docs: update README

Author: ChenZiHong-Gavin

README.md

@@ -21,7 +21,7 @@
 
 GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
 
-[English](README.md) | [中文](README_ZH.md)
+[English](README.md) | [中文](README_zh)
 
 <details close>
 <summary><b>📚 Table of Contents</b></summary>
@@ -62,11 +62,19 @@ After data generation, you can use [LLaMA-Factory](https://github.com/hiyouga/LL
 
 ## 📌 Latest Updates
 
+- **2025.10.21**: We support PDF as input format for data generation now via [MinerU](https://github.com/opendatalab/MinerU).
 - **2025.09.29**: We auto-update gradio demo on [Hugging Face](https://huggingface.co/spaces/chenzihong/GraphGen) and [ModelScope](https://modelscope.cn/studios/chenzihong/GraphGen).
 - **2025.08.14**: We have added support for community detection in knowledge graphs using the Leiden algorithm, enabling the synthesis of Chain-of-Thought (CoT) data.
+
+<details>
+<summary>History</summary>
+
 - **2025.07.31**: We have added Google, Bing, Wikipedia, and UniProt as search back-ends.
 - **2025.04.21**: We have released the initial version of GraphGen.
 
+</details>
+
+
 ## 🚀 Quick Start
 
 Experience GraphGen through [Web](https://g-app-center-120612-6433-jpdvmvp.openxlab.space) or [Backup Web Entrance](https://openxlab.org.cn/apps/detail/chenzihonga/GraphGen)

README_ZH.md renamed to README_zh.md

@@ -20,7 +20,7 @@
 
 GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
 
-[English](README.md) | [中文](README_ZH.md)
+[English](README.md) | [中文](README_zh)
 
 <details close>
 <summary><b>📚 目录</b></summary>
@@ -63,11 +63,19 @@ GraphGen 首先根据源文本构建细粒度的知识图谱，然后利用期
 
 ## 📌 最新更新
 
+- **2025.10.21**：我们现在通过 [MinerU](https://github.com/opendatalab/MinerU) 支持 PDF 作为数据生成的输入格式。
 - **2025.09.29**：我们在 [Hugging Face](https://huggingface.co/spaces/chenzihong/GraphGen) 和 [ModelScope](https://modelscope.cn/studios/chenzihong/GraphGen) 上自动更新 Gradio 应用。
 - **2025.08.14**：支持利用 Leiden 社区发现算法对知识图谱进行社区划分，合成 CoT 数据。
+
+<details>
+<summary>历史更新</summary>
+
 - **2025.07.31**：新增 Google、Bing、Wikipedia 和 UniProt 作为搜索后端，帮助填补数据缺口。  
 - **2025.04.21**：发布 GraphGen 初始版本。
 
+</details>
+
+
 ## 🚀 快速开始
 
 通过 [Web](https://g-app-center-120612-6433-jpdvmvp.openxlab.space) 或 [备用 Web 入口](https://openxlab.org.cn/apps/detail/chenzihonga/GraphGen) 体验 GraphGen。