Perform dense embedding inference on the service

POST /_inference/embedding/{inference_id}

Copy endpoint

Parameters

Name	Type
`inference_id` required The inference Id	type TypesId = string

Name	Type
`timeout` Specifies the amount of time to wait for the inference request to complete.	type TypesDuration = string \| "-1" \| "0"

application/json required

interface InferenceTypesRequestEmbedding {
input:

InferenceTypesEmbeddingInput

Inference input. Either a string, an array of strings, a content object, or an array of content objects.

type InferenceTypesEmbeddingInput = InferenceTypesEmbeddingStringInput | InferenceTypesEmbeddingContentInput

;
input_type?: string;
task_settings?:

InferenceTypesTaskSettings

interface InferenceTypesTaskSettings {}

;
}

200 application/json

interface InferenceTypesEmbeddingInferenceResult {
embeddings_bytes?:

InferenceTypesDenseEmbeddingByteResult

The dense embedding result object for byte representation

interface InferenceTypesDenseEmbeddingByteResult {
embedding: InferenceTypesDenseByteVector;
}

[];
embeddings_bits?:

InferenceTypesDenseEmbeddingByteResult

The dense embedding result object for byte representation

interface InferenceTypesDenseEmbeddingByteResult {
embedding: InferenceTypesDenseByteVector;
}

[];
embeddings?:

InferenceTypesDenseEmbeddingResult

The dense embedding result object for float representation

interface InferenceTypesDenseEmbeddingResult {
embedding: InferenceTypesDenseVector;
}

[];
}