dsProject/dsLightRag/T1_Train.py

import asyncio
import logging

from Util.DocxUtil import get_docx_content_by_pandoc
from Util.LightRagUtil import configure_logging, initialize_rag
import os

KEMU = 'ChuZhongShuXue'  # JiHe,Math,SuShi,Chemistry,ShiJi,ChangChun

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

# 是不是清空重新生成
IS_CLEAR= False

# 更详细地控制日志输出
logger = logging.getLogger('lightrag')
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
logger.addHandler(handler)

async def main():
    # 清空文件
    if IS_CLEAR:
        # 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",
        ]

        # 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)
                logger.info(f"删除的文件:: {file_path}")

    try:
        # 注意：默认设置使用NetworkX
        rag = await initialize_rag(WORKING_DIR)
        # 在docx_file 目录下遍历所有以KEMU开头的文件
        for filename in os.listdir(docx_file):
            if filename.startswith(KEMU):
                file_path = os.path.join(docx_file, filename)
                # 获取docx文件的内容
                content = get_docx_content_by_pandoc(file_path)
                await rag.ainsert(content, file_paths=[filename])
                logger.info(f"Inserted content from {filename}")
    except Exception as e:
        logger.error(f"An error occurred: {e}")
    finally:
        await rag.finalize_storages()


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