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
This page provides step-by-step instructions for setting up a Google Vertex AI connector for the first time. This connector type enables you to leverage Vertex AI’s large language models (LLMs) within {{elastic-sec}}. You’ll first need to enable Vertex AI, then generate an API key, and finally configure the connector in your {{elastic-sec}} project.
16
+
This page provides step-by-step instructions for setting up a Google Vertex AI connector for the first time. This connector type enables you to leverage Vertex AI’s large language models (LLMs) within {{elastic-sec}}. You’ll first need to enable Vertex AI, then generate a key, and finally configure the connector in your {{elastic-sec}} project.
17
17
18
18
::::{important}
19
19
Before continuing, you should have an active project in one of Google Vertex AI’s [supported regions](https://cloud.google.com/vertex-ai/docs/general/locations#feature-availability).
@@ -74,7 +74,7 @@ The following video demonstrates these steps.
74
74
75
75
76
76
77
-
## Generate an API key [_generate_an_api_key]
77
+
## Generate a key [_generate_an_api_key]
78
78
79
79
1. Return to Vertex AI’s **Credentials** menu and click **Manage service accounts**.
80
80
2. Search for the service account you just created, select it, then click the link that appears under **Email**.
@@ -108,7 +108,7 @@ Finally, configure the connector in your Elastic deployment:
108
108
4. Under **URL**, enter the URL for your region.
109
109
5. Enter your **GCP Region** and **GCP Project ID**.
110
110
6. Under **Default model**, specify either `gemini-1.5.pro` or `gemini-1.5-flash`. [Learn more about the models](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models).
111
-
7. Under **Authentication**, enter your API key.
111
+
7. Under **Authentication**, enter your credentials JSON.
0 commit comments