本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。
在您的应用程序中使用 ApplyGuardrail API
防护机制用于为您的生成式人工智能应用程序实现保护措施，这些保护措施是针对您的应用场景定制的，并且符合您的负责任的人工智能策略的要求。防护机制让您能够配置拒绝的主题、筛除有害内容和删除敏感信息。
您可以通过预先配置的 Amazon Bedrock 防护机制，使用 ApplyGuardrail API 来评估任何文本，而无需调用基础模型。
ApplyGuardrail API 的功能：
-
内容验证 – 您可以将任何文本输入或输出发送到
ApplyGuardrailAPI，以将其与您定义的主题禁用规则、内容筛选条件、PII 检测器和单词屏蔽列表进行比较。您可以分别评估用户输入和 FM 生成的输出。 -
灵活部署 – 您可以将
ApplyGuardrailAPI 集成到应用程序流程中的任何位置，以便在进行处理或向用户提供结果之前验证数据。例如，如果您使用的是 RAG 应用程序，现在可以在执行检索之前评估用户输入，而不是等到最终的响应生成时再进行评估。 -
与 FM 分离。–
ApplyGuardrailAPI 已经与基础模型分离。现在，您无需调用基础模型即可使用防护机制。您可以使用评估结果来设计生成式人工智能应用程序中的体验。
在您的应用程序流中调用 ApplyGuardrail API
请求允许客户传递所有应该使用其定义的防护机制进行保护的内容。当需要评估的内容来自用户时（通常是 LLM 提示），应将源字段设置为“INPUT”。当需要对模型输出应用防护机制时（通常是 LLM 响应），应将源设置为“OUTPUT”。
主题
配置防护机制，以便与 ApplyGuardrail API 配合使用
您需要在 guardrailConfig 输入参数中指定防护机制的配置信息。配置包括您要使用的防护机制的 ID 和版本。您还可以为防护机制启用跟踪功能，该功能可以提供关于被防护机制屏蔽的内容的信息。
- ApplyGuardrail API Request
-
POST /guardrail/{guardrailIdentifier}/version/{guardrailVersion}/apply HTTP/1.1 { "source": "INPUT" | "OUTPUT", "content": [ { "text": { "text": "string", } }, ] } - ApplyGuardrail API Response
-
{ "usage": { "topicPolicyUnits": "integer", "contentPolicyUnits": "integer", "wordPolicyUnits": "integer", "sensitiveInformationPolicyUnits": "integer", "sensitiveInformationPolicyFreeUnits": "integer", "contextualGroundingPolicyUnits": "integer" }, "action": "GUARDRAIL_INTERVENED" | "NONE", "output": [ // if guardrail intervened and output is masked we return request in same format // with masking // if guardrail intervened and blocked, output is a single text with canned message // if guardrail did not intervene, output is empty array { "text": "string", }, ], "assessments": [{ "topicPolicy": { "topics": [{ "name": "string", "type": "DENY", "action": "BLOCKED", }] }, "contentPolicy": { "filters": [{ "type": "INSULTS | HATE | SEXUAL | VIOLENCE | MISCONDUCT |PROMPT_ATTACK", "confidence": "NONE" | "LOW" | "MEDIUM" | "HIGH", "filterStrength": "NONE" | "LOW" | "MEDIUM" | "HIGH", "action": "BLOCKED" }] }, "wordPolicy": { "customWords": [{ "match": "string", "action": "BLOCKED" }], "managedWordLists": [{ "match": "string", "type": "PROFANITY", "action": "BLOCKED" }] }, "sensitiveInformationPolicy": { "piiEntities": [{ // for all types see: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GuardrailPiiEntityConfig.html#bedrock-Type-GuardrailPiiEntityConfig-type "type": "ADDRESS" | "AGE" | ..., "match": "string", "action": "BLOCKED" | "ANONYMIZED" }], "regexes": [{ "name": "string", "regex": "string", "match": "string", "action": "BLOCKED" | "ANONYMIZED" }], "contextualGroundingPolicy": { "filters": [{ "type": "GROUNDING | RELEVANCE", "threshold": "double", "score": "double", "action": "BLOCKED | NONE" }] }, "invocationMetrics": { "guardrailProcessingLatency": "integer", "usage": { "topicPolicyUnits": "integer", "contentPolicyUnits": "integer", "wordPolicyUnits": "integer", "sensitiveInformationPolicyUnits": "integer", "sensitiveInformationPolicyFreeUnits": "integer", "contextualGroundingPolicyUnits": "integer" }, "guardrailCoverage": { "textCharacters": { "guarded":"integer", "total": "integer" } } } }, "guardrailCoverage": { "textCharacters": { "guarded": "integer", "total": "integer" } } ] }
ApplyGuardrail API 应用场景示例
ApplyGuardrail 请求的输出取决于防护机制对传递的内容采取的操作。
-
如果防护机制进行了干预并且仅掩蔽了部分内容，则系统会返回原始内容，其中包含被掩蔽的部分。
-
如果防护机制进行了干预并屏蔽了请求内容，则输出字段将是单个文本，这是基于防护机制配置的固定消息。
-
如果防护机制未对请求内容采取任何操作，则输出数组为空。
- No guardrail intervention
-
请求示例
{ "source": "OUTPUT", "content": [ "text": { "text": "Hi, my name is Zaid. Which car brand is reliable?", } ] }防护机制没有进行干预时的响应
{ "usage": { "topicPolicyUnitsProcessed": 1, "contentPolicyUnitsProcessed": 1, "wordPolicyUnitsProcessed": 0, "sensitiveInformationPolicyFreeUnits": 0 }, "action": "NONE", "outputs": [], "assessments": [{}] } - Guardrails intervened with BLOCKED action
-
响应示例
{ "usage": { "topicPolicyUnitsProcessed": 1, "contentPolicyUnitsProcessed": 1, "wordPolicyUnitsProcessed": 0, "sensitiveInformationPolicyFreeUnits": 0 }, "action": "GUARDRAIL_INTERVENED", "outputs": [{ "text": "Configured guardrial canned message, i.e cannot respond", }], "assessments": [{ "topicPolicy": { "topics": [{ "name": "Cars", "type": "DENY", "action": "BLOCKED" }] }, "sensitiveInformationPolicy": { "piiEntities": [{ "type": "NAME", "match": "ZAID", "action": "ANONYMIZED" }], "regexes": [] } }] } - Guardrails intervened with MASKED action
-
响应示例
防护机制进行了干预，并对姓名进行了掩蔽（姓名被掩蔽）
{ "usage": { "topicPolicyUnitsProcessed": 1, "contentPolicyUnitsProcessed": 1, "wordPolicyUnitsProcessed": 0, "sensitiveInformationPolicyFreeUnits": 0 }, "action": "GUARDRAIL_INTERVENED", "outputs": [ { "text": "Hi, my name is {NAME}. Which car brand is reliable?" }, { "text": "Hello {NAME}, ABC Cars are reliable..", } ], "assessments": [{ "sensitiveInformationPolicy": { "piiEntities": [{ "type": "NAME", "match": "ZAID", "action": "MASKED" }], "regexes": [] } }] } - AWS CLI Example
-
输入示例
# Make sure preview CLI is downloaded and setup aws bedrock-runtime apply-guardrail \ --cli-input-json '{ "guardrailIdentifier": "someGuardrailId", "guardrailVersion": "DRAFT", "source": "INPUT", "content": [ { "text": { "text": "How should I invest for my retirement? I want to be able to generate $5,000 a month" } } ] }' \ --region us-east-1 \ --output json输出示例
{ "usage": { "topicPolicyUnits": 1, "contentPolicyUnits": 1, "wordPolicyUnits": 1, "sensitiveInformationPolicyUnits": 1, "sensitiveInformationPolicyFreeUnits": 0 }, "action": "GUARDRAIL_INTERVENED", "outputs": [ { "text": "I apologize, but I am not able to provide fiduciary advice. =" } ], "assessments": [ { "topicPolicy": { "topics": [ { "name": "Fiduciary Advice", "type": "DENY", "action": "BLOCKED" } ] } } ] }
包括带护栏的 Converse API
评估 Amazon Bedrock 资源的性能