Skip to main content
Generates a vector embedding for the provided input text using an embedding model and returns it as an ARRAY(DOUBLE). Provide the model identifier, the plain-text input in INPUT_TEXT, and a LOCATION that holds AWS Bedrock credentials. Optionally specify the embedding DIMENSIONS and whether to return NULL on errors. For setup guidance and end-to-end examples, see Getting started with AI.
Initially, this function uses Amazon Bedrock as its backend. The LOCATION must reference a Bedrock LOCATION. For now, the only supported model is Amazon Titan Embeddings v2 for text: the MODEL must be 'amazon.titan-embed-text-v2:0'.

​
Syntax

AI_EMBED_TEXT(
  MODEL => <model_name>,
  INPUT_TEXT => <input_text>,
  [ DIMENSIONS => <num_dimensions> ],
  LOCATION => <location>,
  [ NULL_ON_ERROR => <bool> ]
)

​
Parameters

ParameterDescriptionSupported input types
MODELThe embedding model to invoke. For now, must be 'amazon.titan-embed-text-v2:0'. The value is forwarded to Bedrock without further validation.TEXT
INPUT_TEXTThe plain-text content to embed.TEXT
DIMENSIONSOptional. The number of dimensions for the generated embedding. For 'amazon.titan-embed-text-v2:0', must be one of 1024, 512, or 256. Defaults to the model’s default dimension if omitted.INTEGER
LOCATIONThe name of the LOCATION to use for AWS credentials. Must be a literal constant. See CREATE LOCATION (Amazon Bedrock).TEXT
NULL_ON_ERROROptional. Whether to return NULL instead of raising an error when a Bedrock invocation error occurs. Default FALSE. Must be a literal constant.BOOL

​
Return type

ARRAY(DOUBLE)
  • Returns the model’s generated embedding vector.
  • If INPUT_TEXT is NULL, the function returns NULL.

​
LLM token budget

Queries executed with AI_EMBED_TEXT count towards your account’s daily LLM token budget. If your account exceeds its allotted token budget, invocations of AI_EMBED_TEXT will fail until the budget is increased or the daily limit resets. For details on setting and monitoring your token budget, see Set your LLM token budget and Check your LLM token quota usage.
LLM token budget accounting is not available in Firebolt Core.

​
Example

SELECT AI_EMBED_TEXT(
    MODEL => 'amazon.titan-embed-text-v2:0',
    INPUT_TEXT => 'lightning fast analytics',
    DIMENSIONS => 256,
    LOCATION => 'my_bedrock_location'
);
Returns (example): 
[0.12341234, 0.754376, 0.98763459, …]