Create a custom inference endpoint

Auth

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.

Note

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.

Required authorization

Cluster privileges manage_inference

Path parameters

task_type enum required

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

Values: text_embedding sparse_embedding rerank completion
custom_inference_id string required

The unique identifier of the inference endpoint.

Request body

chunking_settings object

The chunking configuration object.

Reference
max_chunk_size number · default: 250

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 · default: 100

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.

sentence_overlap number · default: 1

The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.

strategy string · default: sentence

The chunking strategy: sentence or word.

service enum required

The type of service supported for the specified task type. In this case, custom.

Values: custom
service_settings object required

Settings used to install the inference model. These settings are specific to the custom service.

batch_size number

Specifies the batch size used for the semantic_text field. If the field is not provided, the default is 10. The batch size is the maximum number of inputs in a single request to the upstream service. The chunk within the batch are controlled by the selected chunking strategy for the semantic_text field.

Reference
headers object

Specifies the HTTP header parameters – such as Authentication or Content-Type – that are required to access the custom service. For example:

"headers":{
  "Authorization": "Bearer ${api_key}",
  "Content-Type": "application/json;charset=utf-8"
}
input_type object

Specifies the input type translation values that are used to replace the ${input_type} template in the request body. For example:

"input_type": {
  "translation": {
    "ingest": "do_ingest",
    "search": "do_search"
  },
  "default": "a_default"
},

If the subsequent inference requests come from a search context, the search key will be used and the template will be replaced with do_search. If it comes from the ingest context do_ingest is used. If it's a different context that is not specified, the default value will be used. If no default is specified an empty string is used. translation can be:

  • classification
  • clustering
  • ingest
  • search
query_parameters object

Specifies the query parameters as a list of tuples. The arrays inside the query_parameters must have two items, a key and a value. For example:

"query_parameters":[
  ["param_key", "some_value"],
  ["param_key", "another_value"],
  ["other_key", "other_value"]
]

If the base url is https://www.elastic.co it results in: https://www.elastic.co?param_key=some_value&param_key=another_value&other_key=other_value.

request object required

The request configuration object.

content string required

The body structure of the request. It requires passing in the string-escaped result of the JSON format HTTP request body. For example:

"request": "{\"input\":${input}}"
Note

The content string needs to be a single line except when using the Kibana console.

response object required

The response configuration object.

json_parser object required

Specifies the JSON parser that is used to parse the response from the custom service. Different task types require different json_parser parameters. For example:

# text_embedding
# For a response like this:

{
 "object": "list",
 "data": [
     {
       "object": "embedding",
       "index": 0,
       "embedding": [
           0.014539449,
           -0.015288644
       ]
     }
 ],
 "model": "text-embedding-ada-002-v2",
 "usage": {
     "prompt_tokens": 8,
     "total_tokens": 8
 }
}

# the json_parser definition should look like this:

"response":{
  "json_parser":{
    "text_embeddings":"$.data[*].embedding[*]"
  }
}

# sparse_embedding
# For a response like this:

{
  "request_id": "75C50B5B-E79E-4930-****-F48DBB392231",
  "latency": 22,
  "usage": {
     "token_count": 11
  },
  "result": {
     "sparse_embeddings": [
        {
          "index": 0,
          "embedding": [
            {
              "token_id": 6,
              "weight": 0.101
            },
            {
              "token_id": 163040,
              "weight": 0.28417
            }
          ]
        }
     ]
  }
}

# the json_parser definition should look like this:

"response":{
  "json_parser":{
    "token_path":"$.result.sparse_embeddings[*].embedding[*].token_id",
    "weight_path":"$.result.sparse_embeddings[*].embedding[*].weight"
  }
}

# rerank
# For a response like this:

{
  "results": [
    {
      "index": 3,
      "relevance_score": 0.999071,
      "document": "abc"
    },
    {
      "index": 4,
      "relevance_score": 0.7867867,
      "document": "123"
    },
    {
      "index": 0,
      "relevance_score": 0.32713068,
      "document": "super"
    }
  ],
}

# the json_parser definition should look like this:

"response":{
  "json_parser":{
    "reranked_index":"$.result.scores[*].index",
    "relevance_score":"$.result.scores[*].score",
    "document_text":"xxx"
  }
}

# completion
# For a response like this:

{
 "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
 "object": "chat.completion",
 "created": 1741569952,
 "model": "gpt-4.1-2025-04-14",
 "choices": [
   {
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I assist you today?",
      "refusal": null,
      "annotations": []
    },
    "logprobs": null,
    "finish_reason": "stop"
  }
 ]
}

# the json_parser definition should look like this:

"response":{
  "json_parser":{
    "completion_result":"$.choices[*].message.content"
  }
}
  1. optional
  2. optional
secret_parameters object required

Specifies secret parameters, like api_key or api_token, that are required to access the custom service. For example:

"secret_parameters":{
  "api_key":"<api_key>"
}
url string

The URL endpoint to use for the requests.

task_settings object

Settings to configure the inference task. These settings are specific to the task type you specified.

parameters object

Specifies parameters that are required to run the custom service. The parameters depend on the model your custom service uses. For example:

"task_settings":{
  "parameters":{
    "input_type":"query",
    "return_token":true
  }
}
Warning

The task_settings.parameters cannot contain the same keys as secret_parameters. If they do, an error will be returned. This applies to PUT requests and POST requests.

Response

application/json
chunking_settings object

Chunking configuration object

max_chunk_size number · default: 250

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 · default: 100

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.

sentence_overlap number · default: 1

The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.

strategy string · default: sentence

The chunking strategy: sentence or word.

service string required

The service type

service_settings object required

Settings specific to the service

task_settings object

Task settings specific to the service and task type

inference_id string required

The inference Id

task_type enum required

The task type

Values: text_embedding sparse_embedding rerank completion