Skip to content

Cortex Multi Prompt

Public preview

Editions

Production use of this feature is available for specific editions only. Contact our sales team for more information.

Cortex Multi Prompt is a transformation component that uses Snowflake Cortex to receive a prompt and then generate a response (a completion) using your chosen supported language model.

Cortex Multi Prompt is an advancement of the Cortex Completions component, with the functionality for users to add multiple user prompts in the Outputs parameter. With Multi Prompt, you can send multiple queries to your language model via Cortex Completions for the same dataset, without having to write a complex user prompt.

To learn more about Snowflake Cortex, such as availability, usage quotas, managing costs, and more, visit Large Language Model (LLM) Functions (Snowflake Cortex).


Snowflake roles

You must use a Snowflake role that has been granted the SNOWFLAKE.CORTEX_USER database role. Read Required Privileges to learn more about granting this privilege.


Properties

Model = drop-down

Select a language model from the drop-down menu. Review the Snowflake documentation for supported models, costs, and quotas.

Read Availability for details about which models are available in which regions.


User Prompt = text editor

A plain-text prompt provided by the user. This prompt lets the user provide basic instructions and background information on the data.


Inputs = column editor

Select the source columns to feed as input to the model.

  • Column Name: A column from the input table.
  • Descriptive Name (optional): An alternate descriptive name to better contextualize the column. Recommended if your column names are low-context.

Outputs = column editor

Define the parameters for the output data including what each output column should be named and what prompt should be used to query the language model about the input data.

  • Column Name: The name of a column that will hold responses to the corresponding prompt.
  • Prompt: A prompt to the language model about the input data.

For example, if your input data was a table of flights and vacation data, you might set one column name as carbon_footprint and then set the corresponding prompt as "What is the estimated carbon footprint in tons per passenger?".


Include Input Columns = boolean

  • Yes: Outputs both your source input columns and the new completion columns. This will also include those input columns not selected in Inputs.
  • No: Only outputs the new completion columns.

Snowflake Databricks Amazon Redshift