File size: 2,001 Bytes
7b67ad7 0553d6a 7b67ad7 94cd4d3 7b67ad7 af81714 7b67ad7 af81714 9590c46 7b67ad7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
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"))
)
|