File size: 3,079 Bytes
c4d8067 c87e4c5 8b3b01c c87e4c5 c832152 c87e4c5 275e33e 8b3b01c c87e4c5 275e33e c87e4c5 8b3b01c 9f4950c 8b3b01c c87e4c5 |
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 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
###########################################
# TiDB storage implementation is deprecated
###########################################
import asyncio
import os
import numpy as np
from lightrag import LightRAG, QueryParam
from lightrag.llm import siliconcloud_embedding, openai_complete_if_cache
from lightrag.utils import EmbeddingFunc
from lightrag.kg.shared_storage import initialize_pipeline_status
WORKING_DIR = "./dickens"
# We use SiliconCloud API to call LLM on Oracle Cloud
# More docs here https://docs.siliconflow.cn/introduction
BASE_URL = "https://api.siliconflow.cn/v1/"
APIKEY = ""
CHATMODEL = ""
EMBEDMODEL = ""
os.environ["TIDB_HOST"] = ""
os.environ["TIDB_PORT"] = ""
os.environ["TIDB_USER"] = ""
os.environ["TIDB_PASSWORD"] = ""
os.environ["TIDB_DATABASE"] = "lightrag"
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(
CHATMODEL,
prompt,
system_prompt=system_prompt,
history_messages=history_messages,
api_key=APIKEY,
base_url=BASE_URL,
**kwargs,
)
async def embedding_func(texts: list[str]) -> np.ndarray:
return await siliconcloud_embedding(
texts,
# model=EMBEDMODEL,
api_key=APIKEY,
)
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
async def initialize_rag():
# Detect embedding dimension
embedding_dimension = await get_embedding_dim()
print(f"Detected embedding dimension: {embedding_dimension}")
# Initialize LightRAG
# We use TiDB DB as the KV/vector
rag = LightRAG(
enable_llm_cache=False,
working_dir=WORKING_DIR,
chunk_token_size=512,
llm_model_func=llm_model_func,
embedding_func=EmbeddingFunc(
embedding_dim=embedding_dimension,
max_token_size=512,
func=embedding_func,
),
kv_storage="TiDBKVStorage",
vector_storage="TiDBVectorDBStorage",
graph_storage="TiDBGraphStorage",
)
await rag.initialize_storages()
await initialize_pipeline_status()
return rag
async def main():
try:
# Initialize RAG instance
rag = await initialize_rag()
with open("./book.txt", "r", encoding="utf-8") as f:
rag.insert(f.read())
# Perform search in different modes
modes = ["naive", "local", "global", "hybrid"]
for mode in modes:
print("=" * 20, mode, "=" * 20)
print(
await rag.aquery(
"What are the top themes in this story?",
param=QueryParam(mode=mode),
)
)
print("-" * 100, "\n")
except Exception as e:
print(f"An error occurred: {e}")
if __name__ == "__main__":
asyncio.run(main())
|