dsProject/dsRagAnything/T1_Train.py

import asyncio

from raganything import RAGAnything, RAGAnythingConfig
from Util.RagUtil import create_llm_model_func, create_vision_model_func, create_embedding_func

async def main():
    # 要处理的文件路径
    #file_path = "./Txt/氢气与氧气反应化学方程式.docx"
    #file_path = "static/Txt/苏轼.docx"
    file_path = "static/Txt/化学方程式_CHEMISTRY_1.docx"

    # 索引生成目录
    WORKING_DIR = "./Topic/Chemistry"

    # 指定最终的索引生成目录，启动索引生成
    config = RAGAnythingConfig(
        working_dir=WORKING_DIR,
        mineru_parse_method="auto",
        enable_image_processing=True,
        enable_table_processing=True,
        enable_equation_processing=True,
    )
    # 自定义的大模型函数
    llm_model_func = create_llm_model_func()
    # 自定义的可视模型函数
    vision_model_func = create_vision_model_func(llm_model_func)
    # 自定义的嵌入函数
    embedding_func = create_embedding_func()
    rag = RAGAnything(
        config=config,
        llm_model_func=llm_model_func,
        vision_model_func=vision_model_func,
        embedding_func=embedding_func,
    )
<<<<<<< HEAD

    # file_path = "D:\python\小乔证件\黄琬乔2023蓝桥杯省赛准考证.pdf"
    #file_path = "./Txt/驿来特平台安全.docx"
    file_path = "./Txt/苏轼.docx"
=======
>>>>>>> 9a3b002e0c73115f6c6a7a67ddb43e270de17d62
    await rag.process_document_complete(
        file_path=file_path,
        output_dir="./output",
        parse_method="auto"
    )
    print("文档解析索引完成！")

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