LightRAG/examples/lightrag_zhipu_demo.py
2025-03-03 18:40:03 +08:00

81 lines
2.0 KiB
Python

import os
import logging
import asyncio
from lightrag import LightRAG, QueryParam
from lightrag.llm.zhipu import zhipu_complete, zhipu_embedding
from lightrag.utils import EmbeddingFunc
from lightrag.kg.shared_storage import initialize_pipeline_status
WORKING_DIR = "./dickens"
logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR)
api_key = os.environ.get("ZHIPUAI_API_KEY")
if api_key is None:
raise Exception("Please set ZHIPU_API_KEY in your environment")
async def initialize_rag():
rag = LightRAG(
working_dir=WORKING_DIR,
llm_model_func=zhipu_complete,
llm_model_name="glm-4-flashx", # Using the most cost/performance balance model, but you can change it here.
llm_model_max_async=4,
llm_model_max_token_size=32768,
embedding_func=EmbeddingFunc(
embedding_dim=2048, # Zhipu embedding-3 dimension
max_token_size=8192,
func=lambda texts: zhipu_embedding(texts),
),
)
await rag.initialize_storages()
await initialize_pipeline_status()
return rag
def main():
# Initialize RAG instance
rag = asyncio.run(initialize_rag())
with open("./book.txt", "r", encoding="utf-8") 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")
)
)
if __name__ == "__main__":
main()