diff --git a/docs/products/apis/documents/ocr.md b/docs/products/apis/documents/ocr.md
index 6b8c2735e41e4d37dfd652f775ab482518b7afe0..f089ee8731c102a01f7d2c1fa94315d0d11d9a45 100644
--- a/docs/products/apis/documents/ocr.md
+++ b/docs/products/apis/documents/ocr.md
@@ -21,36 +21,37 @@ GOT-OCR2_0 提供功能强大的 OCR 解决方案，能够高精度、快速、
您可以点击 [GOT-OCR2_0]({{SITE_URL}}/serverless-api?model=GOT-OCR2_0) 在线免费体验。以下是代码调用示例。
-
- ```bash showLineNumbers
+
+`bash showLineNumbers
curl {{API_URL}}/v1/images/ocr \
-X POST \
-H "Authorization: Bearer 私人令牌" \
-F "model=GOT-OCR2_0"
-F "image=@path/to/image.jpg"
-F "response_format=text"
- ```
-
-
- ```python showLineNumbers title="python"
- import requests
- API_URL = "{{API_URL}}/v1/images/ocr"
- HEADERS = {
- "Authorization": "Bearer 私人令牌",
- }
- def query(image_path, model="GOT-OCR2_0", response_format="text"):
- with open(image_path, "rb") as image_file:
- response = requests.post(
- API_URL,
- headers=HEADERS,
- files={"image": (image_path, image_file)},
- data={"model": model, "response_format": response_format},
- )
- return response.json()
-
+ `
+
+
+```python showLineNumbers title="python"
+import requests
+API_URL = "{{API_URL}}/v1/images/ocr"
+HEADERS = {
+"Authorization": "Bearer 私人令牌",
+}
+def query(image_path, model="GOT-OCR2_0", response_format="text"):
+with open(image_path, "rb") as image_file:
+response = requests.post(
+API_URL,
+headers=HEADERS,
+files={"image": (image_path, image_file)},
+data={"model": model, "response_format": response_format},
+)
+return response.json()
+
output = query("test.jpg")
print(output) # {"text": "xxx"}
```
+
@@ -70,7 +71,7 @@ GOT-OCR2_0 提供功能强大的 OCR 解决方案，能够高精度、快速、
使用图片：
-
+
执行上文中的代码后将会响应：
@@ -78,10 +79,10 @@ GOT-OCR2_0 提供功能强大的 OCR 解决方案，能够高精度、快速、
{
"text": "美迪兰（南京）医疗设备有限公司\n名称：..."
}
-````
+```
[GOT-OCR2_0]({{SITE_URL}}/serverless-api?model=GOT-OCR2_0)在线体验效果如下：
-
+
更多示例代码您可参考 [模力方舟示例代码仓库](https://gitee.com/moark/examples/tree/master/ocr) 。
diff --git a/docs/products/apis/documents/pdf.md b/docs/products/apis/documents/pdf.md
index 6edce4d6b7126b3fe057e2bbadb8feaeaad822eb..096fb069f78d75d187e1c2aa0c750ab7026f4095 100644
--- a/docs/products/apis/documents/pdf.md
+++ b/docs/products/apis/documents/pdf.md
@@ -11,11 +11,15 @@ import TabItem from '@theme/TabItem';
文档解析是指通过人工智能模型，从各种格式的文档中提取有价值的信息和内容。它的核心任务是将非结构化或半结构化的文档内容转化为结构化数据，便于后续的分析和处理。文档解析技术广泛应用于知识库建设、数据挖掘、信息检索等领域。
-目前模型广场已上线的文档解析模型包括：[PDF-Extract-Kit]({{SITE_URL}}/serverless-api?model=PDF-Extract-Kit-1.0)
+目前模型广场已上线的文档解析模型包括：[MinerU]({{SITE_URL}}/serverless-api?model=MinerU2.5)
-## PDF-Extract-Kit
+:::tip 关于 MinerU 版本
+目前模型广场已上线两个版本的 MinerU ，分别为 1.0 和 2.5，其中 1.0 对应的 model 参数为 `PDF-Extract-Kit-1.0` ， 2.5 对应的 model 参数为 `MinerU2.5` ，后续会持续更新迭代。
+:::
-PDF-Extract-Kit 专为从各类复杂 PDF 文档中高效提取高质量内容而设计。它具备以下特点：
+## MinerU
+
+MinerU 专为从各类复杂 PDF 文档中高效提取高质量内容而设计。它具备以下特点：
- 能够精确还原原始文档的布局。
- 输出内容为 Markdown 格式，便于阅读。
@@ -34,12 +38,13 @@ PDF-Extract-Kit 专为从各类复杂 PDF 文档中高效提取高质量内容
### 使用方法
-您可以点击 [PDF-Extract-Kit]({{SITE_URL}}/serverless-api?model=PDF-Extract-Kit-1.0) 在线免费体验。以下是代码调用示例。
+您可以点击 [MinerU]({{SITE_URL}}/serverless-api?model=MinerU2.5) 在线免费体验。以下是代码调用示例。
+
```bash showLineNumbers
curl {{API_URL}}/v1/async/documents/parse \
-X POST \
-H "Authorization: Bearer 您的访问令牌" \
- -F "model=PDF-Extract-Kit-1.0" \
+ -F "model=MinerU2.5" \
-F "is_ocr=true" \
-F "formula_enable=true" \
-F "table_enable=true" \
@@ -66,7 +71,7 @@ PDF-Extract-Kit 专为从各类复杂 PDF 文档中高效提取高质量内容
### 使用示例
-
+
该接口为异步接口，需要先提交任务，获取到任务 ID，随后再根据 ID 轮询获取执行结果。CURL 提交任务后将会响应：
diff --git a/docs/products/apis/images-vision/fuzzy.md b/docs/products/apis/images-vision/fuzzy.md
index 8178d63e023ebf2242d0d27860a064edff3a93e2..8179c9df6b46023e18865a34df61b5d22ee8b651 100644
--- a/docs/products/apis/images-vision/fuzzy.md
+++ b/docs/products/apis/images-vision/fuzzy.md
@@ -25,7 +25,7 @@ sidebar_position: 5
Serverless API 提供了接口快速体验的界面，可以快速体验接口效果。
打开 [Serverless API 页面]({{SITE_URL}}/serverless-api?model=Kolors&operation=41) ，找到图像生成与处理下的 `Kolors` 模型，点击进入接口详情页，切换到风格迁移的 API 。
-
+
风格迁移接口中，原图指的是想要进行迁移和修改的图片。提示词和 image 是用以指导原图修改的文本和风格图。
@@ -35,35 +35,35 @@ Serverless API 提供了接口快速体验的界面，可以快速体验接口
使用下图，作为参考的图像：
-
+
使用一张普通的风景图作为原图。
-
+
在页面上填入这些图片，为了让产出的图片更贴合原图，我们将 strength 参数设置为0.4。
-
+
输出结果如下：
-
+
### 毛茸茸风格迁移
参考图如下：
-
+
和前文步骤相同，我们能够通过风格迁移接口快速复制毛茸茸的图片风格。
输入如下：
-
+
输出结果如下：
-
+
## 调用风格迁移接口
diff --git a/docs/products/datasets/_category_.json b/docs/products/datasets/_category_.json
index 6715f7e504fcdabb9802970668eb116d4abe9e56..337e4fe0807341fb23a15c0366dea2c8aca45203 100644
--- a/docs/products/datasets/_category_.json
+++ b/docs/products/datasets/_category_.json
@@ -1,5 +1,5 @@
{
"label": "数据集",
- "position": 3,
+ "position": 5,
"collapsed": true
}
\ No newline at end of file
diff --git a/docs/products/models/_category_.json b/docs/products/models/_category_.json
index 0b85ff0867c0a0ec1f6fe9f91dbb53907b6de335..12ccba906010de773fabcbc5abf12aaf0ce66690 100644
--- a/docs/products/models/_category_.json
+++ b/docs/products/models/_category_.json
@@ -1,5 +1,5 @@
{
"label": "模型库",
- "position": 2,
+ "position": 4,
"collapsed": true
}
\ No newline at end of file
diff --git a/docs/products/training/_category_.json b/docs/products/training/_category_.json
index c93cfd02bd028b643ca1bfc9b1a8ba4e02afb02f..6f9da01cb877f61e5484d63845ac7808eeaabfc4 100644
--- a/docs/products/training/_category_.json
+++ b/docs/products/training/_category_.json
@@ -1,5 +1,5 @@
{
"label": "模型微调",
- "position": 5,
+ "position": 3,
"collapsed": true
}
\ No newline at end of file
diff --git a/docs/products/training/image-generate.md b/docs/products/training/image-generate.md
index d825c7da7c51cb7390cf19254cc3d57f673401a6..b616227cc81076ce789605afa23df13623dcb98b 100644
--- a/docs/products/training/image-generate.md
+++ b/docs/products/training/image-generate.md
@@ -8,7 +8,7 @@ sidebar_position: 2
图像大模型本身已经学到非常多通用的艺术风格和物体，但是它没法理解某个具体的人、具体的事物是什么样子的。通过微调，我们可以教会大模型画出您身边某个具体的人或事物。
-目前支持微调的模型包括：`FLUX.1-Krea-dev` 、 `FLUX.1-Dev` 以及 `SDXL 1.0` 。
+目前支持微调的模型包括：`FLUX.1-Krea-dev` 、 `FLUX.1-Dev` 、`Qwen Image` 以及 `SDXL 1.0` 。
本文将通过 5 张特定狗狗照片的数据集，通过模力方舟提供的开箱即用的模型微调功能。让大模型 “记住” 特定狗狗的特征。
@@ -62,6 +62,7 @@ sidebar_position: 2
## 步骤四：算力选择
+
点击 `下一步，选择算力` ，进入算力选择页面，确定后点击 `支付并开始训练`
diff --git a/docs/products/training/index.md b/docs/products/training/index.md
index 29692810ce3302ab484d008400bf18df15168b7c..52a7471217d4d2f90a4560a0496f847e2c108715 100644
--- a/docs/products/training/index.md
+++ b/docs/products/training/index.md
@@ -12,7 +12,7 @@ import ReactPlayer from 'react-player/lazy';
模力方舟支持开箱即用的微调功能。具体支持的微调功能有：
-- 文生图模型： `SDXL 1.0` 以及 `FLUX-Dev`
+- 文生图模型： `SDXL 1.0` 、`FLUX-Dev` 以及 `Qwen Image` 等
- 文本生成模型：`Qwen2.5` , `Qwen3`
#### 从 0 开始实操上手视频
diff --git a/docs/products/training/price.md b/docs/products/training/price.md
index 36e3c3322466ced630cbd5c02e988b2b9e0ed815..c50484fa4ed6e4d6c39a86b2e2a5ff228d6dd3c8 100644
--- a/docs/products/training/price.md
+++ b/docs/products/training/price.md
@@ -10,12 +10,13 @@ sidebar_position: 3
当前支持的模型、算力以及定价的关系如下表所示：
-| 模型/算力 | 天垓100 | 沐曦 C500 |
-| --------- | ------- | --------- |
-| Qwen2.5 | - | 4 元/时 |
-| Qwen3 | - | 4 元/时 |
-| SDXL | 2 元/时 | 4 元/时 |
-| FLUX-Dev | - | 4 元/时 |
+| 模型/算力 | 天垓100 | 沐曦 C500 |
+| ---------- | ------- | --------- |
+| Qwen2.5 | - | 4 元/时 |
+| Qwen3 | - | 4 元/时 |
+| SDXL | 2 元/时 | 4 元/时 |
+| FLUX-Dev | - | 4 元/时 |
+| Qwen Image | - | 4 元/时 |
## 计费流程
diff --git a/docs/products/workflow/_category_.json b/docs/products/workflow/_category_.json
index abf91f33e8048b87f9cff04e1144419d1efcd33d..9fa0203cd537fe6f8335faf3e4739d1817e97fd3 100644
--- a/docs/products/workflow/_category_.json
+++ b/docs/products/workflow/_category_.json
@@ -1,5 +1,5 @@
{
"label": "API 流水线",
- "position": 4,
+ "position": 2,
"collapsed": true
}
\ No newline at end of file
diff --git a/src/components/SidebarWithSearch.jsx b/src/components/SidebarWithSearch.jsx
new file mode 100644
index 0000000000000000000000000000000000000000..0971ca5353fb9afff6416fd0e4697f68524b79a3
--- /dev/null
+++ b/src/components/SidebarWithSearch.jsx
@@ -0,0 +1,23 @@
+import React from 'react';
+import SearchBar from '@theme-original/SearchBar';
+import DocSidebar from '@theme-original/DocSidebar';
+
+export default function SidebarWithSearch(props) {
+ return ;
+}
+
+/**
+ * 该方法主要实现在侧边栏顶部添加搜索框，目前还有一些问题，先保留代码
+ * @param {*} props
+ * @returns
+ */
+export function SidebarWithSearch2(props) {
+ return (
+
+ );
+}
diff --git a/src/theme/DocSidebar/index.js b/src/theme/DocSidebar/index.js
new file mode 100644
index 0000000000000000000000000000000000000000..4a93ee3da6f6c59a2e6242d3d66016f04e5f31d9
--- /dev/null
+++ b/src/theme/DocSidebar/index.js
@@ -0,0 +1,6 @@
+import React from 'react';
+import SidebarWithSearch from '../../components/SidebarWithSearch';
+
+export default function DocSidebarWrapper(props) {
+ return ;
+}
diff --git a/docs/products/fuzzy.assets/P1012997.jpeg b/static/img/fuzzy/P1012997.jpeg
similarity index 100%
rename from docs/products/fuzzy.assets/P1012997.jpeg
rename to static/img/fuzzy/P1012997.jpeg
diff --git "a/docs/products/fuzzy.assets/20250113164303_\345\220\211\345\215\234\345\212\233\351\243\216\346\240\274__\345\260\217\346\270\205\346\226\260.jpeg" b/static/img/fuzzy/ghibli.jpeg
similarity index 100%
rename from "docs/products/fuzzy.assets/20250113164303_\345\220\211\345\215\234\345\212\233\351\243\216\346\240\274__\345\260\217\346\270\205\346\226\260.jpeg"
rename to static/img/fuzzy/ghibli.jpeg
diff --git a/docs/products/fuzzy.assets/image-20250113153212170.png b/static/img/fuzzy/image-20250113153212170.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250113153212170.png
rename to static/img/fuzzy/image-20250113153212170.png
diff --git a/docs/products/fuzzy.assets/image-20250113173048253.png b/static/img/fuzzy/image-20250113173048253.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250113173048253.png
rename to static/img/fuzzy/image-20250113173048253.png
diff --git a/docs/products/fuzzy.assets/image-20250113173107828.png b/static/img/fuzzy/image-20250113173107828.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250113173107828.png
rename to static/img/fuzzy/image-20250113173107828.png
diff --git a/docs/products/fuzzy.assets/image-20250114143124824.png b/static/img/fuzzy/image-20250114143124824.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250114143124824.png
rename to static/img/fuzzy/image-20250114143124824.png
diff --git a/docs/products/fuzzy.assets/image-20250114144653414.png b/static/img/fuzzy/image-20250114144653414.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250114144653414.png
rename to static/img/fuzzy/image-20250114144653414.png
diff --git a/docs/products/fuzzy.assets/image-20250114144718497.png b/static/img/fuzzy/image-20250114144718497.png
similarity index 100%
rename from docs/products/fuzzy.assets/image-20250114144718497.png
rename to static/img/fuzzy/image-20250114144718497.png
diff --git a/docs/products/fuzzy.assets/jojo.jpeg b/static/img/fuzzy/jojo.jpeg
similarity index 100%
rename from docs/products/fuzzy.assets/jojo.jpeg
rename to static/img/fuzzy/jojo.jpeg
diff --git a/docs/products/fuzzy.assets/style_web.jpg b/static/img/fuzzy/style_web.jpg
similarity index 100%
rename from docs/products/fuzzy.assets/style_web.jpg
rename to static/img/fuzzy/style_web.jpg
diff --git a/docs/products/ocr.assets/image-20250114152140833.png b/static/img/ocr/image-20250114152140833.png
similarity index 100%
rename from docs/products/ocr.assets/image-20250114152140833.png
rename to static/img/ocr/image-20250114152140833.png
diff --git a/docs/products/ocr.assets/image-20250114152442007.png b/static/img/ocr/image-20250114152442007.png
similarity index 100%
rename from docs/products/ocr.assets/image-20250114152442007.png
rename to static/img/ocr/image-20250114152442007.png
diff --git a/docs/products/pdf.assets/pdf.png b/static/img/ocr/pdf.png
similarity index 100%
rename from docs/products/pdf.assets/pdf.png
rename to static/img/ocr/pdf.png