清除已训练模型部署缓存 API

POST _ml/trained_models/<deployment_id>/deployment/cache/_clear

需要 manage_ml 集群权限。此权限包含在 machine_learning_admin 内置角色中。

已训练模型部署可能启用了推理缓存。当每个分配的节点处理请求时，它们的响应可能会缓存在该单个节点上。调用此 API 会清除缓存，而无需重新启动部署。

以下示例清除 elastic__distilbert-base-uncased-finetuned-conll03-english 已训练模型的新部署的缓存

resp = client.ml.clear_trained_model_deployment_cache(
    model_id="elastic__distilbert-base-uncased-finetuned-conll03-english",
)
print(resp)

response = client.ml.clear_trained_model_deployment_cache(
  model_id: 'elastic__distilbert-base-uncased-finetuned-conll03-english'
)
puts response

POST _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/deployment/cache/_clear

API 返回以下结果

{
   "cleared": true
}