mirror of
https://github.com/HKUDS/LightRAG.git
synced 2025-10-31 09:49:54 +00:00
81 lines
2.0 KiB
Python
81 lines
2.0 KiB
Python
import os
|
|
import asyncio
|
|
from lightrag import LightRAG, QueryParam
|
|
from lightrag.llm.openai import openai_complete_if_cache
|
|
from lightrag.llm.siliconcloud import siliconcloud_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(
|
|
"Qwen/Qwen2.5-7B-Instruct",
|
|
prompt,
|
|
system_prompt=system_prompt,
|
|
history_messages=history_messages,
|
|
api_key=os.getenv("SILICONFLOW_API_KEY"),
|
|
base_url="https://api.siliconflow.cn/v1/",
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
async def embedding_func(texts: list[str]) -> np.ndarray:
|
|
return await siliconcloud_embedding(
|
|
texts,
|
|
model="netease-youdao/bce-embedding-base_v1",
|
|
api_key=os.getenv("SILICONFLOW_API_KEY"),
|
|
max_token_size=512,
|
|
)
|
|
|
|
|
|
# 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())
|
|
|
|
|
|
rag = LightRAG(
|
|
working_dir=WORKING_DIR,
|
|
llm_model_func=llm_model_func,
|
|
embedding_func=EmbeddingFunc(
|
|
embedding_dim=768, max_token_size=512, func=embedding_func
|
|
),
|
|
)
|
|
|
|
|
|
with open("./book.txt") as f:
|
|
rag.insert(f.read())
|
|
|
|
# Perform naive search
|
|
print(
|
|
rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))
|
|
)
|
|
|
|
# Perform local search
|
|
print(
|
|
rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))
|
|
)
|
|
|
|
# Perform global search
|
|
print(
|
|
rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))
|
|
)
|
|
|
|
# Perform hybrid search
|
|
print(
|
|
rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
|
|
)
|