dsProject/dsLightRag/T1_Train.py

import asyncio

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

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

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

async def main():
    # 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",
    ]
    # 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)

    # 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
        rag = await initialize_rag(WORKING_DIR)
        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())