dnrops
/
KAG
mirror of https://github.com/OpenSPG/KAG
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

doc: note on staring kag in README.md (#59)

This commit is contained in:
xionghuaidong 2024-11-20 14:50:12 +08:00 committed by GitHub
parent 484e16590a
commit b02c4ffe22
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -16,6 +16,10 @@ On October 24, 2024, OpenSPG released v0.5, officially releasing the professiona
KAG is significantly better than NaiveRAG, HippoRAG and other methods in multi-hop Q&A tasks. The F1 score on hotpotQA is relatively increased by 19.6%, and the F1 score on 2wiki is relatively increased by 33.5%. We have successfully applied KAG to Ant Group's professional knowledge Q&A tasks, such as e-government Q&A and e-health Q&A, and the professionalism has been significantly improved compared to the traditional RAG method. KAG is significantly better than NaiveRAG, HippoRAG and other methods in multi-hop Q&A tasks. The F1 score on hotpotQA is relatively increased by 19.6%, and the F1 score on 2wiki is relatively increased by 33.5%. We have successfully applied KAG to Ant Group's professional knowledge Q&A tasks, such as e-government Q&A and e-health Q&A, and the professionalism has been significantly improved compared to the traditional RAG method.
⭐️ Star our repository to stay up-to-date with exciting new features and improvements! Get instant notifications for new releases! 🌟
![Star KAG](./_static/images/star-kag.gif)
### 1.1 Technical Architecture ### 1.1 Technical Architecture
![Figure 1 KAG technical architecture](./_static/images/kag-arch.png) ![Figure 1 KAG technical architecture](./_static/images/kag-arch.png)

3
README_cn.md
View File

@ -16,6 +16,9 @@
KAG 在多跳问答任务中显著优于 NaiveRAG、HippoRAG 等方法，在 hotpotQA 上的 F1 分数相对提高了 19.6%，在 2wiki 上的 F1 分数相对提高了 33.5%。我们已成功将 KAG 应用于蚂蚁集团的电子政务问答和电子健康问答等专业知识服务场景，与 RAG 方法相比，专业性和准确率有了显著提高。 KAG 在多跳问答任务中显著优于 NaiveRAG、HippoRAG 等方法，在 hotpotQA 上的 F1 分数相对提高了 19.6%，在 2wiki 上的 F1 分数相对提高了 33.5%。我们已成功将 KAG 应用于蚂蚁集团的电子政务问答和电子健康问答等专业知识服务场景，与 RAG 方法相比，专业性和准确率有了显著提高。
⭐️点击右上角的 Star 关注 KAG，可以获取最新发布的实时通知！🌟
![Star KAG](./_static/images/star-kag.gif)
### 1.1 技术架构 ### 1.1 技术架构

4
README_ja.md
View File

@ -11,6 +11,10 @@
KAGは、NaiveRAG、HippoRAGなどの方法に比べて、マルチホップ質問応答タスクで顕著に優れています。hotpotQAでのF1スコアは19.6％相対的に向上し、2wikiでのF1スコアは33.5％相対的に向上しました。私たちは、KAGをAnt Groupの2つの専門知識質問応答タスク（電子政府質問応答と電子健康質問応答）に成功裏に適用し、RAG方法に比べて専門性が大幅に向上しました。 KAGは、NaiveRAG、HippoRAGなどの方法に比べて、マルチホップ質問応答タスクで顕著に優れています。hotpotQAでのF1スコアは19.6％相対的に向上し、2wikiでのF1スコアは33.5％相対的に向上しました。私たちは、KAGをAnt Groupの2つの専門知識質問応答タスク（電子政府質問応答と電子健康質問応答）に成功裏に適用し、RAG方法に比べて専門性が大幅に向上しました。
⭐️ リポジトリをスター登録して、エキサイティングな新機能やアップデートを最新の状態に保ちましょう！すべての新しいリリースに関する即時通知を受け取れます！🌟
![Star KAG](./_static/images/star-kag.gif)
### 1.1 技術アーキテクチャ ### 1.1 技術アーキテクチャ
![図1 KAG技術アーキテクチャ](./_static/images/kag-arch.png) ![図1 KAG技術アーキテクチャ](./_static/images/kag-arch.png)

BIN
_static/images/star-kag.gif Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.2 MiB