Tutorial: Function calling with the Gemini API

Python Node.js Go Dart (Flutter) Android Swift Web

Function calling makes it easier for you to get structured data outputs from generative models. You can then use these outputs to call other APIs and return the relevant response data to the model. In other words, function calling helps you connect generative models to external systems so that the generated content includes the most up-to-date and accurate information.

You can provide Gemini models with descriptions of functions. These are functions that you write in the language of your app (that is, they're not Google Cloud Functions). The model may ask you to call a function and send back the result to help the model handle your query.

If you haven't already, check out the Introduction to function calling to learn more.

Set up your project

Before calling the Gemini API, you need to set up your Android project, which includes setting up your API key, adding the SDK dependencies to your Android project, and initializing the model.

// Access your API key as a Build Configuration variable
val apiKey = BuildConfig.apiKey

val generativeModel = GenerativeModel(

    // Use a model that supports function calling, like Gemini 1.0 Pro.
    // See "Supported models" in the "Introduction to function calling" page.
    modelName = "MODEL_NAME",

    // Access your API key as a Build Configuration variable (see "Set up your API key" above).
    apiKey = BuildConfig.apiKey
)

Set up a function call

For this tutorial, you'll have the model interact with a hypothetical currency exchange API that supports the following parameters:

Example API request

{
  "currencyFrom": "USD",
  "currencyTo": "SEK"
}

Example API response

{
  "base": "USD",
  "rates": {"SEK": 0.091}
}

Step 1: Create the function that makes the API request

If you haven't already, start by creating the function that makes an API request.

For demonstration purposes in this tutorial, rather than sending an actual API request, you'll be returning hardcoded values in the same format that an actual API would return.

suspend fun makeApiRequest(
    currencyFrom: String,
    currencyTo: String
): JSONObject {
    // This hypothetical API returns a JSON such as:
    // {"base":"USD","rates":{"SEK": 0.091}}
    return JSONObject().apply {
        put("base", currencyFrom)
        put("rates", hashMapOf(currencyTo to 0.091))
    }
}

Step 2: Create a function declaration

Create the function declaration that you'll pass to the generative model (next step of this tutorial).

Include as much detail as possible in the function and parameter descriptions. The generative model uses this information to determine which function to select and how to provide values for the parameters in the function call.

val getExchangeRate = defineFunction(
  name = "getExchangeRate",
  description = "Get the exchange rate for currencies between countries",
  Schema.str("currencyFrom", "The currency to convert from."),
  Schema.str("currencyTo", "The currency to convert to.")
) { from, to ->
    // Call the function that you declared above
    makeApiRequest(from, to)
}

Step 3: Specify the function declaration during model initialization

Specify the function declaration when initializing the generative model by passing it into the model's tools parameter:

val generativeModel = GenerativeModel(
  // Use a model that supports function calling, like Gemini 1.0 Pro
  // (see "Supported models" in the "Introduction to function calling" page)
  modelName = "gemini-1.0-pro",
  // Access your API key as a Build Configuration variable (see "Set up your API key" above)
  apiKey = BuildConfig.apiKey,
  // Specify the function declaration.
  tools = listOf(Tool(listOf(getExchangeRate)))
)

Step 4: Generate a function call

Now you can prompt the model with the defined function.

The recommended way to use function calling is through the chat interface, since function calls fit nicely into chat's multi-turn structure.

val chat = generativeModel.startChat()

val prompt = "How much is 50 US dollars worth in Swedish krona?"

// Send the message to the generative model
var response = chat.sendMessage(prompt)

// Check if the model responded with a function call
response.functionCall?.let { functionCall ->
  // Try to retrieve the stored lambda from the model's tools and
  // throw an exception if the returned function was not declared
  val matchedFunction = generativeModel.tools?.flatMap { it.functionDeclarations }
      ?.first { it.name == functionCall.name }
      ?: throw InvalidStateException("Function not found: ${functionCall.name}")

  // Call the lambda retrieved above
  val apiResponse: JSONObject = matchedFunction.execute(functionCall)

  // Send the API response back to the generative model
  // so that it generates a text response that can be displayed to the user
  response = chat.sendMessage(
    content(role = "function") {
        part(FunctionResponsePart(functionCall.name, apiResponse))
    }
  )
}

// Whenever the model responds with text, show it in the UI
response.text?.let { modelResponse ->
    println(modelResponse)
}