ex-brain 0.1.0 → 0.2.0

package/README.md

@@ -1,95 +1,145 @@
 # ex-brain
 
-CLI 个人知识库，基于 [seekdb](https://docs.seekdb.ai/) 构建，支持页面管理、混合检索、时间线、标签、导入导出与 MCP Server。
+CLI personal knowledge base built on [seekdb](https://docs.seekdb.ai/), featuring page management, hybrid search, timelines, tags, import/export, and MCP Server.
 
-## 核心功能
+## Core Features
 
-- **知识图谱可视化** - 交互式图谱，展示实体关联关系
-- **智能编译** - 语义分析，智能更新 Compiled Truth
-- **时间线管理** - 自动提取事件，记录历史演变
-- **混合检索** - 全文搜索 + 向量语义查询
-- **实体链接** - 自动识别实体，创建关联页面
+- **Knowledge Graph Visualization** - Interactive graph showing entity relationships
+- **Intelligent Compilation** - Semantic analysis with smart Compiled Truth updates
+- **Timeline Management** - Automatic event extraction and history tracking
+- **Hybrid Search** - Full-text search + vector semantic queries
+- **Entity Linking** - Auto-detect entities and create linked pages
 
-## 数据采集
+<img src="https://mdn.alipayobjects.com/huamei_ytl0i7/afts/img/A*TqdfTZ-yCPwAAAAAgBAAAAgAejCYAQ/original" width="800">
 
-推荐使用 [MarkSnip](https://chromewebstore.google.com/detail/kcbaglhfgbkjdnpeokaamjjkddempipm) 作为数据采集工具：
+## Data Collection
 
-- 一键剪藏网页为 Markdown 格式
-- 支持代码块、表格、数学公式
-- 本地处理，隐私友好
-- 支持 Obsidian 集成
+We recommend [MarkSnip](https://chromewebstore.google.com/detail/kcbaglhfgbkjdnpeokaamjjkddempipm) for data collection:
 
-配合 ex-brain 使用：
+- One-click web clipping to Markdown format
+- Supports code blocks, tables, math formulas
+- Local processing, privacy-friendly
+- Obsidian integration support
+
+Use with ex-brain:
 
 ```bash
-# MarkSnip 剪藏后，导入到知识库
+# After clipping with MarkSnip, import to knowledge base
 cat article.md | ebrain put articles/slug --stdin
 
-# 或智能编译
+# Or intelligent compilation
 ebrain compile companies/river-ai --file article.md --source web_clip
 ```
 
-## 安装
+## Installation
 
 ```bash
-# 全局安装（需要 Bun 或 Node.js）
+# Global installation (requires Bun or Node.js)
 bun install -g ex-brain
-# 或
+# or
 npm install -g ex-brain
 
 ebrain --help
 ```
 
-## 快速开始
+## Quick Start
 
 ```bash
-# 初始化（自动创建 ~/.ebrain/data/ebrain.db）
+# Initialize (creates ~/.ebrain/data/ebrain.db automatically)
 ebrain init
 
-# 写入页面
+# Write a page
 ebrain put my/note --file note.md
 
-# 知识图谱可视化
-ebrain graph                    # 启动图谱 Web UI (http://localhost:3000)
-ebrain graph --port 8080 --open # 指定端口并自动打开浏览器
+# Knowledge graph visualization
+ebrain graph                    # Start graph Web UI (http://localhost:3000)
+ebrain graph --port 8080 --open # Custom port and auto-open browser
 
-# 智能编译新信息
+# Intelligently compile new information
 ebrain compile companies/river-ai "River AI completed Series A funding" --source meeting_notes
 
-# 从页面提取时间线事件
+# Extract timeline events from a page
 ebrain timeline extract companies/river-ai
 
-# 检索
-ebrain search "某主题"
-ebrain query "某问题"
+# Search
+ebrain search "some topic"
+ebrain query "some question"
+
+# AI-powered Q&A with LLM (RAG)
+ebrain query --llm "What is the main idea of River AI's product?"
+ebrain query --llm "What are Mario Zechner's main views on game development?"
+
+# Smart ingest: compile + timeline + entity links in one command
+ebrain smart-ingest companies/river-ai --file article.md
 
-# 启动 MCP Server（供 AI 工具调用）
+# Start MCP Server (for AI tool integration)
 ebrain serve
 ```
 
-## 配置
+## Configuration
 
-编辑 `~/.ebrain/settings.json`：
+Edit `~/.ebrain/settings.json`:
 
 ```jsonc
 {
   "db": { "path": "~/.ebrain/data/ebrain.db" },
   "embed": {
-    "provider": "hash",          // 或 "openai_compatible"
+    "provider": "hash",          // or "openai_compatible"
     "baseURL": "...",
     "model": "...",
     "dimensions": 1024,
     "apiKey": "sk-..."
+  },
+  "llm": {
+    "baseURL": "https://dashscope.aliyuncs.com/compatible-mode/v1",
+    "model": "qwen-plus",
+    "apiKey": "sk-..."
+  },
+  "extraction": {
+    "confidenceThreshold": 0.7   // Entity extraction confidence (0~1)
   }
 }
 ```
 
-运行 `ebrain config` 查看当前生效配置。详见 [docs/ebrain-cli.md](docs/ebrain-cli.md)。
+Run `ebrain config` to view active configuration. See [docs/ebrain-cli.md](docs/ebrain-cli.md) for details.
+
+## AI Q&A (RAG)
+
+Ask natural language questions and get answers based on your knowledge base:
+
+```bash
+# Basic Q&A
+ex-brain query --llm "What is the main idea of River AI's product?"
+
+# Control context depth
+ebrain query --llm "What happened in Q4?" --context-limit 3
+```
+
+How it works:
+
+1. **Semantic Search** — Finds top matching pages for your question
+2. **Multi-Layer Context Collection** — Builds rich context from:
+   - **Page Content** — Compiled truth + timeline for each matched page
+   - **Raw Documents** — Original imported documents (via `raw set`)
+   - **Linked Pages** — Incoming and outgoing linked pages, filtered by semantic relevance to the question
+3. **LLM Synthesis** — Generates a sourced answer with `[[slug|title]]` citations
+
+Configure LLM in `~/.ebrain/settings.json`:
+
+```json
+{
+  "llm": {
+    "baseURL": "https://dashscope.aliyuncs.com/compatible-mode/v1",
+    "model": "qwen-plus",
+    "apiKey": "sk-..."
+  }
+}
+```
 
-## 开发
+## Development
 
 ```bash
 bun install
 bun run src/cli.ts --help
 bun test
-```
+```

package/package.json

@@ -1,15 +1,15 @@
 {
   "name": "ex-brain",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "CLI personal knowledge base powered by seekdb",
-  "main": "dist/cli.js",
+  "module": "src/cli.ts",
   "type": "module",
   "bin": {
-    "ebrain": "dist/cli.js"
+    "ebrain": "src/cli.ts"
   },
   "files": [
-    "dist",
-    "README.md"
+    "src",
+    "!src/**/*.test.ts"
   ],
   "scripts": {
     "dev": "bun run src/cli.ts",
@@ -29,6 +29,7 @@
     "@seekdb/openai": "1.2.0",
     "commander": "^14.0.3",
     "gray-matter": "^4.0.3",
+    "jsonrepair": "^3.13.3",
     "pinyin-pro": "^3.28.0",
     "seekdb": "^1.2.0",
     "yaml": "^2.8.3",