Train and Deploy an AI Support Chatbot
Train and Deploy an AI Support Chatbot (Latest Version)

Overview

Welcome to the trial of NVIDIA AI Enterprise on NVIDIA LaunchPad.

The NVIDIA AI Enterprise suite includes the applications, frameworks, and tools used by AI researchers, data scientists, and developers.

nvaie-overview.png

NVIDIA AI Enterprise allows AI Practitioners to run Deep Learning workflows in virtual machines with the same performance as bare metal. AI Practitioners can quickly access Jupyter Notebooks which leverage NVIDIA GPUs since IT Administrators have all the tools to create VMs with required NVIDIA AI Enterprise components to perform AI Training and deploy inferencing using Triton. This allows AI Practitioners to have instant access to valuable GPU resources which are within Enterprise data centers.

In this AI Practitioner LaunchPad journey, you will gain hands on experience for developing and deploying a Natural Language Processing (NLP) AI application. The use case example within this LaunchPad journey is an IT Help Desk chatbot leveraging TensorRT and Triton Inference Server. Fine tuning is performed using the run_squad library. The fine tuning may take around 90 minutes when using a single A30 GPU to complete.

Important

To assist you in your LaunchPad journey, there are a couple of important links on the left-hand navigation pane of this page. In the next step, you will use the Jupyter notebook link. SSH link to the VM is provided as well, you will use this after you train the Bert QA Model within the Jupyter Notebook.

© Copyright 2022-2023, NVIDIA. Last updated on Jan 10, 2023.