This page explains how to use the Google Cloud console to ground your LLM responses.
Use the Google Cloud console to ground
Grounding can also be used in the Google Cloud console.
In the Vertex AI Studio of the Google Cloud console, go to Create prompt page.
Select a model that supports grounding.
To turn on grounding, click the Grounding: Your data toggle.
Select Elasticsearch, and Grounding with Elasticsearch section displays.
Enter your Elasticsearch endpoint in the Elasticsearch endpoint field.
Enter your API key in the API key field.
Enter your Elasticsearch index in the Index field.
Enter your Elasticsearch template name in the Search template field.
Adjust the number of hits by sliding the Number of hits bar. Click Save.
What's next
- To learn how to send chat prompt requests, see Multiturn chat.
- To learn about responsible AI best practices and Vertex AI's safety filters,
see Safety best practices.