知识卡片
参数结构校验不等于业务有效
JSON Schema可约束字段、类型、枚举和必填项,有助于拒绝格式错误。仍需验证参数是否符合业务范围、路径权限和工具能力;合法JSON也可能表达错误或未经授权的操作。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 外部工具与智能体
原书出处 · 1 处
- · 查看原书依据
required information and retrieval engines that can retrieve relevant data from data stores given a query. The retrieval engine can be powered by an LLM itself, or it can be as simple as a keyword-matching algorithm. The data store(s) can be a repository of data like a database, knowledge graph, vector database, or even just a collection of text files. Data in the data store
参考来源
- 位置:《Designing Large Language Model Applications》第10章《外部工具与智能体》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch10.html)
- 结论依据:摘录中关于参数结构校验不等于业务有效的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:required information and retrieval engines that can retrieve relevant data from data stores given a query. The retrieval engine can be powered by an LLM itself, or it can be as simple as a keyword-matching algorithm. The data store(s) can be a repository of data like a database, knowledge graph, vector database, or even just a collection of text files. Data in the data store