Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
zhougaofeng
magic_pdf
Commits
766dc2f7
Commit
766dc2f7
authored
Oct 22, 2024
by
zhougaofeng
Browse files
Update README.md
parent
20c3128c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
13 additions
and
2 deletions
+13
-2
README.md
README.md
+13
-2
No files found.
README.md
View file @
766dc2f7
...
...
@@ -5,13 +5,18 @@
### 以下演示在223节点安装pdf解析模块(可以直接使用镜像:1177ea7959ce)
下载本项目
`git clone http://developer.sourcefind.cn/codes/zhiAn123/magic_pdf.git`
下载需要的模型库
`git clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit.git`
### 1、安装需要的依赖库
`cd magic_pdf-main`
#### pip install -e .
### 2、安装需要的模型
`git clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit.git`
#### 修改magic-pdf.template.json
<div
align=
center
>
...
...
@@ -25,10 +30,16 @@
</div>
### 4、启动qwen-ocr模块:
下载qwen模型:
[
快速下载通道
](
http://113.200.138.88:18080/aimodels/qwen/Qwen2-VL-7B-Instruct.git
)
修改magic_pdf-main/magic_pdf/dict2md/ocr_server.py文件中模型路径地址
<div
align=
center
>
<img
src=
"doc/image11.png"
/>
</div>
`python magic_pdf/dict2md/ocr_server.py`
默认使用6020端口,0号DCU卡 ,可以通过--dcu_id 指定卡,--server_port指定端口号
默认使用6020端口,0号DCU卡 ,可以通过--dcu_id 指定卡,--server_port指定端口号
,--c 指定qwen模型地址
qwen-ocr模块启动成功:
<div
align=
center
>
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment