更新readme (#460)

This commit is contained in:
田常@蚂蚁 2025-04-18 10:05:27 +08:00 committed by GitHub
parent 13cea5f6fe
commit 7c7910ab67
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 2 deletions

View File

@ -73,6 +73,11 @@ In this process, each step can use different operators, such as exact match retr
## 3.1 Latest Updates
* 2025.04.17 : Released KAG 0.7 Version
* First, we refactored the KAG-Solver framework. Added support for two task planning modes, static and iterative, while implementing a more rigorous knowledge layering mechanism for the reasoning phase.
* Second, we optimized the product experience: introduced dual modes—"Simple Mode" and "Deep Reasoning"—during the reasoning phase, along with support for streaming inference output, automatic rendering of graph indexes, and linking generated content to original references.
* Added an open_benchmark directory to the top level of the KAG repository, comparing various RAG methods under the same base to achieve state-of-the-art (SOTA) results.
* Introduced a "Lightweight Build" mode, reducing knowledge construction token costs by 89%.
* 2025.01.07 : Support domain knowledge injection, domain schema customization, QFS tasks support, Visual query analysis, enables schema-constraint mode for extraction, etc.
* 2024.11.21 : Support Word docs upload, model invoke concurrency setting, User experience optimization, etc.
* 2024.10.25 : KAG initial release
@ -172,7 +177,7 @@ kg-solver uses a logical symbol-guided hybrid solving and reasoning engine that
**GitHub**: <https://github.com/OpenSPG/KAG>
**Website**: <https://spg.openkg.cn/>
**Website**: <https://openspg.github.io/v2/docs_en>
## Discord <a href="https://discord.gg/PURG77zhQ7"> <img src="https://img.shields.io/discord/1329648479709958236?style=for-the-badge&logo=discord&label=Discord" alt="Discord"></a>

View File

@ -64,6 +64,11 @@ KAG 提出了一种逻辑符号引导的混合求解和推理引擎。该引擎
## 3.1 最近更新
* 2025.04.17 : 发布KAG 0.7 版本
* 我们对框架进行了全面重构。新增了对static和iterative两种任务规划模式的支持同时实现了更严谨的推理阶段知识分层机制
* 我们对产品体验进行了全面优化:在推理阶段新增"简易模式"和"深度推理"双模式,并支持流式推理输出、图索引自动渲染、生成内容关联原始文献等
* KAG仓库的一级目录中新增open_benchmark目录相同基座下对比各种RAG方法实现sota
* 提供"轻量级构建"模式,知识构建token 成本降低89%
* 2025.01.07 : 支持 领域知识注入、领域 schema 自定义、摘要生成类任务支持、可视化图分析查询、schema-constraint模式抽取等
* 2024.11.21 : 支持 Word 文档上传、知识库删除、模型调用并发度设置、用户体验优化等
* 2024.10.25 : KAG 首次发布
@ -163,7 +168,7 @@ kg-solver 采用逻辑形式引导的混合求解和推理引擎,该引擎包
**GitHub**: <https://github.com/OpenSPG/KAG>
**OpenSPG**: <https://spg.openkg.cn/>
**官网**: <https://openspg.github.io/v2/docs_ch>
<img src="./_static/images/openspg-qr.png" alt="联系我们OpenSPG 二维码" width="200">