Build multi-turn conversations (chat) with the Gemini API

iOS+ Android Web Flutter

Using the Gemini API, you can build freeform conversations across multiple turns. The Vertex AI in Firebase SDK simplifies the process by managing the state of the conversation, so unlike with generateContentStream() or generateContent(), you don't have to store the conversation history yourself.

Other options for working with the Gemini API

• Optionally experiment with an alternative "Google AI" version of the Gemini API
  Get free-of-charge access (within limits and where available) using Google AI Studio and Google AI client SDKs. These SDKs should be used for prototyping only in mobile and web apps.

  After you're familiar with how a Gemini API works, migrate to our Vertex AI in Firebase SDKs (this documentation), which have many additional features important for mobile and web apps, like protecting the API from abuse using Firebase App Check and support for large media files in requests.

• Optionally call the Vertex AI Gemini API server-side (like with Python, Node.js, or Go)
  Use the server-side Vertex AI SDKs, Firebase Genkit, or Firebase Extensions for the Gemini API.

Before you begin

If you haven't already, complete the getting started guide for the Vertex AI in Firebase SDKs. Make sure that you've done all of the following:

1. Set up a new or existing Firebase project, including using the Blaze pricing plan and enabling the required APIs.

2. Connect your app to Firebase, including registering your app and adding your Firebase config to your app.

3. Add the SDK and initialize the Vertex AI service and the generative model in your app.

After you've connected your app to Firebase, added the SDK, and initialized the Vertex AI service and the generative model, you're ready to call the Gemini API.

Send a chat prompt request

To build a multi-turn conversation (like chat), start off by initializing the chat by calling startChat(). Then use sendMessageStream() (or sendMessage()) to send a new user message, which will also append the message and the response to the chat history.

There are two possible options for role associated with the content in a conversation:

• user: the role which provides the prompts. This value is the default for calls to sendMessageStream() (or sendMessage()), and the function throws an exception if a different role is passed.

• model: the role which provides the responses. This role can be used when calling startChat() with existing history.

Note: If you'd like to provide more initial context for the model to help steer its behavior based on your specific needs and use cases, consider setting system instructions.

Choose whether you want to stream the response (sendMessageStream) or wait for the response until the entire result is generated (sendMessage).

Streaming

You can achieve faster interactions by not waiting for the entire result from the model generation, and instead use streaming to handle partial results.

Without streaming

Alternatively, you can wait for the entire result instead of streaming; the result is only returned after the model completes the entire generation process.

Learn how to choose a model and optionally a location appropriate for your use case and app.

What else can you do?

• Learn how to count tokens before sending long prompts to the model.
• Set up Cloud Storage for Firebase so that you can include large files in your multimodal requests and have a more managed solution for providing files in prompts. Files can include images, PDFs, video, and audio.
• Start thinking about preparing for production, including setting up Firebase App Check to protect the Gemini API from abuse by unauthorized clients. Also, make sure to review the production checklist.

Try out other capabilities of the Gemini API

• Generate text from text-only prompts.
• Generate text from multimodal prompts (including text, images, PDFs, video, and audio).
• Generate structured output (like JSON) from both text and multimodal prompts.
• Use function calling to connect generative models to external systems and information.

Learn how to control content generation

• Understand prompt design, including best practices, strategies, and example prompts.
• Configure model parameters like temperature and maximum output tokens (for Gemini) or aspect ratio and person generation (for Imagen).
• Use safety settings to adjust the likelihood of getting responses that may be considered harmful.

You can also experiment with prompts and model configurations using Vertex AI Studio.

Learn more about the supported models

Learn about the models available for various use cases and their quotas and pricing.

Give feedback about your experience with Vertex AI in Firebase