Create an inference endpoint | Elasticsearch API (v8)

Create an inference endpoint Technical preview

PUT /_inference/{inference_id}

Path parameters

inference_id string Required

The inference Id

application/json

Body Required

service string Required

The service type
service_settings object Required

Additional properties are allowed.
task_settings object

Additional properties are allowed.

Responses

200 application/json
Hide response attributes Show response attributes object
- service string Required
  
  The service type
- service_settings object Required
  
  Additional properties are allowed.
- task_settings object
  
  Additional properties are allowed.
- inference_id string Required
  
  The inference Id
- task_type string Required
  
  Values are sparse_embedding, text_embedding, rerank, or completion.

PUT /_inference/{inference_id}

curl \
 -X PUT http://api.example.com/_inference/{inference_id} \
 -H "Content-Type: application/json" \
 -d '{"service":"string","service_settings":{},"task_settings":{}}'

Request examples

{
  "service": "string",
  "service_settings": {},
  "task_settings": {}
}

Response examples (200)

{
  "service": "string",
  "service_settings": {},
  "task_settings": {},
  "inference_id": "string",
  "task_type": "sparse_embedding"
}