69358d830d
Format entire codebase with ruff and add type hints across all modules: - Apply ruff formatting to all Python files (121 files, 17K insertions) - Add type hints to function signatures throughout lightrag core and API - Update test suite with improved type annotations and docstrings - Add pyrightconfig.json for static type checking configuration - Create prompt_optimized.py and test_extraction_prompt_ab.py test files - Update ruff.toml and .gitignore for improved linting configuration - Standardize code style across examples, reproduce scripts, and utilities
92 lines
2.6 KiB
Python
92 lines
2.6 KiB
Python
import asyncio
|
|
import os
|
|
|
|
from lightrag import LightRAG, QueryParam
|
|
from lightrag.llm.ollama import ollama_embed, openai_complete_if_cache
|
|
from lightrag.utils import EmbeddingFunc
|
|
|
|
# WorkingDir
|
|
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
WORKING_DIR = os.path.join(ROOT_DIR, 'myKG')
|
|
if not os.path.exists(WORKING_DIR):
|
|
os.mkdir(WORKING_DIR)
|
|
print(f'WorkingDir: {WORKING_DIR}')
|
|
|
|
# redis
|
|
os.environ['REDIS_URI'] = 'redis://localhost:6379'
|
|
|
|
# neo4j
|
|
BATCH_SIZE_NODES = 500
|
|
BATCH_SIZE_EDGES = 100
|
|
os.environ['NEO4J_URI'] = 'neo4j://localhost:7687'
|
|
os.environ['NEO4J_USERNAME'] = 'neo4j'
|
|
os.environ['NEO4J_PASSWORD'] = '12345678'
|
|
|
|
# milvus
|
|
os.environ['MILVUS_URI'] = 'http://localhost:19530'
|
|
os.environ['MILVUS_USER'] = 'root'
|
|
os.environ['MILVUS_PASSWORD'] = 'Milvus'
|
|
os.environ['MILVUS_DB_NAME'] = 'lightrag'
|
|
|
|
|
|
async def llm_model_func(prompt, system_prompt=None, history_messages=None, keyword_extraction=False, **kwargs) -> str:
|
|
if history_messages is None:
|
|
history_messages = []
|
|
return await openai_complete_if_cache(
|
|
'deepseek-chat',
|
|
prompt,
|
|
system_prompt=system_prompt,
|
|
history_messages=history_messages,
|
|
api_key='',
|
|
base_url='',
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
embedding_func = EmbeddingFunc(
|
|
embedding_dim=768,
|
|
max_token_size=512,
|
|
func=lambda texts: ollama_embed(texts, embed_model='shaw/dmeta-embedding-zh', host='http://117.50.173.35:11434'),
|
|
)
|
|
|
|
|
|
async def initialize_rag():
|
|
rag = LightRAG(
|
|
working_dir=WORKING_DIR,
|
|
llm_model_func=llm_model_func,
|
|
summary_max_tokens=10000,
|
|
embedding_func=embedding_func,
|
|
chunk_token_size=512,
|
|
chunk_overlap_token_size=256,
|
|
kv_storage='RedisKVStorage',
|
|
graph_storage='Neo4JStorage',
|
|
vector_storage='MilvusVectorDBStorage',
|
|
doc_status_storage='RedisKVStorage',
|
|
)
|
|
|
|
await rag.initialize_storages() # Auto-initializes pipeline_status
|
|
return rag
|
|
|
|
|
|
def main():
|
|
# Initialize RAG instance
|
|
rag = asyncio.run(initialize_rag())
|
|
|
|
with open('./book.txt', 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()
|