github-mirrors/elasticsearch
1
0
Fork 0
mirror of https://github.com/elastic/elasticsearch.git synced 2025-04-25 15:47:23 -04:00
Code Issues Projects Releases Packages Wiki Activity

Adds warning to Create inference API page (#118073) (#118091)

Browse source
This commit is contained in:
kosabogi 2024-12-05 17:00:19 +01:00 • committed by GitHub
parent ceeafcc093
commit b449c8e0ec
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
docs/reference/inference/put-inference.asciidoc
View file

@ -10,7 +10,6 @@ Creates an {infer} endpoint to perform an {infer} task.
* For built-in models and models uploaded through Eland, the {infer} APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the {infer} APIs to use these models or if you want to use non-NLP models, use the <<ml-df-trained-models-apis>>. * For built-in models and models uploaded through Eland, the {infer} APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the {infer} APIs to use these models or if you want to use non-NLP models, use the <<ml-df-trained-models-apis>>.
==== ====
[discrete] [discrete]
[[put-inference-api-request]] [[put-inference-api-request]]
==== {api-request-title} ==== {api-request-title}
@ -47,6 +46,14 @@ Refer to the service list in the <<put-inference-api-desc,API description sectio
The create {infer} API enables you to create an {infer} endpoint and configure a {ml} model to perform a specific {infer} task. The create {infer} API enables you to create an {infer} endpoint and configure a {ml} model to perform a specific {infer} task.
[IMPORTANT]
====
* When creating an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
* After creating the endpoint, wait for the model deployment to complete before using it. You can verify the deployment status by using the <<get-trained-models-stats, Get trained model statistics>> API. In the response, look for `"state": "fully_allocated"` and ensure the `"allocation_count"` matches the `"target_allocation_count"`.
* Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
====
The following services are available through the {infer} API. The following services are available through the {infer} API.
You can find the available task types next to the service name. You can find the available task types next to the service name.
Click the links to review the configuration details of the services: Click the links to review the configuration details of the services: