Unverified50% confidenceFactExact time
Deckhand adopts a RAG (retrieval-augmented generation) architecture: it first vectorizes the user's question, retrieves the most semantically relevant passages from the knowledge base, and then hands them to the large model to generate an answer.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified工程界普遍采用RAG架构：将历史信息切分成语义块，通过嵌入模型转化为向量存入向量数据库（如Faiss、Pinecone、Weaviate），用户提问时计算余弦相似度检索最相关片段72% similarUnverifiedWindsurf的Cascade功能基于检索增强生成（RAG）技术，会对整个代码仓库建立向量索引72% similarUnverifiedRetrieval-Augmented Generation (RAG) architecture decouples knowledge storage from language generation, evolving from simple vector similarity retrieval to hybrid retrieval combining BM25 and semantic vectors, iterative retrieval, and Graph RAG.72% similarUnverifiedModern RAG systems widely adopt vector retrieval technology, converting text into high-dimensional vectors via embedding models and computing cosine similarity to find relevant documents.71% similarVerifiedRetrieval-Augmented Generation (RAG) splits codebases into semantic segments via vector databases and dynamically retrieves the most relevant content to inject into the context when an AI handles specific tasks.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019811API
curl https://kongchang.com/api/v1/knowledge/claims/1019811MCP
get_claim(id=1019811)