vector-composition

About vector-composition

Compose semantic vectors in Scry -- embed concepts as @handles, search by cosine distance, debias with vector algebra, and diagnose signal loss. Use when the task involves: semantic search, embedding, vector, cosine distance, <=>, "X but not Y", debias, embed this concept, @handle, vibe algebra, concept vector. NOT for: word2vec training, fine-tuning embeddings, local vector databases (FAISS, Pinecone, Chroma), or plain keyword/SQL search (use scry).

在 Scry 中合成语义向量——将概念作为 @handles 嵌入、按余弦距离搜索、用向量代数去偏并诊断信号损失。适用于以下任务：语义搜索、嵌入（embedding）、向量、余弦距离、<=>、"X 但不是 Y"、去偏（debias）、嵌入此概念、@handle、vibe algebra、概念向量。不适用于：word2vec 训练、嵌入的微调、本地向量数据库（FAISS、Pinecone、Chroma）或纯关键字/SQL 搜索（此类请使用 scry）。