Sign in

v1

latestOpenAPI 3.0.0Creative Commons Attribution 3.02026-07-132661,4471.5 MB
projects

Embed content with multimodal inputs.

post/v1/{+model}:embedContent

Path parameters

modelstring required

Required. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*

Request body

titlestring

Optional. Deprecated: Please use EmbedContentConfig.title instead. The title for the text.

outputDimensionalityinteger

Optional. Deprecated: Please use EmbedContentConfig.output_dimensionality instead. Reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end.

taskType'UNSPECIFIED' | 'RETRIEVAL_QUERY' | 'RETRIEVAL_DOCUMENT' | 'SEMANTIC_SIMILARITY' | 'CLASSIFICATION' | 'CLUSTERING' | 'QUESTION_ANSWERING' | 'FACT_VERIFICATION' | 'CODE_RETRIEVAL_QUERY'

Optional. Deprecated: Please use EmbedContentConfig.task_type instead. The task type of the embedding.

autoTruncateboolean

Optional. Deprecated: Please use EmbedContentConfig.auto_truncate instead. Whether to silently truncate the input content if it's longer than the maximum sequence length.

Response

Successful response