<img height="1" width="1" style="display:none;" alt="" src="https://px.ads.linkedin.com/collect/?pid=2634489&amp;fmt=gif">

AI and Machine Learning, Vertex AI, API Management

Building a question answering system with Vertex AI

By Markus Koy | June 16, 2022

Let's say it's the first day in your new job and you have lots of questions. Where is the HR department located or how do I validate parking? Wouldn't it be great if you could just ask a chatbot rather than reading through an internal Wiki? 

 

Here is a recipe to build one:

  1. Select your reference documents and pre-process them in Vertex AI Workbench

  2. Download a model from TensorFlow Hub and register with Vertex AI

  3. Have Vertex AI process your questions and answers

  4. Use Cloud Functions for your REST endpoint

  5. Use the Speech-To-Text and Text-To-Speech APIs to allow users using their voice rather than typing

Sounds complicated? Nikita Namjoshi and Zack Akil demonstrate in this 16 minutes Google Cloud Applied ML Summit video how to do just that.

https://youtu.be/5iSmX8sqtx8


Recent Articles

Data Analytics

Generative AI: Are You Behind?!

Review the latest insights from the AI Readiness Report.
By Bruno Aziza
Industry Solutions

Make "Gen AI Work": Landscape, SLMs vs. LLMs, Cost & More...

Discover the 5 metrics you need to know in order to be an exceptional CEO and Operator.
By Bruno Aziza
Google Cloud Strategy

AI Cheat Sheet

AI is no more and no less the drive to create robots with human minds so they can do everything we do and more. Use this cheat sheet to help decode the space.
By Leah Zitter