Create an inference endpoint | Elasticsearch API documentation

Create an inference endpoint Added in 8.11.0

PUT /_inference/{inference_id}

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.

Path parameters

inference_id string Required

The inference Id

application/json

Body Required

chunking_settings object

Additional properties are allowed.
Hide chunking_settings attributes Show chunking_settings attributes object
- max_chunk_size number
  
  Specifies the maximum size of a chunk in words This value cannot be higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy)
- overlap number
  
  Specifies the number of overlapping words for chunks Only for word chunking strategy This value cannot be higher than the half of max_chunk_size
- sentence_overlap number
  
  Specifies the number of overlapping sentences for chunks Only for sentence chunking strategy It can be either 1 or 0
- strategy string
  
  Specifies the chunking strategy It could be either sentence or word
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
- Additional properties are allowed.
  
  Hide attributes Show attributes object
  
  max_chunk_size number
  
  Specifies the maximum size of a chunk in words This value cannot be higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy)
  
  overlap number
  
  Specifies the number of overlapping words for chunks Only for word chunking strategy This value cannot be higher than the half of max_chunk_size
  
  sentence_overlap number
  
  Specifies the number of overlapping sentences for chunks Only for sentence chunking strategy It can be either 1 or 0
  
  strategy string
  
  Specifies the chunking strategy It could be either sentence or word
- 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 \
 --request PUT http://api.example.com/_inference/{inference_id} \
 --header "Authorization: $API_KEY" \
 --header "Content-Type: application/json" \
 --data '{"":{"max_chunk_size":42.0,"overlap":42.0,"sentence_overlap":42.0,"strategy":"string"},"service":"string","service_settings":{},"task_settings":{}}'

Request examples

{
  "": {
    "max_chunk_size": 42.0,
    "overlap": 42.0,
    "sentence_overlap": 42.0,
    "strategy": "string"
  },
  "service": "string",
  "service_settings": {},
  "task_settings": {}
}

Response examples (200)

{
  "": {
    "max_chunk_size": 42.0,
    "overlap": 42.0,
    "sentence_overlap": 42.0,
    "strategy": "string"
  },
  "service": "string",
  "service_settings": {},
  "task_settings": {},
  "inference_id": "string",
  "task_type": "sparse_embedding"
}