Categories:

String & binary functions (AI Functions)

EMBED_TEXT_768 (SNOWFLAKE.CORTEX)

Notice

This page is provided for backward compatibility. For new use cases, start with %aisql-new-func-link%, which is the canonical surface going forward. This legacy function will be deprecated by the end of 2026.

Creates a vector embedding of 768 dimensions from English-language text.

Syntax

SNOWFLAKE.CORTEX.EMBED_TEXT_768( <model>, <text> )

Arguments

model

A string specifying the vector embedding model to be used to generate the embedding. This must be one of the following values.

  • snowflake-arctic-embed-m-v1.5
  • snowflake-arctic-embed-m
  • e5-base-v2

Supported models might have different costs.

text

The text for which an embedding should be calculated.

Returns

A vector embedding of type VECTOR.

Access control requirements

You must use a role that has been granted the SNOWFLAKE.CORTEX_USER database role or the SNOWFLAKE.CORTEX_EMBED_USER database role to call this function. See Cortex LLM privileges for more information on granting one of these privileges.

You must also have the USAGE privilege on the SNOWFLAKE.CORTEX schema to call this function.

Refer to Snowflake AI and ML.