Mistral AI Chat
Spring AI supports the various AI language models from Mistral AI. You can interact with Mistral AI language models and create a multilingual conversational assistant based on Mistral models.
Prerequisites
You will need to create an API with MistralAI to access Mistral AI language models.
Create an account at MistralAI registration page and generate the token on the API Keys page.
The Spring AI project defines a configuration property named spring.ai.mistralai.api-key
that you should set to the value of the API Key
obtained from console.mistral.ai.
Exporting an environment variable is one way to set that configuration property:
export SPRING_AI_MISTRALAI_API_KEY=<INSERT KEY HERE>
Add Repositories and BOM
Spring AI artifacts are published in Spring Milestone and Snapshot repositories. Refer to the Repositories section to add these repositories to your build system.
To help with dependency management, Spring AI provides a BOM (bill of materials) to ensure that a consistent version of Spring AI is used throughout the entire project. Refer to the Dependency Management section to add the Spring AI BOM to your build system.
Auto-configuration
Spring AI provides Spring Boot auto-configuration for the MistralAI Chat Client.
To enable it add the following dependency to your project’s Maven pom.xml
file:
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-mistral-ai-spring-boot-starter</artifactId>
</dependency>
or to your Gradle build.gradle
build file.
dependencies {
implementation 'org.springframework.ai:spring-ai-mistral-ai-spring-boot-starter'
}
Refer to the Dependency Management section to add the Spring AI BOM to your build file. |
Chat Properties
Retry Properties
The prefix spring.ai.retry
is used as the property prefix that lets you configure the retry mechanism for the Mistral AI chat model.
Property | Description | Default |
---|---|---|
spring.ai.retry.max-attempts |
Maximum number of retry attempts. |
10 |
spring.ai.retry.backoff.initial-interval |
Initial sleep duration for the exponential backoff policy. |
2 sec. |
spring.ai.retry.backoff.multiplier |
Backoff interval multiplier. |
5 |
spring.ai.retry.backoff.max-interval |
Maximum backoff duration. |
3 min. |
spring.ai.retry.on-client-errors |
If false, throw a NonTransientAiException, and do not attempt retry for |
false |
spring.ai.retry.exclude-on-http-codes |
List of HTTP status codes that should not trigger a retry (e.g. to throw NonTransientAiException). |
empty |
spring.ai.retry.on-http-codes |
List of HTTP status codes that should trigger a retry (e.g. to throw TransientAiException). |
empty |
Connection Properties
The prefix spring.ai.mistralai
is used as the property prefix that lets you connect to OpenAI.
Property | Description | Default |
---|---|---|
spring.ai.mistralai.base-url |
The URL to connect to |
|
spring.ai.mistralai.api-key |
The API Key |
- |
Configuration Properties
The prefix spring.ai.mistralai.chat
is the property prefix that lets you configure the chat model implementation for MistralAI.
Property | Description | Default |
---|---|---|
spring.ai.mistralai.chat.enabled |
Enable MistralAI chat model. |
true |
spring.ai.mistralai.chat.base-url |
Optional overrides the spring.ai.mistralai.base-url to provide chat specific url |
- |
spring.ai.mistralai.chat.api-key |
Optional overrides the spring.ai.mistralai.api-key to provide chat specific api-key |
- |
spring.ai.mistralai.chat.options.model |
This is the MistralAI Chat model to use |
|
spring.ai.mistralai.chat.options.temperature |
The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. |
0.8 |
spring.ai.mistralai.chat.options.maxTokens |
The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length. |
- |
spring.ai.mistralai.chat.options.safePrompt |
Indicates whether to inject a security prompt before all conversations. |
false |
spring.ai.mistralai.chat.options.randomSeed |
This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. |
- |
spring.ai.mistralai.chat.options.stop |
Up to 4 sequences where the API will stop generating further tokens. |
- |
spring.ai.mistralai.chat.options.topP |
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. |
- |
spring.ai.mistralai.chat.options.responseFormat |
An object specifying the format that the model must output. Setting to |
- |
spring.ai.mistralai.chat.options.tools |
A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. |
- |
spring.ai.mistralai.chat.options.toolChoice |
Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present. |
- |
spring.ai.mistralai.chat.options.functions |
List of functions, identified by their names, to enable for function calling in a single prompt requests. Functions with those names must exist in the functionCallbacks registry. |
- |
spring.ai.mistralai.chat.options.functionCallbacks |
MistralAI Tool Function Callbacks to register with the ChatModel. |
- |
You can override the common spring.ai.mistralai.base-url and spring.ai.mistralai.api-key for the ChatModel and EmbeddingModel implementations.
The spring.ai.mistralai.chat.base-url and spring.ai.mistralai.chat.api-key properties if set take precedence over the common properties.
This is useful if you want to use different MistralAI accounts for different models and different model endpoints.
|
All properties prefixed with spring.ai.mistralai.chat.options can be overridden at runtime by adding a request specific Runtime Options to the Prompt call.
|
Runtime Options
The MistralAiChatOptions.java provides model configurations, such as the model to use, the temperature, the frequency penalty, etc.
On start-up, the default options can be configured with the MistralAiChatModel(api, options)
constructor or the spring.ai.mistralai.chat.options.*
properties.
At run-time you can override the default options by adding new, request specific, options to the Prompt
call.
For example to override the default model and temperature for a specific request:
ChatResponse response = chatModel.call(
new Prompt(
"Generate the names of 5 famous pirates.",
MistralAiChatOptions.builder()
.withModel(MistralAiApi.ChatModel.LARGE.getValue())
.withTemperature(0.5f)
.build()
));
In addition to the model specific MistralAiChatOptions you can use a portable ChatOptions instance, created with the ChatOptionsBuilder#builder(). |
Function Calling
You can register custom Java functions with the MistralAiChatModel and have the Mistral AI model intelligently choose to output a JSON object containing arguments to call one or many of the registered functions. This is a powerful technique to connect the LLM capabilities with external tools and APIs. Read more about Mistral AI Function Calling.
Sample Controller (Auto-configuration)
Create a new Spring Boot project and add the spring-ai-mistral-ai-spring-boot-starter
to your pom (or gradle) dependencies.
Add a application.properties
file, under the src/main/resources
directory, to enable and configure the OpenAi chat model:
spring.ai.mistralai.api-key=YOUR_API_KEY
spring.ai.mistralai.chat.options.model=mistral-medium
spring.ai.mistralai.chat.options.temperature=0.7
replace the api-key with your OpenAI credentials.
|
This will create a MistralAiChatModel
implementation that you can inject into your class.
Here is an example of a simple @Controller
class that uses the chat model for text generations.
@RestController
public class ChatController {
private final MistralAiChatModel chatModel;
@Autowired
public ChatController(MistralAiChatModel chatModel) {
this.chatModel = chatModel;
}
@GetMapping("/ai/generate")
public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
return Map.of("generation", chatModel.call(message));
}
@GetMapping("/ai/generateStream")
public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
var prompt = new Prompt(new UserMessage(message));
return chatModel.stream(prompt);
}
}
Manual Configuration
The MistralAiChatModel implements the ChatModel
and StreamingChatModel
and uses the Low-level MistralAiApi Client to connect to the MistralAI service.
Add the spring-ai-mistral-ai
dependency to your project’s Maven pom.xml
file:
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-mistral-ai</artifactId>
</dependency>
or to your Gradle build.gradle
build file.
dependencies {
implementation 'org.springframework.ai:spring-ai-mistral-ai'
}
Refer to the Dependency Management section to add the Spring AI BOM to your build file. |
Next, create a MistralAiChatModel
and use it for text generations:
var mistralAiApi = new MistralAiApi(System.getenv("MISTRAL_AI_API_KEY"));
var chatModel = new MistralAiChatModel(mistralAiApi, MistralAiChatOptions.builder()
.withModel(MistralAiApi.ChatModel.LARGE.getValue())
.withTemperature(0.4f)
.withMaxTokens(200)
.build());
ChatResponse response = chatModel.call(
new Prompt("Generate the names of 5 famous pirates."));
// Or with streaming responses
Flux<ChatResponse> response = chatModel.stream(
new Prompt("Generate the names of 5 famous pirates."));
The MistralAiChatOptions
provides the configuration information for the chat requests.
The MistralAiChatOptions.Builder
is fluent options builder.
Low-level MistralAiApi Client
The MistralAiApi provides is lightweight Java client for Mistral AI API.
Here is a simple snippet how to use the api programmatically:
MistralAiApi mistralAiApi =
new MistralAiApi(System.getenv("MISTRAL_AI_API_KEY"));
ChatCompletionMessage chatCompletionMessage =
new ChatCompletionMessage("Hello world", Role.USER);
// Sync request
ResponseEntity<ChatCompletion> response = mistralAiApi.chatCompletionEntity(
new ChatCompletionRequest(List.of(chatCompletionMessage), MistralAiApi.ChatModel.LARGE.getValue(), 0.8f, false));
// Streaming request
Flux<ChatCompletionChunk> streamResponse = mistralAiApi.chatCompletionStream(
new ChatCompletionRequest(List.of(chatCompletionMessage), MistralAiApi.ChatModel.LARGE.getValue(), 0.8f, true));
Follow the MistralAiApi.java's JavaDoc for further information.
MistralAiApi Samples
-
The MistralAiApiIT.java test provides some general examples how to use the lightweight library.
-
The PaymentStatusFunctionCallingIT.java test shows how to use the low-level API to call tool functions. Based on the MistralAI Function Calling tutorial.