Building Conversational AI Applications
(대화형 AI 애플리케이션 구축)
Duration
1day 8hous
Language
English
Technologies
NVIDIA Riva, NVIDIA TAO Toolkit, Kubernetes
이미지
Workshop Details
  • As our world continues to evolve and become more digital, conversational AI is increasingly used to facilitate human-to-machine communication. Conversational AI is the technology that powers automated messaging and speech-enabled applications, and its applications are used in various industries to improve overall customer experience, while improving customer service efficiency.
  • Conversational AI pipelines are complex and expensive to develop from scratch. In this course, you'll learn how to build a conversational AI service using the NVIDIA Riva framework. Riva provides a complete, GPU-accelerated software stack, making it easy for developers to quickly create, deploy, and run end-to-end, real-time conversational AI applications that can understand terminology that’s unique to each company and its customers. The Riva framework includes pretrained conversational AI models, tools, and optimized services for speech, vision, and natural language understanding (NLU) tasks. With Riva, developers can create customized language-based AI services for intelligent virtual assistants, virtual customer service agents, real-time transcription, multi-user diarization, chatbots, and much more.
  • In this workshop, you’ll learn how to quickly build and deploy production quality conversational AI applications with real-time transcription and natural language processing (NLP) capabilities. You’ll integrate NVIDIA Riva automatic speech recognition (ASR) and named entity recognition (NER) models with a web-based application to produce transcriptions of audio inputs with highlighted relevant text. You'll then customize the NER model, using NVIDIA TAO Toolkit to provide different targeted highlights for the application. Finally, you'll explore the production-level deployment performance and scaling considerations of Riva services with Helm Charts and Kubernetes clusters.
Prerequisites
  • >

    Basic Python programming experience

  • >

    Fundamental understanding of a deep learning framework, such as TensorFlow, PyTorch, or Keras

  • >

    Basic understanding of neural networks

Assessment Type
  • >

    Skills-based coding assessments evaluate your ability to build a conversational AI application

  • >

    Multiple-choice questions evaluate your understanding of the conversational AI concepts presented in the class

Certificate
Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Hardware Requirements
You’ll need a desktop or laptop computer capable of running the latest version of Chrome or Firefox. You’ll be provided with dedicated access to a fully configured, GPU-accelerated workstation in the cloud.
교육문의하기
Learning Objectives
  • 01

    How to deploy and enable pretrained ASR and NER models on Riva for a conversational AI application.
  • 02

    How to fine-tune and deploy domain-specific models with TAO Toolkit.
  • 03

    How to deploy a production-level conversational AI application with a Helm Chart for scaling in Kubernetes clusters.
Workshop Outline
Introduction (15 mins) · Meet the instructor
· Create an account at courses.nvidia.com/join
Introduction to
Conversational AI
(120 mins)
Explore the conversational AI landscape and gain a deeper understanding of the key components of ASR and NLP pipelines
· Work through a TAO Toolkit model inference example with speech recognition
· Deploy Riva ASR and NER models
· Launch a contact application with ASR and NER
Break (60 mins)
Model Customization
(120 mins)
Explore the details of Riva architecture and discuss the workflow involved in deployment of fine-tuned models using TAO Toolkit
· Fine-tune NER for a specific domain
· Deploy a customized NER model within Riva
· Launch the application with updated models
Break (15 mins)
Inference and
Deployment Challenges
(120 mins)
Explore challenges related to performance, optimization, and scaling in production deployment of conversational AI applications
· Gain an understanding of the inference deployment process
· Analyze non-functional requirements and their implications
· Use a Helm Chart to deploy a conversational AI application with a Kubernetes cluster
Final Review
(15 mins)
· Review key objectives and answer questions.
· Finish the assessment and earn your certificate.
· Complete the workshop survey.
· Learn how to set up your own AI application development environment.