For Firebase AI Logic , the Firebase console provides a guided UI for you to specify the contents of a template. However, there are several use cases where you may need more advanced ways to set up a template, including:
The advanced workflows described in this page use the Firebase AI Logic REST API .
Be aware of the following when using the REST API:
-
If you provision a template in a specific location, then the request from your app must access the model in that same location. If the locations don't match, then the request will fail.
-
The list of templates in the Firebase console only shows templates that are (at minimum) provisioned in the
globallocation. -
If a template is unlocked, then you can overwrite the template by using the same template ID in your REST API call. A locked template cannot be overwritten.
Specify a location for a template
This section is only applicable if you're using the Vertex AI Gemini API and your use case requires location-based restrictions. Learn more about setting a location for accessing a model .
By default, when you use the guided UI in the Firebase console, we provision the template in all available regions for Firebase AI Logic . We do this so that no matter what location you set in your request, the template will be available. However, if you want your template to only be available in a specific location , then you need to create the template using our REST API.
When you call the projects.locations.templates.create
endpoint
,
specify the location
of the template as part of creating a PromptTemplate
.
Provide the template as a file
You can provide the contents of a server prompt template file by calling the projects.locations.templates.create
endpoint
.
