Skip to content

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

TypeScript

docs: sync EN README with CN — add overview, community, insights screenshots

nash_su49b74ba2d215
diff --git a/README.md b/README.md
index 12b178e1..fceb93ae 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@
---
<p align="center">
- <img src="assets/3-knowledge_graph.jpg" width="100%" alt="Knowledge Graph">
+ <img src="assets/overview.jpg" width="100%" alt="Overview">
</p>
## What is this?
@@ -139,6 +139,10 @@ Not in the original. Automatic discovery of knowledge clusters using the **Louva
- **12-color palette** — distinct visual separation between clusters
- **Community legend** — shows top node label, member count, and cohesion per cluster
+<p align="center">
+ <img src="assets/kg_community.jpg" width="100%" alt="Louvain Community Detection">
+</p>
+
### 6. Graph Insights — Surprising Connections & Knowledge Gaps
Not in the original. The system **automatically analyzes graph structure** to surface actionable insights:
@@ -158,6 +162,10 @@ Not in the original. The system **automatically analyzes graph structure** to su
- Knowledge gaps and bridge nodes have a **Deep Research button** — triggers LLM-optimized research with domain-aware topics (reads overview.md + purpose.md for context)
- Research topic shown in **editable confirmation dialog** before starting — user can refine topic and search queries
+<p align="center">
+ <img src="assets/kg_insights.jpg" width="100%" alt="Graph Insights">
+</p>
+
### 7. Optimized Query Retrieval Pipeline
The original describes a simple query where the LLM reads relevant pages. We built a **4-phase retrieval pipeline** with budget control:
diff --git a/README_CN.md b/README_CN.md
index 9e5b9067..4ea8e15b 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -25,7 +25,7 @@
---
<p align="center">
- <img src="assets/3-knowledge_graph.jpg" width="100%" alt="知识图谱">
+ <img src="assets/overview.jpg" width="100%" alt="知识图谱">
</p>
## 这是什么?
@@ -139,6 +139,10 @@ LLM Wiki 是一个跨平台桌面应用,能将你的文档自动转化为有
- **12 色调色板** —— 集群之间视觉区分清晰
- **社区图例** —— 显示核心节点标签、成员数和内聚度
+<p align="center">
+ <img src="assets/kg_community.jpg" width="100%" alt="Louvain 社区检测">
+</p>
+
### 6. 图谱洞察 —— 惊奇连接与知识空白
原始设计中没有。系统**自动分析图谱结构**,呈现可操作的洞察:
@@ -158,6 +162,10 @@ LLM Wiki 是一个跨平台桌面应用,能将你的文档自动转化为有
- 知识空白和桥接节点附带 **Deep Research 按钮** —— 触发 LLM 智能主题生成(读取 overview.md + purpose.md 获取领域上下文)
- 研究主题在**可编辑确认对话框**中展示 —— 用户可修改主题和搜索查询后再启动
+<p align="center">
+ <img src="assets/kg_insights.jpg" width="100%" alt="图谱洞察">
+</p>
+
### 7. 优化的查询检索管线
原始设计描述了 LLM 读取相关页面的简单查询。我们构建了带预算控制的**四阶段检索管线**:
diff --git a/assets/kg_community.jpg b/assets/kg_community.jpg
new file mode 100644
index 00000000..bc5d8bd9
Binary files /dev/null and b/assets/kg_community.jpg differ
diff --git a/assets/kg_insights.jpg b/assets/kg_insights.jpg
new file mode 100644
index 00000000..366fa3e7
Binary files /dev/null and b/assets/kg_insights.jpg differ
diff --git a/assets/overview.jpg b/assets/overview.jpg
new file mode 100644
index 00000000..4202e428
Binary files /dev/null and b/assets/overview.jpg differ