合肥官网建设公司哪家好_浏览器在线_怎么做电商卖东西_轻松seo优化排名 快排

切割方法：

import osfrom langchain_community.embeddings import BaichuanTextEmbeddings
from langchain_experimental.text_splitter import SemanticChunkerwith open('test.txt', encoding='utf8') as f:text_data = f.read()os.environ['BAICHUAN_API_KEY'] = 'sk-732b2b80be7bd800cb3a1dbc330722b4'
# 导入百川大模型的词嵌入模型
# 百川官网，自己注册一个账号，生成apikey：https://platform.baichuan-ai.com/homePage
embeddings = BaichuanTextEmbeddings()
# 按照百分位percentile切割
text_splitter = SemanticChunker(embeddings, breakpoint_threshold_type='percentile')docs_list = text_splitter.create_documents([text_data])print(docs_list[0].page_content)