When you train a model, you will have to select what kind of data you will train, "Conversations" or "General Text Data"

Compared to conversations, general text data is more easily represented.

We only require a .csv file with one row per text item and one column with the content.

Also we can get the data from an integration with our platform like "Intercom" in this case, we will get the data and create de .csv.


We encourage you to include further columns in your dataset.

Metadata of any type may be helpful to train better models, especially dates. Also, we can cross-reference the metadata and the results to provide you with useful insights.

Simply download this example file to get started!

Did this answer your question?