liveBook · Manning

Playground

As explained in AI Agents in Action

The Playground is the browser-based interface used in this book to create, configure, and manage assistants.

The Playground is a browser-based interface for creating, configuring, running, and managing assistants locally. It displays existing assistants and supports assistant instructions, custom actions, and local Python execution. section 6.2.1

Use the Playground to:

  • Create assistants and choose their instructions and options. section 6.2.1
  • Install and manage predefined assistants through a Manager Assistant. section 6.3.1
  • Add custom actions and run Python locally in an isolated virtual environment. section 6.2.1

Install and open the Playground

Clone the project, install its requirements, set OPENAI_API_KEY, and run python main.py. Open the displayed local URL, typically http://127.0.0.1:7860, in a browser. section 6.2.1

Please list all the installable assistants.

Use the Manager Assistant to discover installable assistants, then request a specific installation or save assistant definitions as JSON. section 6.3.1

How AI Agents in Action covers it

How deep it goes
Walks through installation, launching, assistant creation, and management, while deferring detailed implementation code.
Examples
Uses a local math-learning interface, a Manager Assistant, predefined assistants, and terminal installation commands.
What it assumes
Assumes terminal access, Python project installation, and an OpenAI API key before launching the interface.
What you can do after
Operate and configure assistants through a browser, including installing assistants and executing local Python actions.
How it connects
Connects assistants with custom actions, the OpenAI API, Code Interpreter, virtual environments, and JSON definitions.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Agents in Action. The section links point to the parts of the book it draws on.