我有以下代码：

public static String simpleQuestion(String projectId, String location, String modelName) throws Exception {        // Initialize client that will be used to send requests.        // This client only needs to be created once, and can be reused for multiple requests.        try (VertexAI vertexAI = new VertexAI(projectId, location)) {            String output;            GenerativeModel model = new GenerativeModel(modelName, vertexAI);            model.setGenerationConfig(GenerationConfig.newBuilder().build());            model.setSafetySettings(Collections.singletonList(                    SafetySetting.newBuilder()                            .setThreshold(SafetySetting                                    .HarmBlockThreshold.BLOCK_NONE).build()));            GenerateContentResponse response = model.generateContent("What can you tell me about Pythagorean theorem");            output = ResponseHandler.getText(response);            return output;        }    }

有时我会遇到这个错误：

context/6.1.1/spring-context-6.1.1.jar com.mysticriver.service.GoogleGeminiServiceException in thread "main" java.lang.IllegalArgumentException: The response is blocked due to safety reason.    at com.google.cloud.vertexai.generativeai.preview.ResponseHandler.getText(ResponseHandler.java:46)

即使我在设置中使用了HarmBlockThreshold.BLOCK_NONE

回答：

问题

您需要为特定的伤害类别设置伤害阻止阈值。

解决方案

将这个…

SafetySetting.newBuilder()  .setThreshold(SafetySetting.HarmBlockThreshold.BLOCK_NONE)  .build()

…改为这个。

SafetySetting.newBuilder()  .setCategory(HarmCategory.HARM_CATEGORY_YOUR_CATEGORY)  .setThreshold(SafetySetting.HarmBlockThreshold.BLOCK_NONE)  .build()

所有伤害类别的列表：

• HARM_CATEGORY_SEXUALLY_EXPLICIT
• HARM_CATEGORY_HATE_SPEECH
• HARM_CATEGORY_HARASSMENT
• HARM_CATEGORY_DANGEROUS_CONTENT