|
|
|
|
|
import asyncio
|
|
|
|
|
|
import logging
|
|
|
|
|
|
|
|
|
|
|
|
from Util.DocxUtil import get_docx_content_by_pandoc
|
|
|
|
|
|
from Util.LightRagUtil import initialize_pg_rag
|
|
|
|
|
|
|
|
|
|
|
|
# 或者如果你想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)
|
|
|
|
|
|
logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
|
|
|
|
|
|
|
|
|
|
|
|
# 使用PG库后，这个是没有用的,但目前的项目代码要求必传，就写一个吧。
|
|
|
|
|
|
WORKING_DIR = f"../output"
|
|
|
|
|
|
|
|
|
|
|
|
#### 下面两个要注意写清楚内容 ####
|
|
|
|
|
|
# 1、工作空间【知识库名称】
|
|
|
|
|
|
# 2、文档名称【不允许出现重复，因为后面需要以此为条件查询】
|
|
|
|
|
|
tasks = [
|
|
|
|
|
|
# { # 苏轼
|
|
|
|
|
|
# "workspace": "SuShi", "docx_name": "SuShi.docx",
|
|
|
|
|
|
# },
|
|
|
|
|
|
# { # 化学
|
|
|
|
|
|
# "workspace": "Chemistry", "docx_name": "Chemistry.docx",
|
|
|
|
|
|
# },
|
|
|
|
|
|
#{ # 数学
|
|
|
|
|
|
# "workspace": "Math", "docx_name": "Math.docx",
|
|
|
|
|
|
#},
|
|
|
|
|
|
{ # 几何
|
|
|
|
|
|
"workspace": "JiHe", "docx_name": "JiHe.docx",
|
|
|
|
|
|
},
|
|
|
|
|
|
# { # 史记
|
|
|
|
|
|
# "workspace": "ShiJi", "docx_name": "ShiJi.docx",
|
|
|
|
|
|
# },
|
|
|
|
|
|
# { # 长春市一批次高中学校介绍
|
|
|
|
|
|
# "workspace": "ChangChun", "docx_name": "ChangChun_3.docx",
|
|
|
|
|
|
# },
|
|
|
|
|
|
# { # 2024长春43所高中录取分数线
|
|
|
|
|
|
# "workspace": "ChangChun", "docx_name": "ChangChun_1.docx",
|
|
|
|
|
|
# },
|
|
|
|
|
|
# { # 长春市2025年中考各批次录取最低控制线
|
|
|
|
|
|
# "workspace": "ChangChun", "docx_name": "ChangChun_2.docx",
|
|
|
|
|
|
# }
|
|
|
|
|
|
]
|
|
|
|
|
|
for task in tasks:
|
|
|
|
|
|
task["docx_path"] = "./static/Txt/" + task["docx_name"] # 3、文档路径 python是按引用传递的&
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def main():
|
|
|
|
|
|
for task in tasks:
|
|
|
|
|
|
workspace = task["workspace"]
|
|
|
|
|
|
docx_name = task["docx_name"]
|
|
|
|
|
|
docx_path = task["docx_path"]
|
|
|
|
|
|
logger.info(f"开始处理文档: {docx_name}" + ",共%s个文档,当前是第%s个。", len(tasks), tasks.index(task) + 1)
|
|
|
|
|
|
try:
|
|
|
|
|
|
rag = await initialize_pg_rag(WORKING_DIR=WORKING_DIR, workspace=workspace)
|
|
|
|
|
|
# 获取docx文件的内容
|
|
|
|
|
|
content = get_docx_content_by_pandoc(docx_path)
|
|
|
|
|
|
await rag.ainsert(input=content, file_paths=[docx_name]) # 添加来源参数
|
|
|
|
|
|
finally:
|
|
|
|
|
|
if rag:
|
|
|
|
|
|
await rag.finalize_storages()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
|
asyncio.run(main())
|
