From 8055aed1f8b961bfb50a3bb4ceffb05120a10b9d Mon Sep 17 00:00:00 2001
From: "opensearch-trigger-bot[bot]"
 <98922864+opensearch-trigger-bot[bot]@users.noreply.github.com>
Date: Tue, 24 Sep 2024 21:33:57 +0000
Subject: [PATCH] Fix the k-NN train API command for disk based vector search
 (#8369) (#8370)

---
 _search-plugins/knn/disk-based-vector-search.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_search-plugins/knn/disk-based-vector-search.md b/_search-plugins/knn/disk-based-vector-search.md
index 82da30a0ac..dfb9262db5 100644
--- a/_search-plugins/knn/disk-based-vector-search.md
+++ b/_search-plugins/knn/disk-based-vector-search.md
@@ -167,7 +167,7 @@ GET my-vector-index/_search
 For [model-based indexes]({{site.url}}{{site.baseurl}}/search-plugins/knn/approximate-knn/#building-a-k-nn-index-from-a-model), you can specify the `on_disk` parameter in the training request in the same way that you would specify it during index creation. By default, `on_disk` mode will use the [Faiss IVF method]({{site.url}}{{site.baseurl}}/search-plugins/knn/knn-index/#supported-faiss-methods) and a compression level of `32x`. To run the training API, send the following request:
 
 ```json
-POST /_plugins/_knn/models/_train/test-model
+POST /_plugins/_knn/models/test-model/_train
 {
     "training_index": "train-index-name",
     "training_field": "train-field-name",