dsProject/dsLightRag/T3_TrainNeo4j.py

import asyncio

from Config.Config import NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD
from Util.DocxUtil import get_docx_content_by_pandoc
from Util.LightRagUtil import configure_logging, initialize_rag
import os

from Util.Neo4jExecutor import Neo4jExecutor

# 数学
KEMU = 'Chemistry'  # Chinese,Math,Chemistry

# 组装文件路径
WORKING_DIR = "./Topic/" + KEMU
docx_file = 'static/Txt/' + KEMU + '.docx'

async def main():
    # 设置Neo4j连接参数
    os.environ["NEO4J_URI"] = NEO4J_URI
    os.environ["NEO4J_USERNAME"] = NEO4J_USERNAME
    os.environ["NEO4J_PASSWORD"] = NEO4J_PASSWORD

    # 清库
    executor = Neo4jExecutor.create_default()
    executor.graph.run("MATCH (n) DETACH DELETE n")
    print("清库成功")

    # 注释掉或删除以下清理代码
    files_to_delete = [
        "graph_chunk_entity_relation.graphml",
        "kv_store_doc_status.json",
        "kv_store_full_docs.json",
        "kv_store_text_chunks.json",
        "vdb_chunks.json",
        "vdb_entities.json",
        "vdb_relationships.json",
    ]

    # 获取docx文件的内容
    content = get_docx_content_by_pandoc(docx_file)

    # 删除文件
    for file in files_to_delete:
        file_path = os.path.join(WORKING_DIR, file)
        if os.path.exists(file_path):
            os.remove(file_path)
            print(f"Deleting old file:: {file_path}")

    try:
        # 注意：默认设置使用NetworkX,使用Neo4J实现初始化LightRAG
        rag = await initialize_rag(WORKING_DIR, graph_storage="Neo4JStorage")
        await rag.ainsert(content)
        print("\nIndexing completed successfully!")
    except Exception as e:
        print(f"An error occurred: {e}")
    finally:
        await rag.finalize_storages()


if __name__ == "__main__":
    configure_logging()
    asyncio.run(main())