From aba46213a700607e8638409c9a9702f2fe65ebf3 Mon Sep 17 00:00:00 2001 From: yangdx Date: Wed, 30 Jul 2025 13:13:59 +0800 Subject: [PATCH] Update README --- README-zh.md | 43 ++----------------------------------------- README.md | 50 +++----------------------------------------------- 2 files changed, 5 insertions(+), 88 deletions(-) diff --git a/README-zh.md b/README-zh.md index 42ab71f5..5603ad99 100644 --- a/README-zh.md +++ b/README-zh.md @@ -781,7 +781,6 @@ async def initialize_rag(): 使用Faiss进行存储 在使用Faiss向量数据库之前必须手工安装`faiss-cpu`或`faiss-gpu`。 - - 安装所需依赖： ``` @@ -818,51 +817,13 @@ rag = LightRAG(
使用PostgreSQL进行存储 -对于生产级场景，您很可能想要利用企业级解决方案。PostgreSQL可以为您提供一站式解决方案，作为KV存储、向量数据库（pgvector）和图数据库（apache AGE）。 +对于生产级场景，您很可能想要利用企业级解决方案。PostgreSQL可以为您提供一站式解决方案，作为KV存储、向量数据库（pgvector）和图数据库（apache AGE）。支持 PostgreSQL 版本为16.6或以上。 * PostgreSQL很轻量，整个二进制发行版包括所有必要的插件可以压缩到40MB：参考[Windows发布版](https://github.com/ShanGor/apache-age-windows/releases/tag/PG17%2Fv1.5.0-rc0)，它在Linux/Mac上也很容易安装。 * 如果您是初学者并想避免麻烦，推荐使用docker，请从这个镜像开始（请务必阅读概述）：https://hub.docker.com/r/shangor/postgres-for-rag * 如何开始？参考：[examples/lightrag_zhipu_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_zhipu_postgres_demo.py) -* 为AGE创建索引示例：（如有必要，将下面的`dickens`改为您的图名） - ```sql - load 'age'; - SET search_path = ag_catalog, "$user", public; - CREATE INDEX CONCURRENTLY entity_p_idx ON dickens."Entity" (id); - CREATE INDEX CONCURRENTLY vertex_p_idx ON dickens."_ag_label_vertex" (id); - CREATE INDEX CONCURRENTLY directed_p_idx ON dickens."DIRECTED" (id); - CREATE INDEX CONCURRENTLY directed_eid_idx ON dickens."DIRECTED" (end_id); - CREATE INDEX CONCURRENTLY directed_sid_idx ON dickens."DIRECTED" (start_id); - CREATE INDEX CONCURRENTLY directed_seid_idx ON dickens."DIRECTED" (start_id,end_id); - CREATE INDEX CONCURRENTLY edge_p_idx ON dickens."_ag_label_edge" (id); - CREATE INDEX CONCURRENTLY edge_sid_idx ON dickens."_ag_label_edge" (start_id); - CREATE INDEX CONCURRENTLY edge_eid_idx ON dickens."_ag_label_edge" (end_id); - CREATE INDEX CONCURRENTLY edge_seid_idx ON dickens."_ag_label_edge" (start_id,end_id); - create INDEX CONCURRENTLY vertex_idx_node_id ON dickens."_ag_label_vertex" (ag_catalog.agtype_access_operator(properties, '"node_id"'::agtype)); - create INDEX CONCURRENTLY entity_idx_node_id ON dickens."Entity" (ag_catalog.agtype_access_operator(properties, '"node_id"'::agtype)); - CREATE INDEX CONCURRENTLY entity_node_id_gin_idx ON dickens."Entity" using gin(properties); - ALTER TABLE dickens."DIRECTED" CLUSTER ON directed_sid_idx; - -- 如有必要可以删除 - drop INDEX entity_p_idx; - drop INDEX vertex_p_idx; - drop INDEX directed_p_idx; - drop INDEX directed_eid_idx; - drop INDEX directed_sid_idx; - drop INDEX directed_seid_idx; - drop INDEX edge_p_idx; - drop INDEX edge_sid_idx; - drop INDEX edge_eid_idx; - drop INDEX edge_seid_idx; - drop INDEX vertex_idx_node_id; - drop INDEX entity_idx_node_id; - drop INDEX entity_node_id_gin_idx; - ``` -* Apache AGE的已知问题：发布版本存在以下问题： - > 您可能会发现节点/边的属性是空的。 - > 这是发布版本的已知问题：https://github.com/apache/age/pull/1721 - > - > 您可以从源代码编译AGE来修复它。 - > +* Apache AGE的性能不如Neo4j。最求高性能的图数据库请使用Noe4j。
diff --git a/README.md b/README.md index 74ac132c..a3abefd8 100644 --- a/README.md +++ b/README.md @@ -792,58 +792,18 @@ see test_neo4j.py for a working example.
Using PostgreSQL for Storage -For production level scenarios you will most likely want to leverage an enterprise solution. PostgreSQL can provide a one-stop solution for you as KV store, VectorDB (pgvector) and GraphDB (apache AGE). +For production level scenarios you will most likely want to leverage an enterprise solution. PostgreSQL can provide a one-stop solution for you as KV store, VectorDB (pgvector) and GraphDB (apache AGE). PostgreSQL version 16.6 or higher is supported. * PostgreSQL is lightweight,the whole binary distribution including all necessary plugins can be zipped to 40MB: Ref to [Windows Release](https://github.com/ShanGor/apache-age-windows/releases/tag/PG17%2Fv1.5.0-rc0) as it is easy to install for Linux/Mac. * If you prefer docker, please start with this image if you are a beginner to avoid hiccups (DO read the overview): https://hub.docker.com/r/shangor/postgres-for-rag * How to start? Ref to: [examples/lightrag_zhipu_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_zhipu_postgres_demo.py) -* Create index for AGE example: (Change below `dickens` to your graph name if necessary) - ```sql - load 'age'; - SET search_path = ag_catalog, "$user", public; - CREATE INDEX CONCURRENTLY entity_p_idx ON dickens."Entity" (id); - CREATE INDEX CONCURRENTLY vertex_p_idx ON dickens."_ag_label_vertex" (id); - CREATE INDEX CONCURRENTLY directed_p_idx ON dickens."DIRECTED" (id); - CREATE INDEX CONCURRENTLY directed_eid_idx ON dickens."DIRECTED" (end_id); - CREATE INDEX CONCURRENTLY directed_sid_idx ON dickens."DIRECTED" (start_id); - CREATE INDEX CONCURRENTLY directed_seid_idx ON dickens."DIRECTED" (start_id,end_id); - CREATE INDEX CONCURRENTLY edge_p_idx ON dickens."_ag_label_edge" (id); - CREATE INDEX CONCURRENTLY edge_sid_idx ON dickens."_ag_label_edge" (start_id); - CREATE INDEX CONCURRENTLY edge_eid_idx ON dickens."_ag_label_edge" (end_id); - CREATE INDEX CONCURRENTLY edge_seid_idx ON dickens."_ag_label_edge" (start_id,end_id); - create INDEX CONCURRENTLY vertex_idx_node_id ON dickens."_ag_label_vertex" (ag_catalog.agtype_access_operator(properties, '"node_id"'::agtype)); - create INDEX CONCURRENTLY entity_idx_node_id ON dickens."Entity" (ag_catalog.agtype_access_operator(properties, '"node_id"'::agtype)); - CREATE INDEX CONCURRENTLY entity_node_id_gin_idx ON dickens."Entity" using gin(properties); - ALTER TABLE dickens."DIRECTED" CLUSTER ON directed_sid_idx; - - -- drop if necessary - drop INDEX entity_p_idx; - drop INDEX vertex_p_idx; - drop INDEX directed_p_idx; - drop INDEX directed_eid_idx; - drop INDEX directed_sid_idx; - drop INDEX directed_seid_idx; - drop INDEX edge_p_idx; - drop INDEX edge_sid_idx; - drop INDEX edge_eid_idx; - drop INDEX edge_seid_idx; - drop INDEX vertex_idx_node_id; - drop INDEX entity_idx_node_id; - drop INDEX entity_node_id_gin_idx; - ``` -* Known issue of the Apache AGE: The released versions got below issue: - > You might find that the properties of the nodes/edges are empty. - > It is a known issue of the release version: https://github.com/apache/age/pull/1721 - > - > You can Compile the AGE from source code and fix it. - > +* For high-performance graph database requirements, Neo4j is recommended as Apache AGE's performance is not as competitive.
Using Faiss for Storage -You must manually install faiss-cpu or faiss-gpu before using FAISS vector db. -Manually install `faiss-cpu` or `faiss-gpu` before using FAISS vector db. +Before using Faiss vector database, you must manually install `faiss-cpu` or `faiss-gpu`. - Install the required dependencies: @@ -1280,10 +1240,8 @@ LightRAG now seamlessly integrates with [RAG-Anything](https://github.com/HKUDS/ ), ) ) - # Initialize storage (this will load existing data if available) await lightrag_instance.initialize_storages() - # Now initialize RAGAnything with the existing LightRAG instance rag = RAGAnything( lightrag=lightrag_instance, # Pass the existing LightRAG instance @@ -1312,14 +1270,12 @@ LightRAG now seamlessly integrates with [RAG-Anything](https://github.com/HKUDS/ ) # Note: working_dir, llm_model_func, embedding_func, etc. are inherited from lightrag_instance ) - # Query the existing knowledge base result = await rag.query_with_multimodal( "What data has been processed in this LightRAG instance?", mode="hybrid" ) print("Query result:", result) - # Add new multimodal documents to the existing LightRAG instance await rag.process_document_complete( file_path="path/to/new/multimodal_document.pdf",