google.generativeai.embed_content#

Calls the API to create embeddings for content passed in.

google.generativeai.embed_content(
    model: model_types.BaseModelNameOptions,
    content: (content_types.ContentType | Iterable[content_types.ContentType]),
    task_type: (EmbeddingTaskTypeOptions | None) = None,
    title: (str | None) = None,
    output_dimensionality: (int | None) = None,
    client: glm.GenerativeServiceClient = None,
    request_options: (helper_types.RequestOptionsType | None) = None
) -> (text_types.EmbeddingDict | text_types.BatchEmbeddingDict)

Args

model

 
Which [model](https://ai.google.dev/models/gemini#embedding) to

call, as a string or a types.Model.

content

 
Content to embed.

task_type

 
Optional task type for which the embeddings will be used. Can only

be set for models/embedding-001.

title

 
An optional title for the text. Only applicable when task_type is

RETRIEVAL_DOCUMENT.

output_dimensionality

 
Optional reduced dimensionality for the output embeddings. If set,

excessive values from the output embeddings will be truncated from the end.

request_options

 
Options for the request.

Return

Dictionary containing the embedding (list of float values) for the input content.