The highest tagged major version is
Documentation
¶
Overview ¶
Create a custom inference endpoint.
The custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations. The custom service gives you the ability to define the headers, url, query parameters, request body, and secrets. The custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key. Templates are portions of a string that start with `${` and end with `}`. The parameters `secret_parameters` and `task_settings` are checked for keys for template replacement. Template replacement is supported in the `request`, `headers`, `url`, and `query_parameters`. If the definition (key) is not found for a template, an error message is returned. In case of an endpoint definition like the following: ``` PUT _inference/text_embedding/test-text-embedding
{
"service": "custom",
"service_settings": {
"secret_parameters": {
"api_key": "<some api key>"
},
"url": "...endpoints.huggingface.cloud/v1/embeddings",
"headers": {
"Authorization": "Bearer ${api_key}",
"Content-Type": "application/json"
},
"request": "{\"input\": ${input}}",
"response": {
"json_parser": {
"text_embeddings":"$.data[*].embedding[*]"
}
}
}
}
``` To replace `${api_key}` the `secret_parameters` and `task_settings` are checked for a key named `api_key`.
> info > Templates should not be surrounded by quotes.
Pre-defined templates: * `${input}` refers to the array of input strings that comes from the `input` field of the subsequent inference requests. * `${input_type}` refers to the input type translation values. * `${query}` refers to the query field used specifically for reranking tasks. * `${top_n}` refers to the `top_n` field available when performing rerank requests. * `${return_documents}` refers to the `return_documents` field available when performing rerank requests.
Index ¶
- Variables
- type NewPutCustom
- type PutCustom
- func (r *PutCustom) ChunkingSettings(chunkingsettings *types.InferenceChunkingSettings) *PutCustom
- func (r PutCustom) Do(providedCtx context.Context) (*Response, error)
- func (r *PutCustom) ErrorTrace(errortrace bool) *PutCustom
- func (r *PutCustom) FilterPath(filterpaths ...string) *PutCustom
- func (r *PutCustom) Header(key, value string) *PutCustom
- func (r *PutCustom) HttpRequest(ctx context.Context) (*http.Request, error)
- func (r *PutCustom) Human(human bool) *PutCustom
- func (r PutCustom) Perform(providedCtx context.Context) (*http.Response, error)
- func (r *PutCustom) Pretty(pretty bool) *PutCustom
- func (r *PutCustom) Raw(raw io.Reader) *PutCustom
- func (r *PutCustom) Request(req *Request) *PutCustom
- func (r *PutCustom) Service(service customservicetype.CustomServiceType) *PutCustom
- func (r *PutCustom) ServiceSettings(servicesettings *types.CustomServiceSettings) *PutCustom
- func (r *PutCustom) TaskSettings(tasksettings *types.CustomTaskSettings) *PutCustom
- type Request
- type Response
Constants ¶
This section is empty.
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.
Functions ¶
This section is empty.
Types ¶
type NewPutCustom ¶
NewPutCustom type alias for index.
func NewPutCustomFunc ¶
func NewPutCustomFunc(tp elastictransport.Interface) NewPutCustom
NewPutCustomFunc returns a new instance of PutCustom with the provided transport. Used in the index of the library this allows to retrieve every apis in once place.
type PutCustom ¶
type PutCustom struct {
// contains filtered or unexported fields
}
func New ¶
func New(tp elastictransport.Interface) *PutCustom
Create a custom inference endpoint.
The custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations. The custom service gives you the ability to define the headers, url, query parameters, request body, and secrets. The custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key. Templates are portions of a string that start with `${` and end with `}`. The parameters `secret_parameters` and `task_settings` are checked for keys for template replacement. Template replacement is supported in the `request`, `headers`, `url`, and `query_parameters`. If the definition (key) is not found for a template, an error message is returned. In case of an endpoint definition like the following: ``` PUT _inference/text_embedding/test-text-embedding
{
"service": "custom",
"service_settings": {
"secret_parameters": {
"api_key": "<some api key>"
},
"url": "...endpoints.huggingface.cloud/v1/embeddings",
"headers": {
"Authorization": "Bearer ${api_key}",
"Content-Type": "application/json"
},
"request": "{\"input\": ${input}}",
"response": {
"json_parser": {
"text_embeddings":"$.data[*].embedding[*]"
}
}
}
}
``` To replace `${api_key}` the `secret_parameters` and `task_settings` are checked for a key named `api_key`.
> info > Templates should not be surrounded by quotes.
Pre-defined templates: * `${input}` refers to the array of input strings that comes from the `input` field of the subsequent inference requests. * `${input_type}` refers to the input type translation values. * `${query}` refers to the query field used specifically for reranking tasks. * `${top_n}` refers to the `top_n` field available when performing rerank requests. * `${return_documents}` refers to the `return_documents` field available when performing rerank requests.
https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-custom
func (*PutCustom) ChunkingSettings ¶
func (r *PutCustom) ChunkingSettings(chunkingsettings *types.InferenceChunkingSettings) *PutCustom
ChunkingSettings The chunking configuration object. API name: chunking_settings
func (PutCustom) Do ¶
Do runs the request through the transport, handle the response and returns a putcustom.Response
func (*PutCustom) ErrorTrace ¶
ErrorTrace When set to `true` Elasticsearch will include the full stack trace of errors when they occur. API name: error_trace
func (*PutCustom) FilterPath ¶
FilterPath Comma-separated list of filters in dot notation which reduce the response returned by Elasticsearch. API name: filter_path
func (*PutCustom) HttpRequest ¶
HttpRequest returns the http.Request object built from the given parameters.
func (*PutCustom) Human ¶
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 (PutCustom) Perform ¶
Perform runs the http.Request through the provided transport and returns an http.Response.
func (*PutCustom) Pretty ¶
Pretty If set to `true` the returned JSON will be "pretty-formatted". Only use this option for debugging only. API name: pretty
func (*PutCustom) Raw ¶
Raw takes a json payload as input which is then passed to the http.Request If specified Raw takes precedence on Request method.
func (*PutCustom) Request ¶
Request allows to set the request property with the appropriate payload.
func (*PutCustom) Service ¶
func (r *PutCustom) Service(service customservicetype.CustomServiceType) *PutCustom
Service The type of service supported for the specified task type. In this case, `custom`. API name: service
func (*PutCustom) ServiceSettings ¶
func (r *PutCustom) ServiceSettings(servicesettings *types.CustomServiceSettings) *PutCustom
ServiceSettings Settings used to install the inference model. These settings are specific to the `custom` service. API name: service_settings
func (*PutCustom) TaskSettings ¶
func (r *PutCustom) TaskSettings(tasksettings *types.CustomTaskSettings) *PutCustom
TaskSettings Settings to configure the inference task. These settings are specific to the task type you specified. API name: task_settings
type Request ¶
type Request struct {
// ChunkingSettings The chunking configuration object.
ChunkingSettings *types.InferenceChunkingSettings `json:"chunking_settings,omitempty"`
// Service The type of service supported for the specified task type. In this case,
// `custom`.
Service customservicetype.CustomServiceType `json:"service"`
// ServiceSettings Settings used to install the inference model.
// These settings are specific to the `custom` service.
ServiceSettings types.CustomServiceSettings `json:"service_settings"`
// TaskSettings Settings to configure the inference task.
// These settings are specific to the task type you specified.
TaskSettings *types.CustomTaskSettings `json:"task_settings,omitempty"`
}
Request holds the request body struct for the package putcustom
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 tasktypecustom.TaskTypeCustom `json:"task_type"`
}
Response holds the response body struct for the package putcustom
Source Files