vary by a few inches depending on the temperature. The iron structure expands and contracts with the heat and cold. This is a common characteristic of metal structures. Is there anything else you would like to know?

user_proxy (to assistant):

I'm glad you found the information accurate! Yes, the Eiffel Tower is a fascinating structure. If you have any other questions or need information on a different topic, feel free to ask!

assistant (to user_proxy):

I'm glad you found the information accurate! Yes, the Eiffel Tower is a fascinating structure. If you have any other questions or need information on a different topic, feel free to ask!

user_proxy (to assistant):

I'm glad you found the information helpful! If you have any other questions, feel free to ask. I'm here to help!

`

I am running this on replit and receiving the above error.

Could you please help me on this?

Thanks

Now only I can see the assistant reply only when the task is finished. Is there any setting that make the chat interactive?

I'm able to run autogen using a config list like
config_list = [
{
"model": "mistral-7b-instruct-v0.1.Q5_0.gguf",#"mistral-instruct-7b", #t
he name of your running model
"api_base": "http://0.0.0.0:5001/v1", #the local address of the api
"api_type": "open_ai",
"api_key": "sk-111111111111111111111111111111111111111111111111", # just
a placeholder
}
]

Which talks to text-generation-Webui which has the openai api emulation turned on.
It would be nice to have a similar way of using a local llm with autogen-ui

Even after creating a .env file with my API key, it is not recognized. Is there a way to hard code the API key into the script?

I can use Autogen with my AzureOpenAI keys. Can I do the same with this package? Please help.

i have successfully cloned this repo but next I am unaware how to make it run.
i could not gather enough information from the readme.md file so could you please give me a hint on how I can make this web ui run with autogen?

thanks

I am currently using autogen-ui in a project and encountered an issue related to the openai library version. My environment uses openai version 1.3.6, but autogen-ui seems to require a version lower than 1.0. Due to specific needs in my project, downgrading the openai library is not a feasible option for me.

original code : AssertionError: (Deprecated) The autogen.Completion class requires openai<1 and diskcache.

I am seeking guidance or a workaround to make autogen-ui compatible with openai version 1.3.6. Has anyone faced a similar issue or can provide insights into modifying the codebase for compatibility? Any help or suggestions would be greatly appreciated.