Shelves for AI visual

Overview of shelves for Cloudera Data Visualization AI visual.

An AI visual has the following shelves:

Embeddings

This shelf is used for the vector database comparisons. The user input is vectorized and compared to the defined embeddings to get the most similar rows that contain the embeddings. The first field that contains results is returned.

Add a Dimension or Measures vector field that contains embeddings.

This is a mandatory shelf that accepts multiple fields.

Embedding Context

Add fields that you want to send as part of the chat prompt as a formatted version of all of the embedding context data.

This is a mandatory shelf that accepts multiple fields.

Tooltip

This setting enables the addition of a field for source information to be included in the displayed results.

Limit

This setting defines the number of data rows that are processed by the visual.