search

pymupdf / RAG

RAG (Retrieval-Augmented Generation) Chatbot Examples Using PyMuPDF
https://pymupdf.readthedocs.io/en/latest/pymupdf4llm
GNU Affero General Public License v3.0
302 stars 57 forks source link

pymypdf4llm的一些问题，大家有没有遇到 #106

Closed ghost closed 1 month ago

ghost commented 1 month ago

问题 1）基本格式不对啊，行间距，括号中的数字，省略号 2）英文文档无法识别 优点 字体基本可以识别，图片可以提取

pymupdf4llm_原pdf段落_2024-08-21_10-30-56 test001pdf转md_格式不对_不对_2024-08-21_10-32-07
JorjMcKie commented 1 month ago

We only accept English as the language to post in Issues or Discussions, sorry. This is to control effort for our maintenance team and to keep the best possible benefit for other users.