48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
|
import asyncio
|
|||
|
|
|
|||
|
|
from lightrag import LightRAG
|
|||
|
|
from lightrag.kg.shared_storage import initialize_pipeline_status
|
|||
|
|
from raganything import RAGAnything
|
|||
|
|
|
|||
|
|
from Util.RagUtil import create_llm_model_func, create_vision_model_func, create_embedding_func
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def load_existing_lightrag():
|
|||
|
|
# 索引位置
|
|||
|
|
#WORKING_DIR = "./Topic/Chemistry"
|
|||
|
|
#WORKING_DIR = "./Topic/DongHua"
|
|||
|
|
#WORKING_DIR = "./Topic/Chinese"
|
|||
|
|
WORKING_DIR = "./Topic/Math"
|
|||
|
|
|
|||
|
|
# 创建 LLM 模型自定义函数
|
|||
|
|
llm_model_func = create_llm_model_func()
|
|||
|
|
# 创建可视模型自定义函数
|
|||
|
|
vision_model_func = create_vision_model_func(llm_model_func)
|
|||
|
|
# 创建嵌入模型自定义函数
|
|||
|
|
embedding_func = create_embedding_func()
|
|||
|
|
# 声明LightRAG实例
|
|||
|
|
lightrag_instance = LightRAG(
|
|||
|
|
working_dir=WORKING_DIR,
|
|||
|
|
llm_model_func=llm_model_func,
|
|||
|
|
embedding_func=embedding_func
|
|||
|
|
)
|
|||
|
|
# 初始化
|
|||
|
|
await lightrag_instance.initialize_storages()
|
|||
|
|
await initialize_pipeline_status()
|
|||
|
|
# 创建RAGAnything实例，依托于LightRAG实例
|
|||
|
|
rag = RAGAnything(
|
|||
|
|
lightrag=lightrag_instance,
|
|||
|
|
vision_model_func=vision_model_func,
|
|||
|
|
)
|
|||
|
|
# 查询
|
|||
|
|
result = await rag.aquery(
|
|||
|
|
#query="氧化铁和硝酸的反应方程式?",
|
|||
|
|
query="文档介绍了哪些内容？",
|
|||
|
|
mode="hybrid"
|
|||
|
|
)
|
|||
|
|
print("查询结果:", result)
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
asyncio.run(load_existing_lightrag())
|