liveBook · Manning

Action

As explained in Natural Language Processing in Action, Second Edition

A bot action is an executable response or operation that a conversational system performs after processing user input.

A bot action is an executable response or operation performed after processing a user intent. It may be a predefined utterance or Python code that saves or retrieves database data, invokes a web API, or interacts with another system. section 12.5.1

Rasa uses actions as conversation building blocks:

  • Predefined response actions send messages such as greetings, permission requests, or confirmation text. section 12.5.1
  • Custom Python actions perform operations involving databases, web APIs, or other external systems. section 12.5.1
  • Stories chain intents and actions into YAML-defined multistep dialog scenarios. section 12.5.1

How Natural Language Processing in Action, Second Edition covers it

How deep it goes
Explains predefined and Python actions, external integrations, and YAML story wiring.
Examples
Demonstrates greetings, permission prompts, confirmations, and an onboarding story for a math tutor chatbot.
What it assumes
Assumes user intents and multistep conversations as the surrounding dialog concepts.
What you can do after
Apply it via Rasa by configuring response actions and sequencing them with intents in stories.
How it connects
Connects actions with user intents, stories, YAML configuration, databases, and web APIs.

Also explained in

Compare how 13 books explain action →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Natural Language Processing in Action, Second Edition. The section links point to the parts of the book it draws on.