Create a DeepSeek inference endpoint | Elasticsearch Serverless API documentation

Create a DeepSeek inference endpoint Generally available

PUT /_inference/{task_type}/{deepseek_inference_id}

Api key auth

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

Required authorization

Cluster privileges: manage_inference

Path parameters

task_type string

The type of the inference task that the model will perform.

Values are completion or chat_completion.
deepseek_inference_id string Required

The unique identifier of the inference endpoint.

application/json

Body

chunking_settings object

Chunking configuration object
Hide chunking_settings attributes Show chunking_settings attributes object
- max_chunk_size number
  
  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).
  
  Default value is 250.
- overlap number
  
  The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.
  
  Default value is 100.
- sentence_overlap number
  
  The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.
  
  Default value is 1.
- strategy string
  
  The chunking strategy: sentence or word.
  
  Default value is sentence.
service string Required

Value is deepseek.
service_settings object Required
Hide service_settings attributes Show service_settings attributes object
- api_key string Required
  
  A valid API key for your DeepSeek account. You can find or create your DeepSeek API keys on the DeepSeek API key page.
  
  IMPORTANT: You need to provide the API key only once, during the inference model creation. The get inference endpoint API does not retrieve your API key. After creating the inference model, you cannot change the associated API key. If you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.
  
  External documentation
- model_id string Required
  
  For a completion or chat_completion task, the name of the model to use for the inference task.
  
  For the available completion and chat_completion models, refer to the DeepSeek Models & Pricing docs.
- url string
  
  The URL endpoint to use for the requests. Defaults to https://api.deepseek.com/chat/completions.

Responses

200 application/json
Hide response attributes Show response attributes object
- chunking_settings object
  
  Chunking configuration object
  
  Hide chunking_settings attributes Show chunking_settings attributes object
  
  max_chunk_size number
  
  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).
  
  Default value is 250.
  
  overlap number
  
  The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.
  
  Default value is 100.
  
  sentence_overlap number
  
  The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.
  
  Default value is 1.
  
  strategy string
  
  The chunking strategy: sentence or word.
  
  Default value is sentence.
- service string Required
  
  The service type
- service_settings object Required
- task_settings object
- inference_id string Required
  
  The inference Id
- task_type string Required
  
  Values are completion or chat_completion.

PUT /_inference/{task_type}/{deepseek_inference_id}

curl \
 --request PUT 'http://api.example.com/_inference/{task_type}/{deepseek_inference_id}' \
 --header "Authorization: $API_KEY" \
 --header "Content-Type: application/json" \
 --data '{"chunking_settings":{"max_chunk_size":250,"overlap":100,"sentence_overlap":1,"strategy":"sentence"},"service":"deepseek","service_settings":{"api_key":"string","model_id":"string","url":"string"}}'