HuggingFace Chat

HuggingFace 推断端点允许你部署并将机器学习模型托管在云端，并通过 API 访问它们。

Getting Started

有关HuggingFace推理端点的更多详细信息，请访问 here。

Prerequisites

添加 spring-ai-huggingface 依赖项：

<dependency>
   <groupId>org.springframework.ai</groupId>
   <artifactId>spring-ai-huggingface</artifactId>
</dependency>

你应该获取 HuggingFace API 密钥并将其设置为环境变量。

export HUGGINGFACE_API_KEY=your_api_key_here

  1. 参见 Dependency Management 部分，将 Spring AI BOM 添加到你的构建文件中。

注意，此客户端实现尚无 Spring Boot Starter。

获取推理端点的端点 URL。您可以在推理端点的 UI here 上找到它。

Making a call to the model

HuggingfaceChatClient client = new HuggingfaceChatClient(apiKey, basePath);
Prompt prompt = new Prompt("Your text here...");
ChatResponse response = client.call(prompt);
System.out.println(response.getGeneration().getText());

Example

使用 here 中的示例

String mistral7bInstruct = """
        [INST] You are a helpful code assistant. Your task is to generate a valid JSON object based on the given information:
        name: John
        lastname: Smith
        address: #1 Samuel St.
        Just generate the JSON object without explanations:
        [/INST]""";
Prompt prompt = new Prompt(mistral7bInstruct);
ChatResponse aiResponse = huggingfaceChatClient.call(prompt);
System.out.println(response.getGeneration().getText());

将生成如下输出：

{
    "name": "John",
    "lastname": "Smith",
    "address": "#1 Samuel St."
}