Create a machine learning powered web app to answer questions

Summary
In this code pattern, learn how to construct a chatbot that addresses a users concerns by discovering the answer in a college biology textbook.
Description
Ever discovered yourself wondering what mitochondria are? Maybe you are curious about how neurons communicate with each other? A Google search works well to address your questions, however what about something still absorbable, but more precise? This code pattern reveals you how to develop a chatbot that responds to a users concerns by discovering the response in a college biology textbook. In the pattern, the textbook used is Biology 2e by Mary Ann Clark, Matthew Douglas, and Jung Choi.
The web app uses the Model Asset eXchange (MAX) Question Answering Model (hosted on the Machine Learning eXchange) to address questions that are typed in by the user. The back end sends out the concern and associated body of text from the book to a REST endpoint exposed by the MAX model, which returns a response to the question, displayed as a response from the chatbot.
When you have finished this code pattern, you comprehend how to:

Construct a Docker picture of the Question Answering design
Release a deep learning design with a REST endpoint
Produce answers to concerns utilizing the designs REST API
Run a web application that using the models REST API

Flow

Instructions
Find the comprehensive steps for this pattern in the README file. The steps reveal you how to:

A Google search works well to answer your questions, but what about something still absorbable, but more exact? The web app uses the Model Asset eXchange (MAX) Question Answering Model (hosted on the Machine Learning eXchange) to answer concerns that are typed in by the user. The web application offers a chat-like interface that lets users type in questions, which are then sent out to a Flask Python server. The back end sends out the concern and associated body of text from the textbook to a REST endpoint exposed by the MAX design, which returns a response to the question, displayed as a reaction from the chatbot.

Deploy the design.
Build the web app.
Clone the repository.
Install the dependences.
Start the server.

Leave a Reply

Your email address will not be published.