# Inference process generates pytorch error

**URL:** <https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165>\
**Category:** Elastic Search\
**Created:** [June 10, 2024, 2:43pm UTC](https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165 "2024-06-10T14:43:24Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![thoms](https://avatars.discourse-cdn.com/v4/letter/t/46a35a/32.png) [@thoms](https://discuss.elastic.co/u/thoms)\
**Post date:** [June 10, 2024, 2:43pm UTC](https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165/1 "2024-06-10T14:43:24Z")

</div>

Hi,  
I'm using the .multilingual-e5-small\_linux-x86\_64 model as part of a hybrid search query. Most of the time it works fine but it randomly fails giving the following notification:

```auto
 Inference process [.multilingual-e5-small_linux-x86_64] failed due to [[.multilingual-e5-small_linux-x86_64] pytorch_inference/2426 process stopped unexpectedly: ]. 
This is the [3] failure in 24 hours, and the process will be restarted.

```

And sometimes when it happens too often it is not restarted:

`[.multilingual-e5-small_linux-x86_64] inference process failed after [4] starts in 24 hours, not restarting again.`

Is there any way I can find more information about what causes the error?

---

<div class="post-metadata">

**Author:** ![Alex\_Salgado-Elastic](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/alex_salgado-elastic/32/103081_2.png) [@Alex\_Salgado-Elastic](https://discuss.elastic.co/u/Alex_Salgado-Elastic)\
**Post date:** [June 10, 2024, 3:18pm UTC](https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165/2 "2024-06-10T15:18:59Z")

</div>

> [@thoms](#):
>
> Hi,  
> I'm using the .multilingual-e5-small\_linux-x86\_64 model as part of a hybrid search query. Most of the time it works fine but it randomly fails giving the following notification:
> 
> ```auto
> Inference process [.multilingual-e5-small_linux-x86_64] failed due to [[.multilingual-e5-small_linux-x86_64] pytorch_inference/2426 process stopped unexpectedly: ]. 
> This is the [3] failure in 24 hours, and the process will be restarted.
> 
> ```
> 
> And sometimes when it happens too often it is not restarted:
> 
> `[.multilingual-e5-small_linux-x86_64] inference process failed after [4] starts in 24 hours, not restarting again.`
> 
> Is there any way I can find more information about what causes the error?

How are you using this model within the stack (pipeline, ingestion, eland)? On-premise or cloud version?

---

<div class="post-metadata">

**Author:** ![thoms](https://avatars.discourse-cdn.com/v4/letter/t/46a35a/32.png) [@thoms](https://discuss.elastic.co/u/thoms)\
**Post date:** [June 10, 2024, 6:57pm UTC](https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165/3 "2024-06-10T18:57:03Z")

</div>

It's hosted on Azure cloud.  
The model is used when importing documents through an ingestion pipeline using Logstash:

```auto
    "inference": {
      "model_id": ".multilingual-e5-small_linux-x86_64",
      "field_map": {
        "My.Description": "text_field"
      },
      "target_field": "text_embedding"
    }

```

And the when calculating the embeddings for the text to be used in the knn part of the search. HTTP post to "/\_ml/trained\_models/.multilingual-e5-small\_linux-x86\_64/deployment/\_infer"

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [July 8, 2024, 6:57pm UTC](https://discuss.elastic.co/t/inference-process-generates-pytorch-error/361165/4 "2024-07-08T18:57:52Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.