FAQ Solution

Smart Answers model training and deployment with an existing FAQ

FAQ solution flow

The FAQ solution consists of two parts:

  1. Model training

    Model training is performed in a Docker image, downloaded from the Lucidworks Docker hub. The deep learning/word vector training modules and configuration UI are installed in the Docker image, and it can be used on-prem or in the cloud.

    After training is finished, two .zip files are generated which each include a model and associated files. The model is basically an encoder which transforms documents into digital vectors which can be used to measure similarities.

  2. Model deployment

    The deployment part is performed in Fusion:

    1. Upload the question and answer models to the blob store.

    2. Configure the question-answering index pipeline so that it uses the answer model.

    3. Configure the question-answering query pipeline so that it uses the question model.