# Min\_number\_of\_allocations for .elser-2-elasticsearch reverted to 0 and inference failures during bulk indexing

**URL:** <https://discuss.elastic.co/t/min-number-of-allocations-for-elser-2-elasticsearch-reverted-to-0-and-inference-failures-during-bulk-indexing/391400>\
**Category:** Elasticsearch\
**Created:** [November 5, 2026, 4:28am UTC](https://discuss.elastic.co/t/min-number-of-allocations-for-elser-2-elasticsearch-reverted-to-0-and-inference-failures-during-bulk-indexing/391400 "2026-11-05T04:28:16Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![elastic141](https://avatars.discourse-cdn.com/v4/letter/e/3e96dc/32.png) [@elastic141](https://discuss.elastic.co/u/elastic141)\
**Post date:** [November 5, 2026, 4:28am UTC](https://discuss.elastic.co/t/min-number-of-allocations-for-elser-2-elasticsearch-reverted-to-0-and-inference-failures-during-bulk-indexing/391400/1 "2026-11-05T04:28:16Z")

</div>

We are using the preconfigured ELSER inference endpoint `.elser-2-elasticsearch` with a `semantic_text` field.

During a full bulk indexing operation, some documents fail with:

```auto
inference_exception: Exception when running inference id
[.elser-2-elasticsearch] on field [prism_semantic]

```

The entire document fails to index when this occurs.

We previously configured the ELSER deployment with:

```auto
"adaptive_allocations": {
  "enabled": true,
  "min_number_of_allocations": 1
}

```

However we later found that the deployment is back to:

```auto
"adaptive_allocations": {
  "enabled": true,
  "min_number_of_allocations": 0,
  "max_number_of_allocations": 32
}

```

Both GET \_inference/.elser-2-elasticsearch and GET \_ml/trained\_models/.elser-2-elasticsearch/\_stats now show:

```auto
"adaptive_allocations": {
  "enabled": true,
  "min_number_of_allocations": 0,
  "max_number_of_allocations": 32
}

```

Is it expected for the preconfigured `.elser-2-elasticsearch` endpoint to reset/recreate its deployment with `min_number_of_allocations: 0`?

If we need ELSER to remain available during large bulk indexing operations, what is the recommended way to persist `min_number_of_allocations: 1`?

We are using ECH 8.19.12