---
title: "BAAI"
type: entity
tags: [embedding, open-source, chinese-optimized]
sources: ["RAG从入门到精通系列1：基础RAG"]
last_updated: 2026-04-16
---

## Basic Information
- **Type**: Embedding Model Series
- **Source**: RAG从入门到精通系列1：基础RAG

## Definition
BAAI (Beijing Academy of Artificial Intelligence) provides an open-source series of embedding models (e.g., BAAI/bge series) that convert text into embedding vectors for use in RAG systems.

## Key Models
- **BAAI BGE Series**: Chinese-optimized open-source embedding models
- Models can convert text to fixed-length embedding vectors
- Context Window typically 512~8192 tokens

## Applications
- [[Embedding]]：BAAI models are used to create embedding vectors
- [[RAG]]：BAAI embeddings enable semantic search in RAG systems

## Related Concepts
- [[Embedding]]：The technology BAAI models implement
- [[向量数据库]]：Where BAAI embeddings are stored