Rasa Advanced Custom Actions, Forms, & Responses Workshop
What you'll learn
- Build custom integrations with third-party services
- Externalize your assistant's responses via REST APIs in the language of your choice
- Test your assistant end-to-end before releasing it to production
Requirements
- Before taking the Advanced Certification Workshop in Custom Actions, Forms, and Responses, we recommend completing the Rasa Certification Workshop, or equivalent experience building assistants with Rasa.
- Familiarity with Docker
- Familiarity with Python 3.7.x
- Familiarity with Vault
- Familiarity with JDK11
Description
Conversational AI prototypes often don’t uncover the hard problems––conversational AI applications in production do. This ~4 hour certification workshop is designed for experienced Rasa developers and conversational AI professionals who want to grow and test their knowledge of Rasa custom actions, forms, and responses and build resilient applications that work in production environments.
This Advanced Certification workshop is led by Mady Mantha, Senior Technical Evangelist at Rasa. You’ll receive training to help you build custom integrations with third-party services, externalize your assistant’s responses via REST APIs in the language of your choice, and test your assistant end-to-end before releasing it to production.
Prerequisites
Before taking the Advanced Certification Workshop in Custom Actions, Forms, and Responses, we recommend completing the Rasa Certification Workshop, or equivalent experience building assistants with Rasa.
We’ll be working extensively with:
Docker
Python 3.7.x
Vault
JDK11
We recommend that you already have familiarity with these technologies before the workshop, as we’ll be concentrating primarily on how these technologies work with Rasa rather than introducing the tools themselves. This workshop is ideal for developers who already have experience building assistants and want to polish their development skills with Rasa.
Day 1: Custom Actions and Forms
We'll cover:
Deep dive into Custom Actions
Define a user profile slot
Implement and execute secure external service calls
Securely invoke external service to fill slots
Understand security best practices / secure coding
Deep dive into Forms
Required slots
Validate slots
Filling slots via NLU using helper methods
The special "requested_slot" slot
Securely invoke external service on Form submit
Day 2: Responses and Testing
We’ll cover:
Deep dive into Responses
Externalize Utterances/Responses
Responses in Java exposed via REST API
Understand testing
Write unit tests
Mock external services
End-to-end testing
Discuss real-world scenarios - case studies
Who this course is for:
- DevOps engineers
- Chatbot developers
- Data scientists curious about DevOps
Course content
- Preview30:56
Instructors
Rasa supplies the standard infrastructure for conversational AI, providing the tools required to build better, more resilient contextual assistants. With more than 3 million downloads since launch, Rasa Open Source is loved by developers worldwide, with our friendly, fast-growing community learning from each other and working together to make better text- and voice-based AI assistants. Rasa offers three key products in its suite of conversational AI offering. Rasa Open Source is the most popular open source software in conversational AI. Rasa X, released in 2019, is a free toolset that helps developers quickly improve and share an AI assistant built with Rasa Open Source. Rasa Enterprise is the company's commercial offering, providing an enterprise-grade platform for developing contextual assistants at scale. Rasa runs in production everywhere from startups to Fortune 500s, and provides the data privacy and security needed to enterprises of every size. Rasa is privately held, with funding from Accel, Andreessen Horowitz, Basis Set Ventures, and others. The company was founded in 2016 and has offices in San Francisco and Berlin.
Mady Mantha is a Senior Technical Evangelist at Rasa. Mady studied Computer Science, Physics, and International Politics at Georgetown University. Her work focuses on natural language processing, and operationalizing machine learning and conversational AI pipelines. She has years of experience building ML-driven products and services for think tanks, startups, and enterprises. Mady is a space enthusiast.