batch_embeddings

Creates, updates, deletes, gets or lists a batch_embeddings resource.

Overview

Name	batch_embeddings
Type	Resource
Id	gemini.models.batch_embeddings

Fields

The following fields are returned by SELECT queries:

batch_embed_contents

Name	Datatype	Description
▶embeddings	array	Output only. The embeddings for each request, in the same order as provided in the batch request.
▶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
batch_embed_contents	select	modelsId	requests	Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

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
requests	array	Required. Embed requests for the batch. The model in each of these requests must match the model specified BatchEmbedContentsRequest.model.

SELECT examples

batch_embed_contents

Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

Query Shape

SELECT
embeddings,
usageMetadata
FROM gemini.models.batch_embeddings
WHERE modelsId = '{{ modelsId }}' -- required
AND requests = '{{ requests }}'
;

Query Example

SELECT
embeddings
FROM gemini.models.batch_embeddings
WHERE modelsId = 'gemini-embedding-001'
AND requests = '[
  {"model": "models/gemini-embedding-001", "content": {"parts":[{"text":"first passage"}]}},
  {"model": "models/gemini-embedding-001", "content": {"parts":[{"text":"second passage"}]}}
]'
;