As you develop your app with Vertex AI for Firebase, you might want to go beyond the basics discussed in the main guides. The solutions outlined in this section offer guidance on more advanced use cases.
Manage files and include large files in multimodal requests
By using Cloud Storage for Firebase, you can take advantage of a fast, secure, and scalable infrastructure for file storage and management. Plus, you can include larger files in your multimodal requests using a Cloud Storage for Firebase URL.
See the Cloud Storage for Firebase solution
Protect your app from unauthorized clients
For mobile and web apps, you need to protect the Gemini API and your project resources (like tuned models) from abuse by unauthorized clients. You can use Firebase App Check to verify that all API calls are from your actual app.
See the Firebase App Check solution
Dynamically and conditionally set runtime configurations
If you want to set configurations based on runtime conditions, you can use Firebase Remote Config. One example is changing the location where you run the Vertex AI service and generative model based on an end-user's location.
See the Remote Config documentation
Update values in your app without releasing a new version of your app
If you need to dynamically change values in your app without releasing a new version of your app, you can use Firebase Remote Config. Examples include updating the model name when a new model version is released or changing a prompt or input for a request.
See the Remote Config documentation
We're actively working on other solutions and guides, so check back soon!