1. Question Answering module

The Question and Answer (Q&A) module is a Weaviate module for answer extraction from data. It uses BERT-related models for finding and extracting answers.

During the configuration of Weaviate docker compose file, select the extra-module “Question Answering”, with the qna transformer model you want.

During the creation of your docker compose file from Weaviate wizzard : select the QnA module with a specific transformer model among the list. Then start the docker container.

• (1) Add the “QnA” module
• (2) Select a QnA transformer model in the list.

Download and execute the docker-compose file generated by the wizard (docker-compose up -d):

Below is a video to configure the Weaviate Question Answering suggestions with WPSOLR:

2 Create QnA suggestions

• (1) (2) Create a new suggestion
• (3) Set a css selector where to show the suggestions
• (4) Select the “QnA” suggestions type
• (5) Select the post types to look for QnA answers