跳到正文
菜单
简体中文

推荐技术栈

你在构建什么?Semantic search

每个位置一项技术,并说明推荐理由以及可以改用什么。

Embedding

concept

Embedding

Dense numeric vector representing the meaning of a piece of text.

Why editorial

Everything else in semantic search depends on the quality of the embedding: a weak one makes good ranking impossible.

Vector database

database

Weaviate

Open-source vector database with hybrid keyword and vector search built in.

Why 由图谱推导

Weaviate uses Embedding

来源

Base model

model

BERT

Encoder-only Transformer pre-trained with masked language modelling.

Why 由图谱推导

Reranking based on BERT

来源

Reranking

technique

Reranking

Second-stage ordering of retrieved candidates by a more accurate scoring model.

Why 由图谱推导

Retrieve-then-rerank is the standard shape of a semantic search pipeline.

来源