Gemini Api — AI for Every Developer🚀(Part 3)

Image from Google Developers Blog

The Gemini API & Google AI Studio help you start working with Google’s Latest models and turn your ideas into application that scale.

When you start building with Gemini, you will have 2 options to leverage it’s Api on Front End or Backend.

Build Client Side

1. You can build client-side Web & Generative Mobile Apps with Gemini Api & Client SDK
2. SDK’s are available for Swift, Android, Web & Flutter
3. Vertex AI Gemini Api requires a linked Billing Account
4. You can use Firebase App Check to help secure Gemini Api Calls

Build Server Side

1. You can build and deploy server-side Generative AI app feature with open source framework & developer tools
2. You can seamlessly integrate with Gemini Models, Open models or third party Api-providers
3. You can develop multi-stage workflows server side using node.js

Google AI client SDK is also available for integration, but it comes with short advice. oops…

Source from Google Page

Why Vertex-AI ?

1. For mobile & Web apps security is critical & requires special considerations because your code (including calls to Gemini Api) is running in an unprotected environment
2. You need to protect Gemini API and your project resources (like tuned models) from abuse by unauthorized clients
3. You can use Firebase App check to verify that all api calls are from your actual app and it’s only available if you use the Vertex AI in Firebase sdk

Source from Google Page

Benefits of Using Vertex-AI

1. You can generate Text from text only prompts including streaming responses
2. Generate text from multimodal prompts (including text, images, PDFs, video, and audio)
3. Build multi-turn conversations (chat)
4. Generate structured output (like JSON) from both text and multimodal prompts
5. Use function calling to connect generative models to external systems and information

To get start with Vertex AI,
https://firebase.google.com/docs/vertex-ai/get-started?platform=android

Why Firebase Genkit ?

1. You can build and deploy server side generative app features
2. You can deploy and run Genkit libraries anywhere Node.js is supported
3. It’s designed to work with any generative AI model API or vector database

To get start with Firebase Genkit,
https://firebase.google.com/products/genkit

The whole AI works based on Prompts. The different models available are
https://firebase.google.com/docs/vertex-ai/gemini-models

🎉🎆🎇🎉🎆🎇🎉🎆🎇🎉🎆🎇🎉🎆🎇🎉🎆🎇🎉🎆🎇

Stay Tuned and Keep Watch for Part 4, Happy Learning.
Feel Free to Clap 👏 and Keep me Motivated 👏 to come up with Next Parts.