Uploading a dataset is a crucial step in leveraging Artemis Search’s intelligent search capabilities for your specific use case. This guide will walk you through the process of adding a new dataset to your project.

​
Prerequisites

Before you begin, ensure you have:
  1. An active Artemis Search account
  2. A project created in your dashboard
  3. A prepared dataset in the correct format (pandas dataframe saved as a parquet file)

​
Dataset Format Requirements

Your dataset must meet the following criteria:

Dataset Format

  • File type: Pandas dataframe saved as a parquet file
  • Required columns:
    • embedding: OpenAI text-large-3 embeddings of text you want to search through
    • tag: String values associated with each embedding

​
Upload Process

Follow these steps to upload your dataset:
1

Navigate to Your Project

Go to the Project Dashboard and select the project you want to add the dataset to.
2

Open the Datasets Card

Locate the “Datasets” card on your project page.
3

Initiate Upload

Click the “Add Dataset” button at the bottom of the datasets table.
4

Provide Dataset Details

In the popup modal:
  1. Enter a name for your dataset
  2. Click the upload area to select the pandas dataframe saved as a parquet file
5

Confirm and Wait

Click “Upload” and wait for the process to complete. Do not navigate away from the page during this time.
The upload process may take some time depending on the size of your dataset. Ensure you stay on the page until the upload is complete.

​
After Upload

Once your dataset is successfully uploaded:
  1. It will appear in the datasets table on your project page.
  2. You can choose to activate it for use in searches.
  3. The dataset becomes available for management actions like editing or deleting.

​
Next Steps

Now that you’ve uploaded your dataset, learn how to:

Manage Datasets

Activate, edit, or delete your uploaded datasets