autogenstudio 0.0.9a0

Autogen Studio

AutoGen Studio

AutoGen Studio is an Autogen-powered AI app (user interface) that can converse with you to help you conduct research, write and execute code, run saved skills, create new skills (explicitly and by demonstration), and adapt in response to your interactions.

Capabilities / Roadmap

Some of the capabilities supported by the app frontend include the following:

• Select fron a list of agents (current support for two agent workflows - UserProxyAgent and AssistantAgent)
• Modify agent configuration (e.g. temperature, model, agent system message, model etc) and chat with updated agent configurations.
• View agent messages and output files in the UI from agent runs.
• Support for more complex agent workflows (e.g. GroupChat workflows)
• Improved user experience (e.g., streaming intermediate model output, better summarization of agent responses, etc)

Project Structure:

• autogenstudio/ code for the backend classes and web api (FastAPI)
• frontend/ code for the webui, built with Gatsby and Tailwind

Installation

1. Install from PyPi

   We recommend using a virtual environment (e.g., conda) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio:

   pip install autogenstudio
   

2. Install from Source

   Note: This approach requires some familiarity with building interfaces in React.

   If you prefer to install from source, ensure you have Python 3.10+ and Node.js (version above 14.15.0) installed. Here's how you get started:

   • Clone the AutoGen Studio repository and install its Python dependencies:

     pip install -e .
     

   • Navigate to the samples/apps/autogen-assistant/frontend directory, install dependencies, and build the UI:

     npm install -g gatsby-cli
     npm install --global yarn
     cd frontend
     yarn install
     yarn build
     

   For Windows users, to build the frontend, you may need alternative commands to build the frontend.

   ```bash
   
   gatsby clean && rmdir /s /q ..\\autogenstudio\\web\\ui && (set \"PREFIX_PATH_VALUE=\" || ver>nul) && gatsby build --prefix-paths && xcopy /E /I /Y public ..\\autogenstudio\\web\\ui
   
   ````
   

Running the Application

Once installed, run the web UI by entering the following in your terminal:

autogenstudio ui --port 8081

This will start the application on the specified port. Open your web browser and go to http://localhost:8081/ to begin using AutoGen Studio.

Now that you have AutoGen Studio installed and running, you are ready to explore its capabilities, including defining and modifying agent workflows, interacting with agents and sessions, and expanding agent skills.

Capabilities

AutoGen Studio proposes some high-level concepts that help compose agents to solve tasks.

Agent Workflow: An agent workflow is a specification of a set of agents that can work together to accomplish a task. The simplest version of this is a setup with two agents – a user proxy agent (that represents a user i.e. it compiles code and prints result) and an assistant that can address task requests (e.g., generating plans, writing code, evaluating responses, proposing error recovery steps, etc.). A more complex flow could be a group chat where even more agents work towards a solution.

Session: A session refers to a period of continuous interaction or engagement with an agent workflow, typically characterized by a sequence of activities or operations aimed at achieving specific objectives. It includes the agent workflow configuration, the interactions between the user and the agents. A session can be “published” to a “gallery”.

Skills: Skills are functions (e.g., Python functions) that describe how to solve a task. In general, a good skill has a descriptive name (e.g. generate_images), extensive docstrings and good defaults (e.g., writing out files to disk for persistence and reuse). You can add new skills AutoGen Studio app via the provided UI. At inference time, these skills are made available to the assistant agent as they address your tasks.

AutoGen Studio comes with 3 example skills: fetch_profile, find_papers, generate_images. Please feel free to review the repo to learn more about how they work.

Example Usage

Let us use a simple query demonstrating the capabilities of the research assistant.

Plot a chart of NVDA and TESLA stock price YTD. Save the result to a file named nvda_tesla.png

The agents responds by writing and executing code to create a python program to generate the chart with the stock prices.

Note than there could be multiple turns between the AssistantAgent and the UserProxyAgent to produce and execute the code in order to complete the task.

Note: You can also view the debug console that generates useful information to see how the agents are interacting in the background.

FAQ

Q: How can I add more skills in AutoGen Studio? A: You can extend the capabilities of your agents by adding new Python functions. The AutoGen Studio interface also lets you directly paste functions that can be reused in the agent workflow.

Q: Where can I adjust the agent configurations and settings? A: You can modify agent configurations directly from the UI or by editing the default configurations in the utils.py file under the get_default_agent_config() method (assuming you are building your own UI).

Q: If I want to reset the conversation with an agent, how do I go about it? A: To reset your conversation history, you can delete the database.sqlite file. If you need to clear user-specific data, remove the relevant autogenstudio/web/files/user/<user_id_md5hash> folder.

Q: Is it possible to view the output and messages generated by the agents during interactions? A: Yes, you can view the generated messages in the debug console of the web UI, providing insights into the agent interactions. Alternatively, you can inspect the database.sqlite file for a comprehensive record of messages.

Acknowledgements

AutoGen Studio is Based on the AutoGen project. It was adapted from a research prototype built in October 2023 (original credits: Gagan Bansal, Adam Fourney, Victor Dibia, Piali Choudhury, Saleema Amershi, Ahmed Awadallah, Chi Wang).