embeddings

Creates, updates, deletes, gets or lists an embeddings resource.

Overview

Name	embeddings
Type	Resource
Id	gemini.models.embeddings

Fields

The following fields are returned by SELECT queries:

embed_content

Name	Datatype	Description
▶embedding	object	Output only. The embedding generated from the input content.
▶usageMetadata	object	Output only. The usage metadata for the request.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
embed_content	select	modelsId	content, taskType, title, model, embedContentConfig, outputDimensionality	Generates a text embedding vector from the input Content using the specified Gemini Embedding model.
async_batch_embed_content	exec	modelsId		Enqueues a batch of EmbedContent requests for batch processing. We have a BatchEmbedContents handler in GenerativeService, but it was synchronized. So we name this one to be Async to avoid confusion.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
modelsId	string
content	object	The base structured datatype containing multi-part content of a message. A Content includes a role field designating the producer of the Content and a parts field containing multi-part data that contains the content of the message turn.
embedContentConfig	object	Configurations for the EmbedContent request.
model	string	Required. The model's resource name. This serves as an ID for the Model to use. This name should match a model name returned by the ListModels method. Format: models/{model}
outputDimensionality	integer	Optional. Deprecated: Please use EmbedContentConfig.output_dimensionality instead. Optional reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end. Supported by newer models since 2024 only. You cannot set this value if using the earlier model (models/embedding-001).
taskType	string	Optional. Deprecated: Please use EmbedContentConfig.task_type instead. Optional task type for which the embeddings will be used. Not supported on earlier models (models/embedding-001).
title	string	Optional. Deprecated: Please use EmbedContentConfig.title instead. An optional title for the text. Only applicable when TaskType is RETRIEVAL_DOCUMENT. Note: Specifying a title for RETRIEVAL_DOCUMENT provides better quality embeddings for retrieval.

SELECT examples

embed_content

Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

Query Shape

SELECT
embedding,
usageMetadata
FROM gemini.models.embeddings
WHERE modelsId = '{{ modelsId }}' -- required
AND content = '{{ content }}'
AND taskType = '{{ taskType }}'
AND title = '{{ title }}'
AND model = '{{ model }}'
AND embedContentConfig = '{{ embedContentConfig }}'
AND outputDimensionality = '{{ outputDimensionality }}'
;

Query Example

SELECT
JSON_EXTRACT(embedding, '$.values[0]') AS first_dimension
FROM gemini.models.embeddings
WHERE modelsId = 'gemini-embedding-001'
AND content = '{"parts":[{"text":"stackql lets you query cloud APIs with SQL"}]}'
;

Lifecycle Methods

async_batch_embed_content

Enqueues a batch of EmbedContent requests for batch processing. We have a BatchEmbedContents handler in GenerativeService, but it was synchronized. So we name this one to be Async to avoid confusion.

EXEC gemini.models.embeddings.async_batch_embed_content 
@modelsId='{{ modelsId }}' --required
@@json=
'{
"batch": "{{ batch }}"
}'
;