GitHub - JavaAIDev/springai-openai-client: Spring AI ChatModel for OpenAI using official Java SDK, designed for Spring 5

Spring AI ChatModel and EmbeddingModel implementations for OpenAI using the official SDK.

The motivation of this ChatModel and EmbeddingModel implementations is to use Spring AI with Spring 5.

Add Maven dependency of the latest version.

<dependency>
  <groupId>com.javaaidev</groupId>
  <artifactId>springai-openai-client</artifactId>
  <version>${VERSION}</version>
</dependency>

ChatModel

Supported features:

Chat completions
Function calling
Streaming mode

Use ChatModel

To use this ChatModel,

Create an OpenAIClient,
Create an OpenAIChatModel,
Create a Spring AI ChatClient.Builder with this ChatModel,
Create a Spring AI ChatClient from ChatClient.Builder.

See the code below:

val client = OpenAIOkHttpClient.fromEnv()
val chatModel = OpenAIChatModel(client, 
    DefaultToolCallingManager.builder().toolCallbackResolver(CustomToolCallbackResolver()).build())
val chatOptions = OpenAiChatOptions.builder()
    .model("gpt-4o-mini")
    .build()
chatClient =
    ChatClient.builder(chatModel).defaultOptions(chatOptions).build()
val response = chatClient.prompt().user("tell me a joke")
    .call().content()

Streaming

Streaming mode is also supported.

val builder = StringBuilder()
chatClient.prompt().user("tell me a joke")
    .stream().chatResponse().doOnNext {
        builder.append(it.result.output.text)
    }.blockLast()
val result = builder.toString()

EmbeddingModel

To use this EmbeddingModel,

Create an OpenAIClient,
Create an OpenAIEmbeddingModel

See the code below:

val client = OpenAIOkHttpClient.fromEnv()
val embeddingModel = OpenAIEmbeddingModel(client)
val response = embeddingModel.call(
    EmbeddingRequest(
        listOf("hello", "world"),
        OpenAIEmbeddingOptions.builder()
            .model("text-embedding-3-small")
            .build()
    )
)