For the complete documentation index, see llms.txt. This page is also available as Markdown.

Setting up the app

For the Tonic Textual Snowflake Native App, you set up:

  • A compute pool

  • A warehouse to enable queries

  • To enable the app to detect model-based custom entity types, a

Setting up the compute pools

The compute pools must be specific to Textual.

USE ROLE SYSADMIN;

CREATE COMPUTE POOL IF NOT EXISTS textual_api_pool
  MIN_NODES = 1
  MAX_NODES = 1
  INSTANCE_FAMILY = CPU_X64_XS
  AUTO_RESUME = true
  AUTO_SUSPEND_SECS = 600;
  
CREATE COMPUTE POOL IF NOT EXISTS textual_ml_pool
    MIN_NODES = 1
    MAX_NODES = 1
    INSTANCE_FAMILY = GPU_NV_S
    AUTO_RESUME = true;
    AUTO_SUSPEND_SECS = 600;

Creating a warehouse for Textual to query Snowflake

To run SQL queries against Snowflake tables that the app manages, the app requires a warehouse.

Mounting model-based custom entity types

To be able to use the Snowflake integration to detect model-based custom entity types, you must mount the entity types to a Snowflake stage.

To obtain the entity type files to mount, contact Tonic.ai.

Creating the stage to mount the entity types

To create the stage:

After you create the stage, grant read access to the role that you will use to call the app:

Mounting the entity types

You mount to the stage each model-based custom entity type that you want to use in the Snowflake integration. You request the entity type files from Tonic.ai.

The file structure for the mounted entity types is:

Last updated

Was this helpful?