Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Source
Qwen Team
Author
Qwen Team
Date
Terms in this piece · Glossary
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
reranking — A second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
Why it matters
open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → (Apache 2.0) multilingual embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition → and rerankingA second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.Full definition → models built on Qwen3 give you a self-hostable alternative to proprietary embedding APIs for RAGRetrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.Full definition → and retrieval pipelines, with competitive benchmark performance across many languages.
Key quotes
“We release Qwen3 Embedding series, a new proprietary model of the Qwen model family.”