From a0d38019c40127bba4d1324f92cfca63c9294636 Mon Sep 17 00:00:00 2001
From: kazusa <409053122@qq.com>
Date: Wed, 7 Jan 2026 20:40:24 +0800
Subject: [PATCH] art

---
 README.md | 86 ++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 59 insertions(+), 27 deletions(-)

diff --git a/README.md b/README.md
index 3054961..794d103 100644
--- a/README.md
+++ b/README.md
@@ -1,53 +1,85 @@
 # AI Assistant Java (Spring AI + pgvector)
 
-This module is an independent Spring Boot 3 service that provides an OpenAI-compatible API.
+基于 RAG（检索增强生成）的仓配中心 AI 助手服务，提供 OpenAI 兼容 API。
 
-## Requirements
+## 技术栈
 
-- Java 17+
-- PostgreSQL with pgvector
-- Ollama (local inference)
+- Java 17 + Spring Boot 3.2
+- Spring AI + Ollama
+- PostgreSQL + pgvector
+- MyBatis-Plus
 
-## Start pgvector (Docker)
+## 快速启动
 
-```
+### 1. 启动 pgvector
+
+```bash
 docker run --name pgvector -e POSTGRES_PASSWORD=postgres -e POSTGRES_DB=assistant \
   -p 5432:5432 -d pgvector/pgvector:pg16
 ```
 
-## Start Ollama models
+### 2. 启动 Ollama 模型
 
-```
-ollama pull qwen2.5:7b
-ollama pull bge-m3
+```bash
+ollama pull qwen2.5:7b   # 对话模型
+ollama pull bge-m3       # Embedding 模型
 ```
 
-## Configure
+### 3. 启动服务
 
-- `src/main/resources/application.yml`
-- `src/main/resources/domains.yml`
-
-## Run
-
-```
+```bash
 ./mvnw spring-boot:run
 ```
 
-## OpenAI-compatible endpoint
+## API 接口
 
-```
-POST http://127.0.0.1:8010/v1/chat/completions
-```
+### 知识录入
 
-Sample payload:
+```bash
+POST http://localhost:8010/ingest
 
-```
 {
-  "model": "local",
-  "tenant_id": "customer_a",
+  "domain_id": "general",
+  "content": "SKU A001 是一款高端电子产品，库存预警阈值为100件"
+}
+```
+
+### 智能问答 (OpenAI 兼容)
+
+```bash
+POST http://localhost:8010/v1/chat/completions
+
+{
+  "model": "qwen2.5:7b",
   "stream": true,
   "messages": [
-    {"role": "user", "content": "订单有多少?"}
+    {"role": "user", "content": "SKU A001 的库存预警阈值是多少？"}
   ]
 }
 ```
+
+## 配置说明
+
+`src/main/resources/application.yml`:
+
+```yaml
+assistant:
+  routing:
+    use-llm: true           # 是否使用 LLM 进行域路由
+    fallback-domain: general # 默认域
+  vector:
+    table: assistant_vectors # 向量表名
+    dimension: 1024          # Embedding 维度
+  domains:
+    - id: general
+      name: 通用知识
+      keywords: []
+```
+
+## 架构
+
+```
+用户问题 → 域路由 → 相似度搜索(RAG) → LLM 生成回答
+              ↓
+         向量知识库 (pgvector)
+```