gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README

Browse source
This commit is contained in:
zrguo 2025-06-26 16:17:00 +08:00
parent 145e3a238b
commit fc7a0329df
2 changed files with 169 additions and 112 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

118
README-zh.md
View file

@ -1108,40 +1108,98 @@ LightRAG 现已与 [RAG-Anything](https://github.com/HKUDS/RAG-Anything) 实现
pip install raganything pip install raganything
``` ```
2. 处理多模态文档： 2. 处理多模态文档：
```python <details>
import asyncio <summary> <b> RAGAnything 使用实例 </b></summary>
from raganything import RAGAnything ```python
from lightrag.llm.openai import openai_complete_if_cache, openai_embed import asyncio
from raganything import RAGAnything
from lightrag import LightRAG
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
from lightrag.utils import EmbeddingFunc
import os
async def main(): async def load_existing_lightrag():
# 使用LightRAG集成初始化RAGAnything # 首先，创建或加载现有的 LightRAG 实例
rag = RAGAnything( lightrag_working_dir = "./existing_lightrag_storage"
working_dir="./rag_storage",
llm_model_func=lambda prompt, **kwargs: openai_complete_if_cache(
"gpt-4o-mini", prompt, api_key="your-api-key", **kwargs
),
embedding_func=lambda texts: openai_embed(
texts, model="text-embedding-3-large", api_key="your-api-key"
),
embedding_dim=3072,
)
# 处理多模态文档 # 检查是否存在之前的 LightRAG 实例
await rag.process_document_complete( if os.path.exists(lightrag_working_dir) and os.listdir(lightrag_working_dir):
file_path="path/to/your/document.pdf", print("✅ Found existing LightRAG instance, loading...")
output_dir="./output" else:
) print("❌ No existing LightRAG instance found, will create new one")
# 查询多模态内容 # 使用您的配置创建/加载 LightRAG 实例
result = await rag.query_with_multimodal( lightrag_instance = LightRAG(
"图表中显示的主要发现是什么？", working_dir=lightrag_working_dir,
mode="hybrid" llm_model_func=lambda prompt, system_prompt=None, history_messages=[], **kwargs: openai_complete_if_cache(
) "gpt-4o-mini",
print(result) prompt,
system_prompt=system_prompt,
history_messages=history_messages,
api_key="your-api-key",
**kwargs,
),
embedding_func=EmbeddingFunc(
embedding_dim=3072,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
api_key=api_key,
base_url=base_url,
),
)
)
if __name__ == "__main__": # 初始化存储（如果有现有数据，这将加载现有数据）
asyncio.run(main()) 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
# 仅需要视觉模型用于多模态处理
vision_model_func=lambda prompt, system_prompt=None, history_messages=[], image_data=None, **kwargs: openai_complete_if_cache(
"gpt-4o",
"",
system_prompt=None,
history_messages=[],
messages=[
{"role": "system", "content": system_prompt} if system_prompt else None,
{"role": "user", "content": [
{"type": "text", "text": prompt},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}}
]} if image_data else {"role": "user", "content": prompt}
],
api_key="your-api-key",
**kwargs,
) if image_data else openai_complete_if_cache(
"gpt-4o-mini",
prompt,
system_prompt=system_prompt,
history_messages=history_messages,
api_key="your-api-key",
**kwargs,
)
# 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())
```
</details>
如需详细文档和高级用法，请参阅 [RAG-Anything 仓库](https://github.com/HKUDS/RAG-Anything)。 如需详细文档和高级用法，请参阅 [RAG-Anything 仓库](https://github.com/HKUDS/RAG-Anything)。

163
README.md
View file

@ -1159,99 +1159,98 @@ LightRAG now seamlessly integrates with [RAG-Anything](https://github.com/HKUDS/
pip install raganything pip install raganything
``` ```
2. Process multimodal documents: 2. Process multimodal documents:
<details>
<summary> <b> RAGAnything Usage Example </b></summary>
```python
import asyncio
from raganything import RAGAnything
from lightrag import LightRAG
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
from lightrag.utils import EmbeddingFunc
import os
<details> async def load_existing_lightrag():
<summary> <b> RAGAnything Usage Example </b></summary> # First, create or load an existing LightRAG instance
```python lightrag_working_dir = "./existing_lightrag_storage"
import asyncio
from raganything import RAGAnything
from lightrag import LightRAG
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
from lightrag.utils import EmbeddingFunc
import os
async def load_existing_lightrag(): # Check if previous LightRAG instance exists
# First, create or load an existing LightRAG instance if os.path.exists(lightrag_working_dir) and os.listdir(lightrag_working_dir):
lightrag_working_dir = "./existing_lightrag_storage" print("✅ Found existing LightRAG instance, loading...")
else:
print("❌ No existing LightRAG instance found, will create new one")
# Check if previous LightRAG instance exists # Create/Load LightRAG instance with your configurations
if os.path.exists(lightrag_working_dir) and os.listdir(lightrag_working_dir): lightrag_instance = LightRAG(
print("✅ Found existing LightRAG instance, loading...") working_dir=lightrag_working_dir,
else: llm_model_func=lambda prompt, system_prompt=None, history_messages=[], **kwargs: openai_complete_if_cache(
print("❌ No existing LightRAG instance found, will create new one") "gpt-4o-mini",
prompt,
# Create/Load LightRAG instance with your configurations system_prompt=system_prompt,
lightrag_instance = LightRAG( history_messages=history_messages,
working_dir=lightrag_working_dir, api_key="your-api-key",
llm_model_func=lambda prompt, system_prompt=None, history_messages=[], **kwargs: openai_complete_if_cache( **kwargs,
"gpt-4o-mini",
prompt,
system_prompt=system_prompt,
history_messages=history_messages,
api_key="your-api-key",
**kwargs,
),
embedding_func=EmbeddingFunc(
embedding_dim=3072,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
api_key=api_key,
base_url=base_url,
), ),
embedding_func=EmbeddingFunc(
embedding_dim=3072,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
api_key=api_key,
base_url=base_url,
),
)
) )
)
# Initialize storage (this will load existing data if available) # Initialize storage (this will load existing data if available)
await lightrag_instance.initialize_storages() await lightrag_instance.initialize_storages()
# Now initialize RAGAnything with the existing LightRAG instance # Now initialize RAGAnything with the existing LightRAG instance
rag = RAGAnything( rag = RAGAnything(
lightrag=lightrag_instance, # Pass the existing LightRAG instance lightrag=lightrag_instance, # Pass the existing LightRAG instance
# Only need vision model for multimodal processing # Only need vision model for multimodal processing
vision_model_func=lambda prompt, system_prompt=None, history_messages=[], image_data=None, **kwargs: openai_complete_if_cache( vision_model_func=lambda prompt, system_prompt=None, history_messages=[], image_data=None, **kwargs: openai_complete_if_cache(
"gpt-4o", "gpt-4o",
"", "",
system_prompt=None, system_prompt=None,
history_messages=[], history_messages=[],
messages=[ messages=[
{"role": "system", "content": system_prompt} if system_prompt else None, {"role": "system", "content": system_prompt} if system_prompt else None,
{"role": "user", "content": [ {"role": "user", "content": [
{"type": "text", "text": prompt}, {"type": "text", "text": prompt},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}} {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}}
]} if image_data else {"role": "user", "content": prompt} ]} if image_data else {"role": "user", "content": prompt}
], ],
api_key="your-api-key", api_key="your-api-key",
**kwargs, **kwargs,
) if image_data else openai_complete_if_cache( ) if image_data else openai_complete_if_cache(
"gpt-4o-mini", "gpt-4o-mini",
prompt, prompt,
system_prompt=system_prompt, system_prompt=system_prompt,
history_messages=history_messages, history_messages=history_messages,
api_key="your-api-key", api_key="your-api-key",
**kwargs, **kwargs,
)
# Note: working_dir, llm_model_func, embedding_func, etc. are inherited from lightrag_instance
) )
# Note: working_dir, llm_model_func, embedding_func, etc. are inherited from lightrag_instance
)
# Query the existing knowledge base # Query the existing knowledge base
result = await rag.query_with_multimodal( result = await rag.query_with_multimodal(
"What data has been processed in this LightRAG instance?", "What data has been processed in this LightRAG instance?",
mode="hybrid" mode="hybrid"
) )
print("Query result:", result) print("Query result:", result)
# Add new multimodal documents to the existing LightRAG instance # Add new multimodal documents to the existing LightRAG instance
await rag.process_document_complete( await rag.process_document_complete(
file_path="path/to/new/multimodal_document.pdf", file_path="path/to/new/multimodal_document.pdf",
output_dir="./output" output_dir="./output"
) )
if __name__ == "__main__": if __name__ == "__main__":
asyncio.run(load_existing_lightrag()) asyncio.run(load_existing_lightrag())
``` ```
</details> </details>
For detailed documentation and advanced usage, please refer to the [RAG-Anything repository](https://github.com/HKUDS/RAG-Anything). For detailed documentation and advanced usage, please refer to the [RAG-Anything repository](https://github.com/HKUDS/RAG-Anything).