Skip to content

Commit 862e1d4

Browse files
docs: update README
1 parent 56362ac commit 862e1d4

File tree

2 files changed

+4
-2
lines changed

2 files changed

+4
-2
lines changed

README.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,13 +62,14 @@ After data generation, you can use [LLaMA-Factory](https://github.com/hiyouga/LL
6262

6363
## 📌 Latest Updates
6464

65+
- **2025.10.23**: We support VQA(Visual Question Answering) data generation now. Run script: `bash scripts/generate/generate_vqa.sh`.
6566
- **2025.10.21**: We support PDF as input format for data generation now via [MinerU](https://github.com/opendatalab/MinerU).
6667
- **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).
67-
- **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.
6868

6969
<details>
7070
<summary>History</summary>
7171

72+
- **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.
7273
- **2025.07.31**: We have added Google, Bing, Wikipedia, and UniProt as search back-ends.
7374
- **2025.04.21**: We have released the initial version of GraphGen.
7475

README_zh.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -63,13 +63,14 @@ GraphGen 首先根据源文本构建细粒度的知识图谱,然后利用期
6363

6464
## 📌 最新更新
6565

66+
- **2025.10.23**:我们现在支持视觉问答(VQA)数据生成。运行脚本:`bash scripts/generate/generate_vqa.sh`
6667
- **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。
6768
- **2025.09.29**:我们在 [Hugging Face](https://huggingface.co/spaces/chenzihong/GraphGen)[ModelScope](https://modelscope.cn/studios/chenzihong/GraphGen) 上自动更新 Gradio 应用。
68-
- **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。
6969

7070
<details>
7171
<summary>历史更新</summary>
7272

73+
- **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。
7374
- **2025.07.31**:新增 Google、Bing、Wikipedia 和 UniProt 作为搜索后端,帮助填补数据缺口。
7475
- **2025.04.21**:发布 GraphGen 初始版本。
7576

0 commit comments

Comments
 (0)