Architecture

基于向量的记忆模式，其中文本被分块、嵌入并存储在向量数据库中。查询时，问题被嵌入，运行向量搜索，重新排序候选，并将顶部结果注入提示。智能体感觉像记住一切而不会产生幻觉的地方。

完整 FlowZap 代码

User {
  n1: circle label="Ask question"
  n2: rectangle label="See answer with references"
  n1.handle(right) -> Agent.n3.handle(left)
  Agent.n12.handle(right) -> n2.handle(left)
}

Agent {
  n3: rectangle label="Receive query"
  n4: rectangle label="Build memory search query"
  n5: rectangle label="Send to retriever"
  n6: rectangle label="Inject recalled memories"
  n7: rectangle label="Assemble final prompt"
  n8: rectangle label="Call LLM"
  n12: rectangle label="Return answer"
  n3.handle(right) -> n4.handle(left)
  n4.handle(right) -> n5.handle(left)
  n5.handle(bottom) -> Retriever.n9.handle(top) [label="Semantic query"]
  n6.handle(right) -> n7.handle(left)
  n7.handle(right) -> n8.handle(left)
  n8.handle(right) -> LLM.n13.handle(left)
}

Retriever {
  n9: rectangle label="Embed query"
  n10: rectangle label="Search vector store"
  n11: rectangle label="Rerank top memories"
  n9.handle(right) -> n10.handle(left)
  n10.handle(right) -> n11.handle(left)
  n11.handle(top) -> Agent.n6.handle(bottom) [label="Top memories"]
}

VectorDB {
  n13: rectangle label="Vector index"
  Retriever.n10.handle(bottom) -> n13.handle(top) [label="Similarity search"]
}

LLM {
  n14: rectangle label="Answer using recalled facts"
  n14.handle(right) -> Agent.n12.handle(left)
}

相关模板