Spring AI更新：支持OpenAI的結(jié)構(gòu)化輸出，增強(qiáng)JSON響應(yīng)可靠性

管理

編輯

刪除

CRMEB 2025-02-24 15:29:37

暫不處理

由于最近OpenAI推出了結(jié)構(gòu)化輸出的功能，可確保 AI 生成的響應(yīng)嚴(yán)格遵守預(yù)定義的 JSON 模式。此功能顯著提高了人工智能生成內(nèi)容在現(xiàn)實(shí)應(yīng)用中的可靠性和可用性。Spring AI 緊隨其后，現(xiàn)在也可以對(duì)OpenAI的結(jié)構(gòu)化輸出完美支持了。

下圖展示了本次擴(kuò)展的實(shí)現(xiàn)結(jié)構(gòu)，如果對(duì)于當(dāng)前實(shí)現(xiàn)還不夠滿意，需要擴(kuò)展的可以根據(jù)此圖來著手理解分析進(jìn)行下一步擴(kuò)展工作。

#使用樣例

通過Spring AI，開發(fā)者可以很方便的來構(gòu)建針對(duì) OpenAI 結(jié)構(gòu)化輸出的請求和解析：

String jsonSchema = """
  {
      "type": "object",
      "properties": {
          "steps": {
              "type": "array",
              "items": {
                  "type": "object",
                  "properties": {
                      "explanation": { "type": "string" },
                      "output": { "type": "string" }
                  },
                  "required": ["explanation", "output"],
                  "additionalProperties": false
              }
          },
          "final_answer": { "type": "string" }
      },
      "required": ["steps", "final_answer"],
      "additionalProperties": false
  }
  """;

Prompt prompt = new Prompt("how can I solve 8x + 7 = -23",
OpenAiChatOptions.builder()
    .withModel(ChatModel.GPT_4_O_MINI)
    .withResponseFormat(new ResponseFormat(ResponseFormat.Type.JSON_SCHEMA, jsonSchema))
    .build());

ChatResponse response = this.openAiChatModel.call(prompt);

通過 OpenAiChatOptions中指定ResponseFormat來讓OpenAI返回JSON格式。

Spring AI還提供了BeanOutputConverter來實(shí)現(xiàn)將JSON出轉(zhuǎn)換成Java Bean，比如下面這樣：

record MathReasoning(
  @JsonProperty(required = true, value = "steps") Steps steps,
  @JsonProperty(required = true, value = "final_answer") String finalAnswer) {

  record Steps(
    @JsonProperty(required = true, value = "items") Items[] items) {

    record Items(
      @JsonProperty(required = true, value = "explanation") String explanation,
      @JsonProperty(required = true, value = "output") String output) {}
  }
}

var outputConverter = new BeanOutputConverter<>(MathReasoning.class);

var jsonSchema = outputConverter.getJsonSchema();

Prompt prompt = new Prompt("how can I solve 8x + 7 = -23",
OpenAiChatOptions.builder()
    .withModel(ChatModel.GPT_4_O_MINI)
    .withResponseFormat(new ResponseFormat(ResponseFormat.Type.JSON_SCHEMA, jsonSchema))
    .build());

ChatResponse response = this.openAiChatModel.call(prompt);
String content = response.getResult().getOutput().getContent();

MathReasoning mathReasoning = outputConverter.convert(content);

如果你整合了Spring AI針對(duì)OpenAI的Spring Boot Starter模塊，那么也可以通過下面的方式來自動(dòng)配置默認(rèn)的JSON返回格式：

spring.ai.openai.api-key=YOUR_API_KEY
spring.ai.openai.chat.options.model=gpt-4o-mini

spring.ai.openai.chat.options.response-format.type=JSON_SCHEMA
spring.ai.openai.chat.options.response-format.name=MySchemaName
spring.ai.openai.chat.options.response-format.schema={"type":"object","properties":{"steps":{"type":"array","items":{"type":"object","properties":{"explanation":{"type":"string"},"output":{"type":"string"}},"required":["explanation","output"],"additionalProperties":false}},"final_answer":{"type":"string"}},"required":["steps","final_answer"],"additionalProperties":false}
spring.ai.openai.chat.options.response-format.strict=true

轉(zhuǎn)載： https://spring.didispace.com/article/spring-ai-openai-json.html#%E4%BD%BF%E7%94%A8%E6%A0%B7%E4%BE%8B

請登錄后查看

CRMEB 最后編輯于2025-02-24 15:29:37

快捷回復(fù)