NGC | Catalog
CatalogCollectionsAccelerate Development of Intelligent Virtual Assistants

Accelerate Development of Intelligent Virtual Assistants

For contents of this collection and more information, please view on a desktop device.
Logo for Accelerate Development of Intelligent Virtual Assistants

Description

Quickly develop and provide accurate and engaging English intelligent virtual assistant for contact centers, at a large scale, around the clock, at lower operational costs.

Curator

NVIDIA

Modified

January 6, 2023
Containers
Helm Charts
Models
Resources

Overview

The intelligent virtual assistant AI workflow integrates NVIDIA Riva English automatic speech recognition (ASR) and text-to-speech (TTS) with Haystack, a third-party, open-source natural language processing (NLP) service for information retrieval and question answering (IRQA), and Rasa, an open-source dialog manager.

The intelligent virtual assistant is available to customers with a subscription to NVIDIA AI Enterprise software.

Besides Riva, Haystack, and Rasa helm charts, a Grafana dashboard helm chart exposes NVIDIA Triton™ Inference Server GPU request metrics for monitoring via Prometheus.

The packaged components of this workflow are cloud native and include examples of enterprise-ready best practices for authentication, monitoring, reporting, and load balancing, while allowing a path for you to deviate.

image1



Key benefits of the Riva intelligent virtual assistant for contact centers AI workflow:

  • The Best Possible Accuracy: Get an intelligent virtual assistant with customized Riva English ASR service for the best possible real-time accuracy for the financial service industry use case.

  • Expressive OOTB English Voices: Provide intelligent virtual assistants with professional English female and male voices with Riva pretrained TTS models.

  • Seamless Scaling: Instantly scale to hundreds and thousands of intelligent virtual assistants with microservices deployable on any cloud Kubernetes distribution. 

  • Fast & Flexible Deployment: Quickly get started with a deployable intelligent virtual assistant in the cloud, on-premises, or on edge.

Documentation

Additional Resources

Learn more about how to use NVIDIA Riva through our Deep Learning Institute platform. You can work with Riva interactively on hardware provided by NVIDIA hosted in the cloud.

You must have a developer account and be signed in to access the following Riva courses:

If you have an NVIDIA AI Enterprise subscription access the intelligent virtual assistant workflow through Enterprise Catalog.