Beibin Li

@tomorrmato 1. You should NOT provide a "llm_config" into user_proxy; otherwise, it will not run code for you. 2. You need to wrap your code in markdown if you want...

Because you have a manually-defined workflow, you don't need a groupchat manager. You can either use [sequential chat](https://microsoft.github.io/autogen/docs/notebooks/agentchats_sequential_chats/) or the FigureCreator directly from [here](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_dalle_and_gpt4v.ipynb). I can create an example later...

Very good project! Can you provide some details how you convert the MXnet (or Caffe, PyTorch, TensorFlow, etc) models into the TXT files? Thanks!

Very interesting! Do you have a blog, tutorial, or video to teach me how to use the terminal app? I have tried some basic functionalities here, but would need help...

@shaunaa126 You should use MultimodalConversableAgent instead of LLaVAAgent, because your API call supports the OpenAI API version. The LLaVA agents are designed for the original LLaVA client. Check the [GPT-4V...

> @BeibinLi thanks for your response, your solution worked. I was able to use MultiModalConversableAgent to make a call to my OpenAI API endpoint. > > Do you know how...

It is not a HTML image tag. Just use "image_path". For instance `user_proxy.initiate_chat(assistant, message=f"Describe this image. " )` `user_proxy.initiate_chat(assistant, message=f"Describe this image. " )` `user_proxy.initiate_chat(assistant, message=f"Describe this image. " )`

@whatUwilldoknowingmyname Yes, check - LLaVA: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_llava.ipynb - DALLE: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_dalle_and_gpt4v.ipynb Even if DALLE is not open source, using other open-source stable diffusion model would be the same process.

Very interesting PR, and it simulates how a human user (agent) would navigate within the browser. Quick question: can we have an option to use "BeautifulSoup" to fetch the whole...

Thanks for the details! It seems you are using a different pydantic version. Can you try: ``` pip install "google-generativeai" "pydash" "pillow" "pydantic==1.10.13" ```