Mistral Function Calling

You can register custom Java functions with the MistralAiChatClient and have the Mistral AI models intelligently choose to output a JSON object containing arguments to call one or many of the registered functions. This allows you to connect the LLM capabilities with external tools and APIs. The mistral_small_latest and mistral_large_latest models are trained to detect when a function should be called and to respond with JSON that adheres to the function signature.

The MistralAI API does not call the function directly; instead, the model generates JSON that you can use to call the function in your code and return the result back to the model to complete the conversation.

Currently the MistralAI API doesn’t support parallel function calling, similarly to the OpenAI API, Azure OpenAI API, and Vertex AI Gemini API.

Spring AI provides flexible and user-friendly ways to register and call custom functions. In general, the custom functions need to provide a function name, description, and the function call signature (as JSON schema) to let the model know what arguments the function expects. The description helps the model to understand when to call the function.

As a developer, you need to implement a functions that takes the function call arguments sent from the AI model, and respond with the result back to the model. Your function can in turn invoke other 3rd party services to provide the results.

Spring AI makes this as easy as defining a @Bean definition that returns a java.util.Function and supplying the bean name as an option when invoking the ChatClient.

Under the hood, Spring wraps your POJO (the function) with the appropriate adapter code that enables interaction with the AI Model, saving you from writing tedious boilerplate code. The basis of the underlying infrastructure is the FunctionCallback.java interface and the companion FunctionCallbackWrapper.java utility class to simplify the implementation and registration of Java callback functions.

How it works

Suppose we want the AI model to respond with information that it does not have, for example the current temperature at a given location.

We can provide the AI model with metadata about our own functions that it can use to retrieve that information as it processes your prompt.

For example, if during the processing of a prompt, the AI Model determines that it needs additional information about the temperature in a given location, it will start a server side generated request/response interaction. The AI Model invokes a client side function. The AI Model provides method invocation details as JSON and it is the responsibility of the client to execute that function and return the response.

Spring AI greatly simplifies code you need to write to support function invocation. It brokers the function invocation conversation for you. You can simply provide your function definition as a @Bean and then provide the bean name of the function in your prompt options. You can also reference multiple function bean names in your prompt.

Quick Start

Let’s create a chatbot that answer questions by calling our own function. To support the response of the chatbot, we will register our own function that takes a location and returns the current weather in that location.

When the response to the prompt to the model needs to answer a question such as "What’s the weather like in Boston?" the AI model will invoke the client providing the location value as an argument to be passed to the function. This RPC-like data is passed as JSON.

Our function can some SaaS based weather service API and returns the weather response back to the model to complete the conversation. In this example we will use a simple implementation named MockWeatherService that hard codes the temperature for various locations.

The following MockWeatherService.java represents the weather service API:

public class MockWeatherService implements Function<Request, Response> {

	public enum Unit { C, F }
	public record Request(String location, Unit unit) {}
	public record Response(double temp, Unit unit) {}

	public Response apply(Request request) {
		return new Response(30.0, Unit.C);

Registering Functions as Beans

With the MistralAiChatClient Auto-Configuration you have multiple ways to register custom functions as beans in the Spring context.

We start with describing the most POJO friendly options.

Plain Java Functions

In this approach you define @Beans in your application context as you would any other Spring managed object.

Internally, Spring AI ChatClient will create an instance of a FunctionCallbackWrapper wrapper that adds the logic for it being invoked via the AI model. The name of the @Bean is passed as a ChatOption.

static class Config {

	@Description("Get the weather in location") // function description
	public Function<MockWeatherService.Request, MockWeatherService.Response> weatherFunction1() {
		return new MockWeatherService();

The @Description annotation is optional and provides a function description (2) that helps the model to understand when to call the function. It is an important property to set to help the AI model determine what client side function to invoke.

Another option to provide the description of the function is to the @JacksonDescription annotation on the MockWeatherService.Request to provide the function description:

static class Config {

	public Function<Request, Response> currentWeather3() { // (1) bean name as function name.
		return new MockWeatherService();

@JsonClassDescription("Get the weather in location") // (2) function description
public record Request(String location, Unit unit) {}

It is a best practice to annotate the request object with information such that the generates JSON schema of that function is as descriptive as possible to help the AI model pick the correct function to invoke.

The PaymentStatusBeanIT.java demonstrates this approach.

The PaymentStatusBeanOpenAiIT implements the same function using the OpenAI API. MistralAI is almost identical to OpenAI in this regard.

FunctionCallback Wrapper

Another way register a function is to create FunctionCallbackWrapper wrapper like this:

static class Config {

	public FunctionCallback weatherFunctionInfo() {

		return new FunctionCallbackWrapper<>("CurrentWeather", // (1) function name
				"Get the weather in location", // (2) function description
				(response) -> "" + response.temp() + response.unit(), // (3) Response Converter
				new MockWeatherService()); // function code

It wraps the 3rd party, MockWeatherService function and registers it as a CurrentWeather function with the MistralAiChatClient. It also provides a description (2) and an optional response converter (3) to convert the response into a text as expected by the model.

By default, the response converter does a JSON serialization of the Response object.
The FunctionCallbackWrapper internally resolves the function call signature based on the MockWeatherService.Request class.

Specifying functions in Chat Options

To let the model know and call your CurrentWeather function you need to enable it in your prompt requests:

MistralAiChatClient chatClient = ...

UserMessage userMessage = new UserMessage("What's the weather like in Paris?");

ChatResponse response = chatClient.call(new Prompt(List.of(userMessage),
		MistralAiChatOptions.builder().withFunction("CurrentWeather").build())); // (1) Enable the function

logger.info("Response: {}", response);

Above user question will trigger 3 calls to CurrentWeather function (one for each city) and produce the final response.

Register/Call Functions with Prompt Options

In addition to the auto-configuration you can register callback functions, dynamically, with your Prompt requests:

MistralAiChatClient chatClient = ...

UserMessage userMessage = new UserMessage("What's the weather like in Paris?");

var promptOptions = MistralAiChatOptions.builder()
	.withFunctionCallbacks(List.of(new FunctionCallbackWrapper<>(
		"CurrentWeather", // name
		"Get the weather in location", // function description
		new MockWeatherService()))) // function code

ChatResponse response = chatClient.call(new Prompt(List.of(userMessage), promptOptions));
The in-prompt registered functions are enabled by default for the duration of this request.

This approach allows to dynamically chose different functions to be called based on the user input.

The PaymentStatusPromptIT.java integration test provides a complete example of how to register a function with the MistralAiChatClient and use it in a prompt request.