update readme

CosmosShadow · Jun 28, 2024 · 99cdf8e · 99cdf8e
1 parent 91ffc53
commit 99cdf8e
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -17,13 +17,13 @@ This package use [GeneralAgent](https://github.com/CosmosShadow/GeneralAgent) li
 
 ## Process steps
 
-1. Use the PyMuPDF library to parse the PDF and extract all non-text rectangular areas (tables, pictures, icons, etc.)
+1. Use the PyMuPDF library to parse the PDF and extract all non-text rectangular areas.
 2. Convert all non-text rectangular areas on the PDF into pictures and number them
 3. Mark each page of the PDF with a red rectangle and number and save it as an image, similar to the following:
 
 ![](docs/demo.jpg)
 
-4. Based on the picture in step 3, use a large visual model (such as GPT-4o) to parse and get the markdown content (including pictures, tables, formulas, etc.)
+4. Based on the picture in step 3, use a large visual model (such as GPT-4o) to parse and get the markdown content.
 
 
 

diff --git a/README_CN.md b/README_CN.md
@@ -17,7 +17,7 @@
 
 ## 处理流程
 
-1. 使用 PyMuPDF 库，对 PDF 进行解析，提取所有非文本的矩形区域(表格、图片、图标等)
+1. 使用 PyMuPDF 库，对 PDF 进行解析，提取所有非文本的矩形区域(包括表格、图片、图标等)
 2. 将 PDF 上所有非文本的矩形区域转成图片，并进行编号
 3. 在每页PDF上标记好红色矩形框和编号，保存为图片，类似如下: