v0.7 #andy

Author: andylau-55

.idea/workspace.xml

@@ -11,7 +11,7 @@ import TabItem from '@theme/TabItem';
 <Tabs>
 <TabItem value="English" label="English">
 
-# 1、Overview
+## 1、Overview
 We are pleased to announce the official release of KAG 0.7. This update continues our commitment to enhancing the consistency, rigor, and precision of knowledge base-augmented reasoning in large language models, while introducing several significant new features.
 
 Firstly, we have completely refactored the framework. The update adds support for both **static** and **iterative** task planning modes, along with a more rigorous hierarchical knowledge mechanism during the reasoning phase. Additionally, the new **multi-executor** extension mechanism and MCP protocol integration enable horizontal scaling of various symbolic solvers (such as **math-executor** and **cypher-executor**). These improvements not only help users quickly build knowledge-augmented applications to validate innovative ideas or domain-specific solutions, but also support continuous optimization of KAG Solver's capabilities, thereby further enhancing reasoning rigor in vertical applications.
@@ -28,7 +28,7 @@ _Figure1. Performance of KAG V0.7 and baselines on Multi-hop QA benchmarks_
 
 ![](https://intranetproxy.alipay.com/skylark/lark/0/2025/png/358/1744801826055-7e6985ad-d708-432d-9c57-7a0560ffef61.png)_Figure2. Performance of KAG V0.7 and baselines(from OpenKG OneEval) on __Knowledge based QA benchmarks_
 
-# 2、Framework Enhancements
+## 2、Framework Enhancements
 ### 2.1、Hybrid Static-Dynamic Task Planning
 This release introduces optimizations to the KAG-Solver framework implementation, providing more flexible architectural support for: "Retrieval during reasoning" workflows, Multi-scenario algorithm experimentation, LLM-symbolic engine integration (via MCP protocol).
 
@@ -47,7 +47,7 @@ Using the enhanced KAG-Solver framework, we have rewritten the logic of **kag_hy
 ### 2.4、MCP Protocol Integration
 This KAG release achieves compatibility with the MCP protocol, enabling the incorporation of external data sources and symbolic solvers into the KAG framework via MCP. We have included a **baidu_map_mcp** example in the **example** directory for developers' reference.
 
-# 3、OpenBenchmark
+## 3、OpenBenchmark
 To better facilitate academic exchange and accelerate the adoption and technological advancement of large language models with external knowledge bases in enterprise settings, KAG has released more detailed benchmark reproduction steps in this version, along with open-sourcing all code and data. This will enable developers and researchers to easily reproduce and align results across various datasets.
 
 For more accurate quantification of reasoning performance, we have adopted multiple evaluation metrics, including EM (Exact Match), F1, and LLM_Accuracy. In addition to existing datasets such as TwoWiki, Musique, and HotpotQA, this update introduces the OpenKG OneEval knowledge graph QA dataset (including AffairQA and PRQA) to evaluate the capabilities of both the **cypher_executor** and KAG's default framework.
@@ -137,7 +137,7 @@ In this update, KAG has validated its retrieval and reasoning capabilities on tr
 | KAG-V0.7 | **77.5%** | **83.1%** | **88.2%** | Custom PRQA Pipeline with Cypher Solver Based on KAG Framework | Ant Group <br/>KAG Team |
 
 
-# 4、Product and platform optimization
+## 4、Product and platform optimization
 This update enhances the knowledge Q&A product experience. Users can refer to the [KAG User Manual](https://openspg.github.io/v2/docs_en) and access our demo files under the Quick Start -> Product Mode section to reproduce the results shown in the following video.
 
 + **Demo Of KAG Builder**
@@ -164,10 +164,10 @@ The new Deep Reasoning Toggle allows users to balance answer accuracy against co
   - Unified handling of structured and unstructured data
   - Enhanced task management via: Job scheduling、Execution logging、Data sampling for diagnostics
 
-# 5、Roadmap
+## 5、Roadmap
 In upcoming iterations, We are continuously committed to enhancing the capability of large models to utilize external knowledge bases, achieving bidirectional enhancement and organic integration between large models and symbolic knowledge. This effort aims to consistently improve the factual accuracy, rigor, and coherence of reasoning and question-answering in specialized scenarios. We will also continue to release updates, constantly raising the upper limits of these capabilities and advancing their implementation in vertical domains.
 
-# 6、Acknowledgments
+## 6、Acknowledgments
 This release addresses several issues in the hierarchical retrieval module, and we extend our sincere gratitude to the community developers who reported these problems.
 
 The framework upgrade has received tremendous support from the following experts and colleagues, to whom we are deeply grateful:
@@ -181,7 +181,7 @@ The framework upgrade has received tremendous support from the following experts
 </TabItem>
 <TabItem value="中文" label="中文">
 
-# 1、总体摘要
+## 1、总体摘要
 我们正式发布KAG 0.7版本，本次更新旨在持续提升大模型利用知识库推理问答的一致性、严谨性和精准性，并引入了多项重要功能特性。
 
 首先，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。此外，新增的**multi-executor**扩展机制以及MCP协议的接入，使用户能够横向扩展多种符号求解器（如**math-executor**和**cypher-executor**等）。这些改进不仅帮助用户快速搭建外挂知识库应用以验证创新想法或领域解决方案，还支持用户持续优化KAG Solver的能力，从而进一步提升垂直领域应用的推理严谨性。
@@ -198,7 +198,7 @@ _图1 Performance of KAG V0.7 and baselines on Multi-hop QA benchmarks_
 
 ![](https://intranetproxy.alipay.com/skylark/lark/0/2025/png/358/1744801826055-7e6985ad-d708-432d-9c57-7a0560ffef61.png)_图2 Performance of KAG V0.7 and baselines(from OpenKG OneEval) on __Knowledge based QA benchmarks_
 
-# 2、框架优化
+## 2、框架优化
 ### 2.1、静态与动态结合的任务规划
 本次发布对KAG-Solver框架的实现进行了优化，为“边推理边检索”、“多场景算法实验”以及“大模型与符号引擎结合（基于MCP协议）”提供了更加灵活的框架支持。
 
@@ -217,7 +217,7 @@ _图1 Performance of KAG V0.7 and baselines on Multi-hop QA benchmarks_
 ### 2.4、拥抱MCP协议
 KAG本次发版实现了对MCP协议的兼容，支持在KAG框架中通过MCP协议引入外部数据源和外部符号求解器。在**example**目录中，我们内置了**baidu_map_mcp**示例，供开发者参考使用。
 
-# 3、OpenBenchMark
+## 3、OpenBenchMark
 为更好地促进学术交流，加速大模型外挂知识库在企业中的落地和技术进步，KAG在本次发版中发布了更详细的Benchmark复现步骤，并开源了全部代码和数据。这将方便开发者和科研人员复现并对齐各数据集的结果。为了更准确地量化推理效果，我们采用了EM（Exact Match）、F1和LLM_Accuracy等多项评估指标。在原有TwoWiki、Musique、HotpotQA等数据集的基础上，本次更新新增了OpenKG OneEval知识图谱类问答数据集（如AffairQA和PRQA），以分别验证**cypher_executor**及KAG默认框架的能力。
 
 搭建Benchmark是一个耗时且复杂的工程。在未来的工作中，我们将持续扩充更多Benchmark数据集，并提供针对不同领域的解决方案，进一步提升大模型利用外部知识的准确性、严谨性和一致性。我们也诚邀社区同仁共同参与，携手推进KAG框架在各类任务中的能力提升与实际应用落地。
@@ -306,7 +306,7 @@ OpenKG OneEval 榜单的重点在于评估大语言模型（LLM）对各类知
 | KAG-V0.7 | **77.5%** | **83.1%** | **88.2%** | 基于KAG 框架自定义AffairQA pipeline | 蚂蚁KAG 团队  |
 
 
-# 4、产品及平台优化
+## 4、产品及平台优化
 本次更新优化了知识问答的产品体验，用户可访问 [KAG 用户手册](https://openspg.github.io/v2/docs_ch)，在快速开始->产品模式一节，获取我们的语料文件以复现以下视频中的结果。
 
 + **知识构建Demo**
@@ -324,10 +324,10 @@ OpenKG OneEval 榜单的重点在于评估大语言模型（LLM）对各类知
 ### 4.3、索引构建能力完善
 本次更新提升结构化数据导入能力，支持从 CSV、ODPS、SLS 等多种数据源导入结构化数据，优化数据加载流程，提升使用体验；可同时处理"结构化"和"非结构化"数据，满足多样性需求。同时，增强了知识构建的任务管理能力，提供任务调度、执行日志、数据抽样 等功能，便于问题追踪与分析。
 
-# 5、后续计划
+## 5、后续计划
 近期版本迭代中，我们持续致力于持续提升大模型利用外部知识库的能力，实现大模型与符号知识的双向增强和有机融合，不断提升专业场景推理问答的事实性、严谨性和一致性等，我们也将持续发布，不断提升能力的上限，不断推进垂直领域的落地。
 
-# 6、致谢
+## 6、致谢
 本次发布修复了分层检索模块中的若干问题，在此特别感谢反馈这些问题的社区开发者们。
 
 此次框架升级得到了以下专家和同仁的鼎力支持，我们深表感激：

website/docs/recent_posts/release_notes/0.7.md

@@ -134,15 +134,15 @@ const config = {
             title: 'Contact US',
             items: [
               {
-                label: 'zhengke.gzk@antgroup.com',
+                label: 'mengshu.sms@antgroup.com',
                 to: 'https://github.com/OpenSPG/KAG',
               },
               {
-                label: 'leywar.liang@antgroup.com',
+                label: 'zhengke.gzk@antgroup.com',
                 to: 'https://github.com/OpenSPG/KAG',
               },
               {
-                label: 'mengshu.sms@antgroup.com',
+                label: 'leywar.liang@antgroup.com',
                 to: 'https://github.com/OpenSPG/KAG',
               },
             ],