---
type: api
title: Create an ELSER inference endpoint
description: Create an inference endpoint to perform an inference task with the `elser` service.
url: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch-serverless/operation/operation-inference-put-elser
resource: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch-serverless/operation/operation-inference-put-elser
products:
  - Elasticsearch Serverless
---

# Create an ELSER inference endpoint

deprecated

Availability:

## Paths

- `PUT` `/_inference/{task_type}/{elser_inference_id}`

- [Api key auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch-serverless/authentication#apikeyauth)

#### Path Parameters

- `task_type` (enum ElserTaskType)
  The type of the inference task that the model will perform.
  Values: `sparse_embedding`
- `elser_inference_id` (string Id)
  The unique identifier of the inference endpoint.

## Description

Create an inference endpoint to perform an inference task with the `elser` service.
You can also deploy ELSER by using the Elasticsearch inference integration.

> info
> Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.

The API request will automatically download and deploy the ELSER model if it isn't already downloaded.

> info
> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.

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.

## Required authorization

* Cluster privileges: `manage_inference`

## Query String Parameters

- `timeout` (string Duration · default: 30s)
  Specifies the amount of time to wait for the inference endpoint to be created.

## Request Body

`application/json`

- `chunking_settings` ({} InferenceChunkingSettings) — optional
  The chunking configuration object.
Note that for ELSER endpoints, the max_chunk_size may not exceed `300`.
  - `max_chunk_size` (number · default: 250) — optional
    The maximum size of a chunk in words.
This value cannot be lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).
This value should not exceed the window size for the associated model.
  - `overlap` (number · default: 100) — optional
    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) — optional
    The number of overlapping sentences for chunks.
It is applicable only for a `sentence` chunking strategy.
It can be either `1` or `0`.
  - `separator_group` (string) — optional
    Only applicable to the `recursive` strategy and required when using it.

Sets a predefined list of separators in the saved chunking settings based on the selected text type.
Values can be `markdown` or `plaintext`.

Using this parameter is an alternative to manually specifying a custom `separators` list.
  - `separators` ([] string) — optional
    Only applicable to the `recursive` strategy and required when using it.

A list of strings used as possible split points when chunking text.

Each string can be a plain string or a regular expression (regex) pattern.
The system tries each separator in order to split the text, starting from the first item in the list.

After splitting, it attempts to recombine smaller pieces into larger chunks that stay within
the `max_chunk_size` limit, to reduce the total number of chunks generated.
  - `strategy` (string · default: sentence) — optional
    The chunking strategy: `sentence`, `word`, `none` or `recursive`.

 * If `strategy` is set to `recursive`, you must also specify:

- `max_chunk_size`
- either `separators` or`separator_group`

Learn more about different chunking strategies in the linked documentation.
- `service` (enum ElserServiceType) — required
  The type of service supported for the specified task type. In this case, `elser`.
  Values: `elser`
- `service_settings` ({} ElserServiceSettings) — required
  Settings used to install the inference model. These settings are specific to the `elser` service.
  - `adaptive_allocations` ({} AdaptiveAllocations) — optional
    Adaptive allocations configuration details.
If `enabled` is true, the number of allocations of the model is set based on the current load the process gets.
When the load is high, a new model allocation is automatically created, respecting the value of `max_number_of_allocations` if it's set.
When the load is low, a model allocation is automatically removed, respecting the value of `min_number_of_allocations` if it's set.
If `enabled` is true, do not set the number of allocations manually.
    - `enabled` (boolean · default: false) — optional
      Turn on `adaptive_allocations`.
    - `max_number_of_allocations` (number) — optional
      The maximum number of allocations to scale to.
If set, it must be greater than or equal to `min_number_of_allocations`.
    - `min_number_of_allocations` (number) — optional
      The minimum number of allocations to scale to.
If set, it must be greater than or equal to 0.
If not defined, the deployment scales to 0.
  - `num_allocations` (number) — required
    The total number of allocations this model is assigned across machine learning nodes.
Increasing this value generally increases the throughput.
If adaptive allocations is enabled, do not set this value because it's automatically set.
  - `num_threads` (number) — required
    The number of threads used by each model allocation during inference.
Increasing this value generally increases the speed per inference request.
The inference process is a compute-bound process; `threads_per_allocations` must not exceed the number of available allocated processors per node.
The value must be a power of 2.
The maximum value is 32.

> info
> If you want to optimize your ELSER endpoint for ingest, set the number of threads to 1. If you want to optimize your ELSER endpoint for search, set the number of threads to greater than 1.

## Response

`application/json`

- `chunking_settings` ({} InferenceChunkingSettings)
  The chunking configuration object.
Applies only to the `embedding`, `sparse_embedding` and `text_embedding` task types.
Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
  - `max_chunk_size` (number · default: 250)
    The maximum size of a chunk in words.
This value cannot be lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).
This value should not exceed the window size for the associated model.
  - `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`.
  - `separator_group` (string)
    Only applicable to the `recursive` strategy and required when using it.

Sets a predefined list of separators in the saved chunking settings based on the selected text type.
Values can be `markdown` or `plaintext`.

Using this parameter is an alternative to manually specifying a custom `separators` list.
  - `separators` ([] string)
    Only applicable to the `recursive` strategy and required when using it.

A list of strings used as possible split points when chunking text.

Each string can be a plain string or a regular expression (regex) pattern.
The system tries each separator in order to split the text, starting from the first item in the list.

After splitting, it attempts to recombine smaller pieces into larger chunks that stay within
the `max_chunk_size` limit, to reduce the total number of chunks generated.
  - `strategy` (string · default: sentence)
    The chunking strategy: `sentence`, `word`, `none` or `recursive`.

 * If `strategy` is set to `recursive`, you must also specify:

- `max_chunk_size`
- either `separators` or`separator_group`

Learn more about different chunking strategies in the linked documentation.
- `service` (string)
  The service type
- `service_settings` (ServiceSettings)
  Settings specific to the service
- `task_settings` (TaskSettings)
  Task settings specific to the service and task type
- `inference_id` (string)
  The inference Id
- `task_type` (enum TaskTypeELSER)
  The task type
  Values: `sparse_embedding`
## Code Examples

#### Console

```console
PUT _inference/sparse_embedding/my-elser-model
{
    "service": "elser",
    "service_settings": {
        "num_allocations": 1,
        "num_threads": 1
    }
}
```

#### JavaScript

```javascript
const response = await client.inference.put({
  task_type: "sparse_embedding",
  inference_id: "my-elser-model",
  inference_config: {
    service: "elser",
    service_settings: {
      num_allocations: 1,
      num_threads: 1,
    },
  },
});
```

#### Python

```python
resp = client.inference.put(
    task_type="sparse_embedding",
    inference_id="my-elser-model",
    inference_config={
        "service": "elser",
        "service_settings": {
            "num_allocations": 1,
            "num_threads": 1
        }
    },
)
```

#### curl

```curl
curl -X PUT "$ELASTICSEARCH_URL/_inference/sparse_embedding/my-elser-model" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "elser",
    "service_settings": {
      "num_allocations": 1,
      "num_threads": 1
    }
  }'
```

#### Java

```java
client.inference().put(p -> p
    .inferenceId("my-elser-model")
    .taskType(TaskType.SparseEmbedding)
    .inferenceConfig(i -> i
        .service("elser")
        .serviceSettings(JsonData.fromJson("""
{"num_allocations":1,"num_threads":1}
"""))
    )
);
```

#### C#

```c#
var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "my-elser-model",
        TaskType = TaskType.SparseEmbedding,
        InferenceConfig = new()
        {
            Service = "elser",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "num_allocations": 1,
              "num_threads": 1
            }
            """)
        }
    });
```

#### PHP

```php
$resp = $client->inference()->put([
    "task_type" => "sparse_embedding",
    "inference_id" => "my-elser-model",
    "body" => [
        "service" => "elser",
        "service_settings" => [
            "num_allocations" => 1,
            "num_threads" => 1,
        ],
    ],
]);
```

#### Ruby

```ruby
response = client.inference.put(
  task_type: "sparse_embedding",
  inference_id: "my-elser-model",
  body: {
    "service": "elser",
    "service_settings": {
      "num_allocations": 1,
      "num_threads": 1
    }
  }
)
```

## Response Examples

#### Put elser response example1

A successful response when creating an ELSER inference endpoint.

```json
{
  "inference_id": "my-elser-model",
  "task_type": "sparse_embedding",
  "service": "elser",
  "service_settings": {
    "num_allocations": 1,
    "num_threads": 1
  },
  "task_settings": {}
}
```