Autogen + Ollama: Selfhosting Local LLM Agents with UI

SelfHosting Conversating Agens with Autogen & Ollama for free - GPT4 Code Interpreter F/OSS Alternative

Multi-Agent Workflows

The Autogen Project

AutoGen is a F/OSS framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

AutoGen agents are customizable, conversable, and seamlessly allow human participation.

• https://github.com/microsoft/autogen

AutoGen Studio is an AutoGen-powered AI app (user interface) to help you rapidly prototype AI agents, enhance them with skills, compose them into workflows and interact with them to accomplish tasks. It is built on top of the AutoGen framework, which is a toolkit for building AI agents.

• https://github.com/microsoft/autogen/tree/main/samples/apps/autogen-studio
• https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/

Why Autogen?

They can operate in various modes that employ combinations of LLMs, human inputs, and tools.

The Autogen package in PyPI.

pip install pyautogen==0.1.14
#pip show pyautogen


pip install --upgrade streamlit reflex
pip install webencodings

pip install beautifulsoup4
pip install bleach nbconvert

pip install pexpect #for jupyter

Autogen with Ollama

Get Ollama running.

Autogen + Autogen Studio

pip install autogenstudio
autogenstudio ui --port 8007

version: '3'

services:
  autogen:
    image: python:3.11-slim
    container_name: autogen
    command: tail -f /dev/null
    volumes:
      - ai_autogen:/app
    working_dir: /app  # Set the working directory to /app
    ports:
      - "8007:8001"

volumes:
  ai_autogen:

FAQ

Other F/OSS Multi-Agent Projects

• https://github.com/lavague-ai/LaVague

Large Action Model framework to develop AI Web Agents

The Lavague project is about automating web interactions using large language models (LLMs).

Open-source Text2Action AI pipeline to turn natural language into Selenium code

F/OSS prompt management & versioning tools

• Pezzo: https://github.com/pezzolabs/pezzo

• Agenta: https://github.com/Agenta-AI/agenta

https://github.com/tensorchord/Awesome-LLMOps?tab=readme-ov-file#llmops