Import a CSV

The first step in this process is to upload a CSV containing the data you would like to use to fine-tune the model.

If you have access to training data you'd like to use, you can use your own CSV.

If you'd like to follow along using a pre-built example, you can download the CSV below:

2KB

Customer Chat Support Messages.csv

This example CSV contains two columns:

Inbound Request: An inbound chat message from a client seeking support with an enterprise SaaS product.
Support Agent Response: A response from a customer support agent designed to gather a few pieces of information during the intake of the support event.

Create a New Project

Go to the home screen and press + to create a new project.

For the Project description, you can put the following:

Respond to inbound chat support requests

Press "Create" and you will land in a new project called "Chat Support Agent" or similar.

Import CSV

Press "Import" in the lower left-hand corner of the main project page.

Review Columns

Once you've uploaded your CSV, you'll be asked to review your columns.

Each column in your CSV will be mapped to a field in Entry Point.

Selecting "New" vs "Skip" will determine if the given column gets included or removed from the import.
- This is helpful because in some cases your CSV will contain columns that are not relevant to your fine-tuning project. Selecting "Skip" will leave them out of the import.
You can choose to enter a new field name. By default, this will inherit from the header column of your CSV.
Type will allow you to select between text, number, or pre-defined options.

If you were to import a CSV after your Fields are created, you would see an additional choice for "Existing" which would map your columns to existing fields.

In this example, we will leave all the values at their defaults.

Press "Continue" in the top-right corner.