mirror of
https://github.com/HKUDS/LightRAG.git
synced 2025-10-31 17:59:36 +00:00
84e3b9e44b
- 在 LightRAG 类中添加 embedding_cache_config配置项 - 实现基于 embedding 相似度的缓存查询和存储 - 添加量化和反量化函数，用于压缩 embedding 数据 - 新增示例演示 embedding 缓存的使用
113 lines
2.9 KiB
Python
113 lines
2.9 KiB
Python
import os
|
|
import asyncio
|
|
from lightrag import LightRAG, QueryParam
|
|
from lightrag.llm import openai_complete_if_cache, openai_embedding
|
|
from lightrag.utils import EmbeddingFunc
|
|
import numpy as np
|
|
|
|
WORKING_DIR = "./dickens"
|
|
|
|
if not os.path.exists(WORKING_DIR):
|
|
os.mkdir(WORKING_DIR)
|
|
|
|
|
|
async def llm_model_func(
|
|
prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
|
|
) -> str:
|
|
return await openai_complete_if_cache(
|
|
"solar-mini",
|
|
prompt,
|
|
system_prompt=system_prompt,
|
|
history_messages=history_messages,
|
|
api_key=os.getenv("UPSTAGE_API_KEY"),
|
|
base_url="https://api.upstage.ai/v1/solar",
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
async def embedding_func(texts: list[str]) -> np.ndarray:
|
|
return await openai_embedding(
|
|
texts,
|
|
model="solar-embedding-1-large-query",
|
|
api_key=os.getenv("UPSTAGE_API_KEY"),
|
|
base_url="https://api.upstage.ai/v1/solar",
|
|
)
|
|
|
|
|
|
async def get_embedding_dim():
|
|
test_text = ["This is a test sentence."]
|
|
embedding = await embedding_func(test_text)
|
|
embedding_dim = embedding.shape[1]
|
|
return embedding_dim
|
|
|
|
|
|
# function test
|
|
async def test_funcs():
|
|
result = await llm_model_func("How are you?")
|
|
print("llm_model_func: ", result)
|
|
|
|
result = await embedding_func(["How are you?"])
|
|
print("embedding_func: ", result)
|
|
|
|
|
|
# asyncio.run(test_funcs())
|
|
|
|
|
|
async def main():
|
|
try:
|
|
embedding_dimension = await get_embedding_dim()
|
|
print(f"Detected embedding dimension: {embedding_dimension}")
|
|
|
|
rag = LightRAG(
|
|
working_dir=WORKING_DIR,
|
|
embedding_cache_config={
|
|
"enabled": True,
|
|
"similarity_threshold": 0.90,
|
|
},
|
|
llm_model_func=llm_model_func,
|
|
embedding_func=EmbeddingFunc(
|
|
embedding_dim=embedding_dimension,
|
|
max_token_size=8192,
|
|
func=embedding_func,
|
|
),
|
|
)
|
|
|
|
with open("./book.txt", "r", encoding="utf-8") as f:
|
|
await rag.ainsert(f.read())
|
|
|
|
# Perform naive search
|
|
print(
|
|
await rag.aquery(
|
|
"What are the top themes in this story?", param=QueryParam(mode="naive")
|
|
)
|
|
)
|
|
|
|
# Perform local search
|
|
print(
|
|
await rag.aquery(
|
|
"What are the top themes in this story?", param=QueryParam(mode="local")
|
|
)
|
|
)
|
|
|
|
# Perform global search
|
|
print(
|
|
await rag.aquery(
|
|
"What are the top themes in this story?",
|
|
param=QueryParam(mode="global"),
|
|
)
|
|
)
|
|
|
|
# Perform hybrid search
|
|
print(
|
|
await rag.aquery(
|
|
"What are the top themes in this story?",
|
|
param=QueryParam(mode="hybrid"),
|
|
)
|
|
)
|
|
except Exception as e:
|
|
print(f"An error occurred: {e}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|