GPT Columns
Last updated
Last updated
GPT Columns enable you to dynamically generate unique content for each row in your dataset using OpenAI's GPT models. With GPT Columns, you can define a prompt and use liquid templating to reference values from other columns. This setup allows you to send a customized GPT prompt request for each row, with the response automatically written back to your GPT Column.
Automatically generate personalized email content or messages based on customer data.
Generate insights or recommendations from transactional data, such as suggesting complementary products based on purchase history.
Sentiment analysis of email received by sales team from outbound campaign to help with categorization and reporting
Summarize product usage among specific features by “high” or “low” to identify upsell fits and run PLG playbooks
Clean up data by removing special characters from a column
Dataset should have a Unique ID column
You will need your API key to connect OpenAI (ChatGPT). To create a new API key, log into OpenAI and navigate to Dashboard / API keys and generate a new Project API Key.
If you are a video person, watch how to create a GPT column. Otherwise, follow the steps below.
Step 1: Log into your Census account.
Step 2: Navigate to the Datasets tab by clicking on Datasets in the left navigation panel.
Step 3: Choose a dataset where you want to add a new AI-based column. Make sure the Dataset has a Unique ID column assigned
Step 4: Select Enrich & Enhance on your top right corner and choose GPT
Step 5: Connect to OpenAI using your OpenAI API Key and click Next.
Step 6: Create a GPT prompt and fill the column name.
Refer to Sample GPT Prompts for inspiration on GPT based prompts
We recommend you refine your prompt outside Census before saving the prompt for the GPT Columns.
Model Type - you can select from the provided list of GPT based models or manually enter a valid model. Here's a full list of GPT models. We recommend gpt-4o-mini model to limit cost associated with the OpenAI tokens.
The expected output type - there are several optional properties to help you guarantee data quality.
The prompt to run against each row of your data. Your prompt can leverage Liquid templating to reference column values.
Step 7: Hit the Create button and that's it. Census will generate a GPT based column into your dataset.
This step can take several minutes. Behind the scene Census sets up OpenAI as a destination and runs a sync across all your rows in the selected dataset.
The GPT columns refresh every 6 hours and only process new rows.
The results generated by GPT Columns are stored directly in your source warehouse. Census creates a new table within the Census schema, prefixed with DATASET_COLUMN_GPT, containing the GPT Column.
This allows you to not only sync these AI-generated columns to your destination via Census but also explore them further within your warehouse.
GPT Columns are currently supported on Snowflake, Redshift, BigQuery, Databricks, and Postgres with more warehouses coming soon.
Census only sends your prompt to OpenAI. If your prompt includes specific dataset columns via liquid templates, these columns will be included as part of the prompt sent to OpenAI. No other data is shared with OpenAI or any other LLM.
OpenAI does not use the data sent via Census for training its models. For more information, please refer to OpenAI’s data usage policies.
All OpenAI calls are made through secure HTTPS channels, and only successful responses are saved to your dataset.
