diff --git a/docs/2-search/3-test-search.mdx b/docs/2-search/3-test-search.mdx
index f04399a5..b931ba09 100644
--- a/docs/2-search/3-test-search.mdx
+++ b/docs/2-search/3-test-search.mdx
@@ -19,9 +19,9 @@ and look at the results you get.
 <Screenshot src="img/screenshots/2-search/3-test-search/2-search-tester.png" alt="The Search Tester" url="https://cloud.mongodb.com" />
 
 You can see that you get a list of books back including:
-* High-Flavor, Low-Fat Vegetarian _Cooking_
-* _Cooking_ Secrets of the CIA: Favorite Recipes from the Culinary Institu…
+* Pennsylvania Dutch _Cooking_: A Mennonite Community Cookbook
 * Semi-Homemade _Cooking_: Quick, Marvelous Meals and Nothing is Made from…
+* Cookin' Cajun _Cooking_ School Cookbook - Creole and Cajun Cuisine from …
 
 All those results match the word _cooking_. Notice how capitalization doesn't matter. Neither does the placement of the word in the title. The search index is smart enough to find the word _cooking_ in all those titles.
 
diff --git a/docs/7-vector-search/9-filtering.mdx b/docs/7-vector-search/9-filtering.mdx
index ccbf6bab..bf0842e8 100644
--- a/docs/7-vector-search/9-filtering.mdx
+++ b/docs/7-vector-search/9-filtering.mdx
@@ -48,30 +48,28 @@ In this case, we already have our index and we're going to edit it in the JSON e
 
 ```js
 {
-  "mappings": {
-    "dynamic": true,
-    "fields": {
-      "embeddings": {
-        "dimensions": 384,
-        "similarity": "cosine",
-        "type": "knnVector"
-      },
-      "language": {
-        "normalizer": "none",
-        "type": "token"
-      }
+  "fields": [
+    {
+      "type": "vector",
+      "path": "embeddings",
+      "numDimensions": 1536,
+      "similarity": "cosine"
+    },
+    {
+      "type": "filter",
+      "path": "language"
     }
-  }
+  ]
 }
 ```
 
-The only difference is that we've added this part, stating that `language` should be indexed as a [token](https://www.mongodb.com/docs/atlas/atlas-search/field-types/token-type/), not as a string (we're not going to do full text search here, but Vector Search)
+The only difference is that we've added this part, stating that `language` should be indexed as a [filter](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-type/#about-the-filter-type).
 
 ```js
-"language": {
-    "normalizer": "none",
-    "type": "token"
-}
+    {
+      "type": "filter",
+      "path": "language"
+    }
 ```
 
 Add that new aggregation pipeline in your code (`server/src/controllers/books.ts` inside the now familiar `searchBooks` method) and when searching, you'll get semantic results written in Spanish.
diff --git a/static/img/screenshots/2-search/3-test-search/2-search-tester.png b/static/img/screenshots/2-search/3-test-search/2-search-tester.png
index cbc5aabc..99b3f2bb 100644
Binary files a/static/img/screenshots/2-search/3-test-search/2-search-tester.png and b/static/img/screenshots/2-search/3-test-search/2-search-tester.png differ