put

Documentation

Overview

Create an inference endpoint. When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. After creating the endpoint, wait for the model deployment to complete before using it. To verify the deployment status, use the get trained model statistics API. Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Index

• Variables
• type NewPut
  • func NewPutFunc(tp elastictransport.Interface) NewPut
• type Put
  • func New(tp elastictransport.Interface) *Put
  • func (r *Put) ChunkingSettings(chunkingsettings types.InferenceChunkingSettingsVariant) *Put
  • func (r Put) Do(providedCtx context.Context) (*Response, error)
  • func (r *Put) ErrorTrace(errortrace bool) *Put
  • func (r *Put) FilterPath(filterpaths ...string) *Put
  • func (r *Put) Header(key, value string) *Put
  • func (r *Put) HttpRequest(ctx context.Context) (*http.Request, error)
  • func (r *Put) Human(human bool) *Put
  • func (r Put) Perform(providedCtx context.Context) (*http.Response, error)
  • func (r *Put) Pretty(pretty bool) *Put
  • func (r *Put) Raw(raw io.Reader) *Put
  • func (r *Put) Request(req *Request) *Put
  • func (r *Put) Service(service string) *Put
  • func (r *Put) ServiceSettings(servicesettings json.RawMessage) *Put
  • func (r *Put) TaskSettings(tasksettings json.RawMessage) *Put
  • func (r *Put) TaskType(tasktype string) *Put
• type Request
  • func NewRequest() *Request
• type Response
  • func NewResponse() *Response

Variables

var ErrBuildPath = errors.New("cannot build path, check for missing path parameters")

ErrBuildPath is returned in case of missing parameters within the build of the request.

Types

type NewPut

type NewPut func(inferenceid string) *Put

NewPut type alias for index.

func NewPutFunc

func NewPutFunc(tp elastictransport.Interface) NewPut

NewPutFunc returns a new instance of Put with the provided transport. Used in the index of the library this allows to retrieve every apis in once place.

type Put

type Put struct {
	// contains filtered or unexported fields
}

func New

func New(tp elastictransport.Interface) *Put

Create an inference endpoint. When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. After creating the endpoint, wait for the model deployment to complete before using it. To verify the deployment status, use the get trained model statistics API. Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html

func (*Put) ChunkingSettings

func (r *Put) ChunkingSettings(chunkingsettings types.InferenceChunkingSettingsVariant) *Put

Chunking configuration object API name: chunking_settings

func (Put) Do

func (r Put) Do(providedCtx context.Context) (*Response, error)

Do runs the request through the transport, handle the response and returns a put.Response

func (*Put) ErrorTrace

func (r *Put) ErrorTrace(errortrace bool) *Put

ErrorTrace When set to `true` Elasticsearch will include the full stack trace of errors when they occur. API name: error_trace

func (*Put) FilterPath

func (r *Put) FilterPath(filterpaths ...string) *Put

FilterPath Comma-separated list of filters in dot notation which reduce the response returned by Elasticsearch. API name: filter_path

func (*Put) Header

func (r *Put) Header(key, value string) *Put

Header set a key, value pair in the Put headers map.

func (*Put) HttpRequest

func (r *Put) HttpRequest(ctx context.Context) (*http.Request, error)

HttpRequest returns the http.Request object built from the given parameters.

func (*Put) Human

func (r *Put) Human(human bool) *Put

Human When set to `true` will return statistics in a format suitable for humans. For example `"exists_time": "1h"` for humans and `"eixsts_time_in_millis": 3600000` for computers. When disabled the human readable values will be omitted. This makes sense for responses being consumed only by machines. API name: human

func (Put) Perform

func (r Put) Perform(providedCtx context.Context) (*http.Response, error)

Perform runs the http.Request through the provided transport and returns an http.Response.

func (*Put) Pretty

func (r *Put) Pretty(pretty bool) *Put

Pretty If set to `true` the returned JSON will be "pretty-formatted". Only use this option for debugging only. API name: pretty

func (*Put) Raw

func (r *Put) Raw(raw io.Reader) *Put

Raw takes a json payload as input which is then passed to the http.Request If specified Raw takes precedence on Request method.

func (*Put) Request

func (r *Put) Request(req *Request) *Put

Request allows to set the request property with the appropriate payload.

func (*Put) Service

func (r *Put) Service(service string) *Put

The service type API name: service

func (*Put) ServiceSettings

func (r *Put) ServiceSettings(servicesettings json.RawMessage) *Put

Settings specific to the service API name: service_settings

func (*Put) TaskSettings

func (r *Put) TaskSettings(tasksettings json.RawMessage) *Put

Task settings specific to the service and task type API name: task_settings

func (*Put) TaskType

func (r *Put) TaskType(tasktype string) *Put

TaskType The task type API Name: tasktype

type Request

type Request = types.InferenceEndpoint

Request holds the request body struct for the package put

https://github.com/elastic/elasticsearch-specification/blob/f6a370d0fba975752c644fc730f7c45610e28f36/specification/inference/put/PutRequest.ts#L25-L65

func NewRequest

func NewRequest() *Request

NewRequest returns a Request

type Response

type Response struct {

	// ChunkingSettings Chunking configuration object
	ChunkingSettings *types.InferenceChunkingSettings `json:"chunking_settings,omitempty"`
	// InferenceId The inference Id
	InferenceId string `json:"inference_id"`
	// Service The service type
	Service string `json:"service"`
	// ServiceSettings Settings specific to the service
	ServiceSettings json.RawMessage `json:"service_settings"`
	// TaskSettings Task settings specific to the service and task type
	TaskSettings json.RawMessage `json:"task_settings,omitempty"`
	// TaskType The task type
	TaskType tasktype.TaskType `json:"task_type"`
}

Response holds the response body struct for the package put

https://github.com/elastic/elasticsearch-specification/blob/f6a370d0fba975752c644fc730f7c45610e28f36/specification/inference/put/PutResponse.ts#L22-L24

func NewResponse

func NewResponse() *Response

NewResponse returns a Response