diff --git a/.new_docs/api_docs/README.md b/.new_docs/api_docs/README.md
new file mode 100644
index 0000000000..4da649deca
--- /dev/null
+++ b/.new_docs/api_docs/README.md
@@ -0,0 +1,21 @@
+# API文档生成
+
+## 环境要求
+- Ubuntu
+- python >= 3.6
+
+## 前置依赖安装
+
+```
+sudo apt-get install doxygen
+
+pip install -r python/requirements.txt
+```
+
+## 文档生成
+
+```
+bash build.sh
+```
+
+执行完成后，浏览器打开当前目录下的`index.html`即可查阅API文档
diff --git a/.new_docs/api_docs/build.sh b/.new_docs/api_docs/build.sh
new file mode 100644
index 0000000000..e064140c32
--- /dev/null
+++ b/.new_docs/api_docs/build.sh
@@ -0,0 +1,9 @@
+CURRENT_DIR=${PWD}
+
+cd cpp
+doxygen
+
+cd ../python
+make html
+
+cd ${CURRENT_DIR}
diff --git a/.new_docs/api_docs/cpp/docs/.gitignore b/.new_docs/api_docs/cpp/.gitignore
similarity index 100%
rename from .new_docs/api_docs/cpp/docs/.gitignore
rename to .new_docs/api_docs/cpp/.gitignore
diff --git a/.new_docs/api_docs/cpp/Doxyfile b/.new_docs/api_docs/cpp/Doxyfile
index b5f23f5c03..4bd48f09d7 100644
--- a/.new_docs/api_docs/cpp/Doxyfile
+++ b/.new_docs/api_docs/cpp/Doxyfile
@@ -791,6 +791,7 @@ WARN_LOGFILE           =
 # Note: If this tag is empty the current directory is searched.
 
 INPUT                  = ../../../fastdeploy/
+INPUT += ./main_page.md
 
 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
@@ -982,7 +983,7 @@ FILTER_SOURCE_PATTERNS =
 # (index.html). This can be useful if you have a project on for instance GitHub
 # and want to reuse the introduction page also for the doxygen output.
 
-USE_MDFILE_AS_MAINPAGE = main_page.md
+USE_MDFILE_AS_MAINPAGE = ./main_page.md
 
 #---------------------------------------------------------------------------
 # Configuration options related to source browsing
@@ -1666,7 +1667,7 @@ EXTRA_SEARCH_MAPPINGS  =
 # If the GENERATE_LATEX tag is set to YES, doxygen will generate LaTeX output.
 # The default value is: YES.
 
-GENERATE_LATEX         = YES
+GENERATE_LATEX         = NO
 
 # The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. If a
 # relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
diff --git a/.new_docs/api_docs/index.html b/.new_docs/api_docs/index.html
new file mode 100644
index 0000000000..4f65912813
--- /dev/null
+++ b/.new_docs/api_docs/index.html
@@ -0,0 +1,13 @@
+<h1 id="fastdeploy-api-documents">FastDeploy API Documents</h1>
+<ul>
+<li><p><a href="./python/_build/html">Python API</a></p>
+</li>
+<li><p><a href="./cpp/docs/html">C++ API</a></p>
+</li>
+</ul>
+<h2 id="more-information">More Information</h2>
+<ul>
+<li>Github: <a href="https://github.com/PaddlePaddle/FastDeployqq.com">https://github.com/PaddlePaddle/FastDeployqq.com</a> </li>
+<li>Email: fastdeploy@baidu.com</li>
+<li><a href="https://join.slack.com/t/fastdeployworkspace/shared_invite/zt-1hhvpb279-iw2pNPwrDaMBQ5OQhO3Siw">Click here join FastDeploy Slack</a></li>
+</ul>
diff --git a/.new_docs/api_docs/python/conf.py b/.new_docs/api_docs/python/conf.py
index 667d2dd0c9..f22b0fd169 100644
--- a/.new_docs/api_docs/python/conf.py
+++ b/.new_docs/api_docs/python/conf.py
@@ -35,7 +35,8 @@ extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.mathjax',
     'sphinx_markdown_tables',
-    'sphinx.ext.viewcode'
+    'sphinx.ext.viewcode',
+    'sphinx.ext.githubpages',
 ]
 
 autoclass_content = 'both'
diff --git a/.new_docs/cn/quick_start/models/python.md b/.new_docs/cn/quick_start/models/python.md
index 6cad7ccf1b..55a245dd9f 100644
--- a/.new_docs/cn/quick_start/models/python.md
+++ b/.new_docs/cn/quick_start/models/python.md
@@ -1,8 +1,8 @@
-# Python部署
+# PPYOLOE Python部署
 
 确认开发环境已安装FastDeploy，参考[FastDeploy安装](../../build_and_install/)安装预编译的FastDeploy，或根据自己需求进行编译安装。
 
-本文档以PaddleDetection目标检测模型PicoDet为例展示CPU上的推理示例
+本文档以PaddleDetection目标检测模型PPYOLOE为例展示CPU上的推理示例
 
 ## 1. 获取模型和测试图像
 
diff --git a/fastdeploy/README.md b/fastdeploy/README.md
deleted file mode 100644
index 2266d476aa..0000000000
--- a/fastdeploy/README.md
+++ /dev/null
@@ -1,27 +0,0 @@
-# FastDeploy C++ API Summary
-
-## Runtime
-
-FastDeploy Runtime can be used as an inference engine with the same code, we can deploy Paddle/ONNX model on different device by different backends.  
-Currently, FastDeploy supported backends listed as below,
-
-| Backend | Hardware | Support Model Format | Platform |
-| :------ | :------- | :------------------- | :------- |
-| Paddle Inference | CPU/Nvidia GPU | Paddle | Windows(x64)/Linux(x64) |
-| ONNX Runtime | CPU/Nvidia GPU | Paddle/ONNX | Windows(x64)/Linux(x64/aarch64)/Mac(x86/arm64) |
-| TensorRT | Nvidia GPU | Paddle/ONNX | Windows(x64)/Linux(x64)/Jetson |
-| OpenVINO | CPU | Paddle/ONNX | Windows(x64)/Linux(x64)/Mac(x86) |
-
-### Example code
-- [Python examples](./)
-- [C++ examples](./)
-
-### Related APIs
-- [RuntimeOption](./structfastdeploy_1_1RuntimeOption.html)
-- [Runtime](./structfastdeploy_1_1Runtime.html)
-
-## Vision Models
-
-| Task | Model | API | Example |
-| :---- | :---- | :---- | :----- |
-| object detection | PaddleDetection/PPYOLOE | [fastdeploy::vision::detection::PPYOLOE](./classfastdeploy_1_1vision_1_1detection_1_1PPYOLOE.html) | [C++](./)/[Python](./) |