Update README

This commit is contained in:
yangdx 2025-08-16 06:15:27 +08:00
parent bdd1169cfb
commit dc7a6e1c5b
4 changed files with 7 additions and 3 deletions

View file

@ -145,7 +145,7 @@ LightRAG对大型语言模型LLM的能力要求远高于传统RAG因为
- **Embedding模型**
- 高性能的Embedding模型对RAG至关重要。
- 推荐使用主流的多语言Embedding模型例如BAAI/bge-m3 和 text-embedding-3-large。
- **重要提示**在文档索引前必须确定使用的Embedding模型且在文档查询阶段必须沿用与索引阶段相同的模型。
- **重要提示**在文档索引前必须确定使用的Embedding模型且在文档查询阶段必须沿用与索引阶段相同的模型。有些存储例如PostgreSQL在首次建立数表的时候需要确定向量维度因此更换Embedding模型后需要删除向量相关库表以便让LightRAG重建新的库表。
- **Reranker模型配置**
- 配置Reranker模型能够显著提升LightRAG的检索效果。
- 启用Reranker模型后推荐将“mix模式”设为默认查询模式。

View file

@ -144,7 +144,7 @@ LightRAG's demands on the capabilities of Large Language Models (LLMs) are signi
- **Embedding Model**:
- A high-performance Embedding model is essential for RAG.
- We recommend using mainstream multilingual Embedding models, such as: `BAAI/bge-m3` and `text-embedding-3-large`.
- **Important Note**: The Embedding model must be determined before document indexing, and the same model must be used during the document query phase.
- **Important Note**: The Embedding model must be determined before document indexing, and the same model must be used during the document query phase. For certain storage solutions (e.g., PostgreSQL), the vector dimension must be defined upon initial table creation. Therefore, when changing embedding models, it is necessary to delete the existing vector-related tables and allow LightRAG to recreate them with the new dimensions.
- **Reranker Model Configuration**:
- Configuring a Reranker model can significantly enhance LightRAG's retrieval performance.
- When a Reranker model is enabled, it is recommended to set the "mix mode" as the default query mode.

View file

@ -1,4 +1,4 @@
# LightRAG 服务器和 Web 界面
# LightRAG 服务器和 WebUI
LightRAG 服务器旨在提供 Web 界面和 API 支持。Web 界面便于文档索引、知识图谱探索和简单的 RAG 查询界面。LightRAG 服务器还提供了与 Ollama 兼容的接口,旨在将 LightRAG 模拟为 Ollama 聊天模型。这使得 AI 聊天机器人(如 Open WebUI可以轻松访问 LightRAG。
@ -79,6 +79,8 @@ EMBEDDING_DIM=1024
# EMBEDDING_BINDING_API_KEY=your_api_key
```
> **重要提示**在文档索引前必须确定使用的Embedding模型且在文档查询阶段必须沿用与索引阶段相同的模型。有些存储例如PostgreSQL在首次建立数表的时候需要确定向量维度因此更换Embedding模型后需要删除向量相关库表以便让LightRAG重建新的库表。
### 启动 LightRAG 服务器
LightRAG 服务器支持两种运行模式:

View file

@ -79,6 +79,8 @@ EMBEDDING_DIM=1024
# EMBEDDING_BINDING_API_KEY=your_api_key
```
> **Important Note**: The Embedding model must be determined before document indexing, and the same model must be used during the document query phase. For certain storage solutions (e.g., PostgreSQL), the vector dimension must be defined upon initial table creation. Therefore, when changing embedding models, it is necessary to delete the existing vector-related tables and allow LightRAG to recreate them with the new dimensions.
### Starting LightRAG Server
The LightRAG Server supports two operational modes: