Implementation of AutoGen inside ComfyUI.
This repository is under development, and not everything is functioning correctly yet.
Dont share your workflow with any API keys inside!!!
The example above should work mostly after installation. The output is displayed in the terminal, and the workflow can be found in the repository (Task_Solving_with_Code_Generation.json).
-
autogen: Automated Multi Agent Chat
-
Automated Task Solving with Code Generation, Execution & Debugging
-
Automated Complex Task Solving by Group Chat
-
New: llama-cpp (slow), llava
-
Functions
-
MemGPT (NotWorkingFolder)
please let me now if you have any issus installing.
Install: https://github.com/comfyanonymous/ComfyUI
I would recomend using LM Studio: https://lmstudio.ai/
Git clone the repository: git clone https://github.com/xXAdonesXx/NodeGPT into the "custom nodes" folder inside ComfyUI
Upon starting, ComfyUI should install the requirements.
Try running the Update.bat inside ComfyUI\custom_nodes\NodeGPT
Start the LM Studio Server
Start ComfUI and place nodes.
For llava:
https://huggingface.co/mys/ggml_llava-v1.5-7b
Pull requests, suggestions, and issue reports are welcome.
LM Studio
ComfyUI: https://github.com/comfyanonymous/ComfyUI
oobabooga: https://github.com/oobabooga/text-generation-webui
chatGPT: https://chat.openai.com/chat
autogen: https://github.com/microsoft/autogen