mirror of
https://github.com/HKUDS/LightRAG.git
synced 2026-01-04 10:50:46 +00:00
Update README
This commit is contained in:
yangdx
parent
feb30d8987
commit
bfa0844ecb
30
README-zh.md
30
README-zh.md
@ -824,7 +824,7 @@ rag = LightRAG(
|
||||
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;
|
||||
@ -849,6 +849,18 @@ rag = LightRAG(
|
||||
|
||||
</details>
|
||||
|
||||
### LightRAG实例间的数据隔离
|
||||
|
||||
通过 workspace 参数可以不同实现不同LightRAG实例之间的存储数据隔离。LightRAG在初始化后workspace就已经确定，之后修改workspace是无效的。下面是不同类型的存储实现工作空间的方式：
|
||||
|
||||
- **对于本地基于文件的数据库，数据隔离通过工作空间子目录实现：** JsonKVStorage, JsonDocStatusStorage, NetworkXStorage, NanoVectorDBStorage, FaissVectorDBStorage。
|
||||
- **对于将数据存储在集合（collection）中的数据库，通过在集合名称前添加工作空间前缀来实现：** RedisKVStorage, RedisDocStatusStorage, MilvusVectorDBStorage, QdrantVectorDBStorage, MongoKVStorage, MongoDocStatusStorage, MongoVectorDBStorage, MongoGraphStorage, PGGraphStorage。
|
||||
- **对于关系型数据库，数据隔离通过向表中添加 `workspace` 字段进行数据的逻辑隔离：** PGKVStorage, PGVectorStorage, PGDocStatusStorage。
|
||||
|
||||
* **对于Neo4j图数据库，通过label来实现数据的逻辑隔离**：Neo4JStorage
|
||||
|
||||
为了保持对遗留数据的兼容，在未配置工作空间时PostgreSQL的默认工作空间为`default`，Neo4j的默认工作空间为`base`。对于所有的外部存储，系统都提供了专用的工作空间环境变量，用于覆盖公共的 `WORKSPACE`环境变量配置。这些适用于指定存储类型的工作空间环境变量为：`REDIS_WORKSPACE`, `MILVUS_WORKSPACE`, `QDRANT_WORKSPACE`, `MONGODB_WORKSPACE`, `POSTGRES_WORKSPACE`, `NEO4J_WORKSPACE`。
|
||||
|
||||
## 编辑实体和关系
|
||||
|
||||
LightRAG现在支持全面的知识图谱管理功能，允许您在知识图谱中创建、编辑和删除实体和关系。
|
||||
@ -1170,17 +1182,17 @@ LightRAG 现已与 [RAG-Anything](https://github.com/HKUDS/RAG-Anything) 实现
|
||||
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
|
||||
from lightrag.utils import EmbeddingFunc
|
||||
import os
|
||||
|
||||
|
||||
async def load_existing_lightrag():
|
||||
# 首先，创建或加载现有的 LightRAG 实例
|
||||
lightrag_working_dir = "./existing_lightrag_storage"
|
||||
|
||||
|
||||
# 检查是否存在之前的 LightRAG 实例
|
||||
if os.path.exists(lightrag_working_dir) and os.listdir(lightrag_working_dir):
|
||||
print("✅ Found existing LightRAG instance, loading...")
|
||||
else:
|
||||
print("❌ No existing LightRAG instance found, will create new one")
|
||||
|
||||
|
||||
# 使用您的配置创建/加载 LightRAG 实例
|
||||
lightrag_instance = LightRAG(
|
||||
working_dir=lightrag_working_dir,
|
||||
@ -1203,10 +1215,10 @@ LightRAG 现已与 [RAG-Anything](https://github.com/HKUDS/RAG-Anything) 实现
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
# 初始化存储（如果有现有数据，这将加载现有数据）
|
||||
await lightrag_instance.initialize_storages()
|
||||
|
||||
|
||||
# 现在使用现有的 LightRAG 实例初始化 RAGAnything
|
||||
rag = RAGAnything(
|
||||
lightrag=lightrag_instance, # 传递现有的 LightRAG 实例
|
||||
@ -1235,20 +1247,20 @@ LightRAG 现已与 [RAG-Anything](https://github.com/HKUDS/RAG-Anything) 实现
|
||||
)
|
||||
# 注意：working_dir、llm_model_func、embedding_func 等都从 lightrag_instance 继承
|
||||
)
|
||||
|
||||
|
||||
# 查询现有的知识库
|
||||
result = await rag.query_with_multimodal(
|
||||
"What data has been processed in this LightRAG instance?",
|
||||
mode="hybrid"
|
||||
)
|
||||
print("Query result:", result)
|
||||
|
||||
|
||||
# 向现有的 LightRAG 实例添加新的多模态文档
|
||||
await rag.process_document_complete(
|
||||
file_path="path/to/new/multimodal_document.pdf",
|
||||
output_dir="./output"
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(load_existing_lightrag())
|
||||
```
|
||||
|
||||
30
README.md
30
README.md
@ -239,6 +239,7 @@ A full list of LightRAG init parameters:
|
||||
| **Parameter** | **Type** | **Explanation** | **Default** |
|
||||
|--------------|----------|-----------------|-------------|
|
||||
| **working_dir** | `str` | Directory where the cache will be stored | `lightrag_cache+timestamp` |
|
||||
| **workspace** | str | Workspace name for data isolation between different LightRAG Instances | |
|
||||
| **kv_storage** | `str` | Storage type for documents and text chunks. Supported types: `JsonKVStorage`,`PGKVStorage`,`RedisKVStorage`,`MongoKVStorage` | `JsonKVStorage` |
|
||||
| **vector_storage** | `str` | Storage type for embedding vectors. Supported types: `NanoVectorDBStorage`,`PGVectorStorage`,`MilvusVectorDBStorage`,`ChromaVectorDBStorage`,`FaissVectorDBStorage`,`MongoVectorDBStorage`,`QdrantVectorDBStorage` | `NanoVectorDBStorage` |
|
||||
| **graph_storage** | `str` | Storage type for graph edges and nodes. Supported types: `NetworkXStorage`,`Neo4JStorage`,`PGGraphStorage`,`AGEStorage` | `NetworkXStorage` |
|
||||
@ -796,7 +797,7 @@ For production level scenarios you will most likely want to leverage an enterpri
|
||||
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;
|
||||
@ -895,6 +896,17 @@ async def initialize_rag():
|
||||
|
||||
</details>
|
||||
|
||||
### Data Isolation Between LightRAG Instances
|
||||
|
||||
The `workspace` parameter ensures data isolation between different LightRAG instances. Once initialized, the `workspace` is immutable and cannot be changed.Here is how workspaces are implemented for different types of storage:
|
||||
|
||||
- **For local file-based databases, data isolation is achieved through workspace subdirectories:** `JsonKVStorage`, `JsonDocStatusStorage`, `NetworkXStorage`, `NanoVectorDBStorage`, `FaissVectorDBStorage`.
|
||||
- **For databases that store data in collections, it's done by adding a workspace prefix to the collection name:** `RedisKVStorage`, `RedisDocStatusStorage`, `MilvusVectorDBStorage`, `QdrantVectorDBStorage`, `MongoKVStorage`, `MongoDocStatusStorage`, `MongoVectorDBStorage`, `MongoGraphStorage`, `PGGraphStorage`.
|
||||
- **For relational databases, data isolation is achieved by adding a `workspace` field to the tables for logical data separation:** `PGKVStorage`, `PGVectorStorage`, `PGDocStatusStorage`.
|
||||
- **For the Neo4j graph database, logical data isolation is achieved through labels:** `Neo4JStorage`
|
||||
|
||||
To maintain compatibility with legacy data, the default workspace for PostgreSQL is `default` and for Neo4j is `base` when no workspace is configured. For all external storages, the system provides dedicated workspace environment variables to override the common `WORKSPACE` environment variable configuration. These storage-specific workspace environment variables are: `REDIS_WORKSPACE`, `MILVUS_WORKSPACE`, `QDRANT_WORKSPACE`, `MONGODB_WORKSPACE`, `POSTGRES_WORKSPACE`, `NEO4J_WORKSPACE`.
|
||||
|
||||
## Edit Entities and Relations
|
||||
|
||||
LightRAG now supports comprehensive knowledge graph management capabilities, allowing you to create, edit, and delete entities and relationships within your knowledge graph.
|
||||
@ -1219,17 +1231,17 @@ LightRAG now seamlessly integrates with [RAG-Anything](https://github.com/HKUDS/
|
||||
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
|
||||
from lightrag.utils import EmbeddingFunc
|
||||
import os
|
||||
|
||||
|
||||
async def load_existing_lightrag():
|
||||
# First, create or load an existing LightRAG instance
|
||||
lightrag_working_dir = "./existing_lightrag_storage"
|
||||
|
||||
|
||||
# Check if previous LightRAG instance exists
|
||||
if os.path.exists(lightrag_working_dir) and os.listdir(lightrag_working_dir):
|
||||
print("✅ Found existing LightRAG instance, loading...")
|
||||
else:
|
||||
print("❌ No existing LightRAG instance found, will create new one")
|
||||
|
||||
|
||||
# Create/Load LightRAG instance with your configurations
|
||||
lightrag_instance = LightRAG(
|
||||
working_dir=lightrag_working_dir,
|
||||
@ -1252,10 +1264,10 @@ 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
|
||||
@ -1284,20 +1296,20 @@ 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",
|
||||
output_dir="./output"
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(load_existing_lightrag())
|
||||
```
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user