Create a Cohere inference endpoint

PUT /_inference/{task_type}/{cohere_inference_id}

Copy endpoint

Create an inference endpoint to perform an inference task with the cohere service.

Required authorization

Cluster privileges: manage_inference

Parameters

path Path Parameters

Name	Type
`task_type` required The type of the inference task that the model will perform.	type InferenceTypesCohereTaskType = "completion" \| "rerank" \| "text_embedding"
`cohere_inference_id` required The unique identifier of the inference endpoint.	type TypesId = string

query Query Parameters

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

Request Body

application/json required

{
chunking_settings?:

InferenceTypesInferenceChunkingSettings

Chunking configuration object

interface InferenceTypesInferenceChunkingSettings {
max_chunk_size?: number;
overlap?: number;
sentence_overlap?: number;
separator_group?: string;
separators?: string[];
strategy?: string;
}

;
service:

InferenceTypesCohereServiceType

type InferenceTypesCohereServiceType = "cohere"

;
service_settings:

InferenceTypesCohereServiceSettings

interface InferenceTypesCohereServiceSettings {
api_key: string;
embedding_type?: InferenceTypesCohereEmbeddingType;
model_id: string;
rate_limit?: InferenceTypesRateLimitSetting;
similarity?: InferenceTypesCohereSimilarityType;
}

;
task_settings?:

InferenceTypesCohereTaskSettings

interface InferenceTypesCohereTaskSettings {
input_type: InferenceTypesCohereInputType;
return_documents?: boolean;
top_n?: number;
truncate?: InferenceTypesCohereTruncateType;
}

;
}

Responses

200 application/json

type InferenceTypesInferenceEndpointInfoCohere = interface InferenceTypesInferenceEndpoint {
chunking_settings?:

InferenceTypesInferenceChunkingSettings

Chunking configuration object

interface InferenceTypesInferenceChunkingSettings {
max_chunk_size?: number;
overlap?: number;
sentence_overlap?: number;
separator_group?: string;
separators?: string[];
strategy?: string;
}

;
service: string;
service_settings:

InferenceTypesServiceSettings

interface InferenceTypesServiceSettings {}

;
task_settings?:

InferenceTypesTaskSettings

interface InferenceTypesTaskSettings {}

;
} & { inference_id: string;task_type:

InferenceTypesTaskTypeCohere

type InferenceTypesTaskTypeCohere = "text_embedding" | "rerank" | "completion"

; }