You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/search/search-get-started-portal-import-vectors.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,7 @@ ms.date: 01/02/2024
17
17
> [!IMPORTANT]
18
18
> **Import and vectorize data** wizard is in public preview under [Supplemental Terms of Use](https://azure.microsoft.com/support/legal/preview-supplemental-terms/). It targets the [2023-10-01-Preview REST API](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2023-10-01-preview&preserve-view=true).
19
19
20
-
Get started with [integrated vectorization (preview)](vector-search-integrated-vectorization.md) using the **Import and vectorize data** wizard in the Azure portal. This wizard calls an Azure OpenAI text embedding model to vectorize content during indexing.
20
+
Get started with [integrated vectorization (preview)](vector-search-integrated-vectorization.md) using the **Import and vectorize data** wizard in the Azure portal. This wizard calls an Azure OpenAI text embedding model to vectorize content during indexing and for queries.
21
21
22
22
In this preview version of the wizard:
23
23
@@ -145,13 +145,15 @@ Search explorer accepts text strings as input and then vectorizes the text for v
145
145
146
146
1. Select your index.
147
147
148
-
1. Make sure the API version is **2023-10-01-preview**.
149
-
150
148
1. Optionally, select **Query options** and hide vector values in search results. This step makes your search results easier to read.
151
149
152
150
:::image type="content" source="media/search-get-started-portal-import-vectors/query-options.png" alt-text="Screenshot of the query options button.":::
153
151
154
-
1. Select **JSON view** so that you can enter text for your vector query in the **text** vector query parameter. This wizard offers a default query that issues a vector query on the "vector" field, returning the 5 nearest neighbors. If you opted to hide vector values, your default query includes a "select" statement that excludes the vector field from search results.
152
+
1. Select **JSON view** so that you can enter text for your vector query in the **text** vector query parameter.
153
+
154
+
:::image type="content" source="media/search-get-started-portal-import-vectors/search-results.png" alt-text="Screenshot of search results.":::
155
+
156
+
This wizard offers a default query that issues a vector query on the "vector" field, returning the 5 nearest neighbors. If you opted to hide vector values, your default query includes a "select" statement that excludes the vector field from search results.
155
157
156
158
```json
157
159
{
@@ -171,9 +173,7 @@ Search explorer accepts text strings as input and then vectorizes the text for v
171
173
172
174
1. Select **Search** to run the query.
173
175
174
-
:::image type="content" source="media/search-get-started-portal-import-vectors/search-results.png" alt-text="Screenshot of search results.":::
175
-
176
-
You should see 5 matches, where each document is a chunk of the original PDF. The title field shows which PDF the chunk comes from.
176
+
You should see 5 matches, where each document is a chunk of the original PDF. The title field shows which PDF the chunk comes from.
177
177
178
178
1. To see all of the chunks from a specific document, add a filter for the title field for a specific PDF:
0 commit comments