282 lines
9.9 KiB
Python
282 lines
9.9 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
创建「智能学习助手」(KG+RAG) Agent
|
|||
|
|
|
|||
|
|
基于知识图谱 + RAG 增强的学习助手：
|
|||
|
|
- 实体抽取：自动从学习材料提取知识点
|
|||
|
|
- 关系图谱：构建前置/扩展/包含/示例关系
|
|||
|
|
- 向量检索：语义搜索相关知识和历史记忆
|
|||
|
|
- 永久记忆：跨会话保存学习进度和用户画像
|
|||
|
|
|
|||
|
|
用法:
|
|||
|
|
cd backend && .\\venv\\Scripts\\python.exe scripts/create_learning_assistant_agent.py
|
|||
|
|
|
|||
|
|
环境变量:
|
|||
|
|
PLATFORM_BASE_URL - 平台地址（默认 http://127.0.0.1:8037）
|
|||
|
|
PLATFORM_USERNAME - 用户名（默认 admin）
|
|||
|
|
PLATFORM_PASSWORD - 密码（默认 123456）
|
|||
|
|
AGENT_NAME - Agent 名称（默认 智能学习助手(KG+RAG)）
|
|||
|
|
SUBJECT - 学科领域（默认 通用）
|
|||
|
|
LEVEL - 难度级别（默认 中级）
|
|||
|
|
"""
|
|||
|
|
from __future__ import annotations
|
|||
|
|
|
|||
|
|
import json
|
|||
|
|
import os
|
|||
|
|
import sys
|
|||
|
|
from typing import Any, Dict, List, Optional
|
|||
|
|
|
|||
|
|
import requests
|
|||
|
|
|
|||
|
|
BASE = os.getenv("PLATFORM_BASE_URL", "http://127.0.0.1:8037").rstrip("/")
|
|||
|
|
USER = os.getenv("PLATFORM_USERNAME", "admin")
|
|||
|
|
PWD = os.getenv("PLATFORM_PASSWORD", "123456")
|
|||
|
|
AGENT_NAME = os.getenv("AGENT_NAME", "智能学习助手(KG+RAG)")
|
|||
|
|
SUBJECT = os.getenv("SUBJECT", "通用")
|
|||
|
|
LEVEL = os.getenv("LEVEL", "中级")
|
|||
|
|
|
|||
|
|
# 学习助手专用工具集
|
|||
|
|
LEARNING_TOOLS = [
|
|||
|
|
"knowledge_graph_search",
|
|||
|
|
"knowledge_graph_add",
|
|||
|
|
"entity_search",
|
|||
|
|
"learning_path",
|
|||
|
|
"file_read",
|
|||
|
|
"file_write",
|
|||
|
|
"text_analyze",
|
|||
|
|
"web_search",
|
|||
|
|
"task_plan",
|
|||
|
|
"self_review",
|
|||
|
|
"math_calculate",
|
|||
|
|
"json_process",
|
|||
|
|
"datetime",
|
|||
|
|
"http_request",
|
|||
|
|
"code_execute",
|
|||
|
|
"system_info",
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
SYSTEM_PROMPT = f"""# 角色：智能学习助手（知识图谱 + RAG 增强版）
|
|||
|
|
|
|||
|
|
你是专为深度学习场景设计的 AI 学习助手，具备**知识图谱构建**、**向量语义检索**和**永久记忆**能力。
|
|||
|
|
|
|||
|
|
## 核心架构
|
|||
|
|
|
|||
|
|
你的知识系统由三层组成：
|
|||
|
|
1. **知识图谱 (Knowledge Graph)**：结构化存储知识点实体及其前置/扩展/包含/示例关系，构建学科知识网络
|
|||
|
|
2. **向量记忆 (Vector Memory)**：语义检索历史对话和相关知识，找到最相似的学习内容
|
|||
|
|
3. **长期记忆 (Persistent Memory)**：跨会话保存用户画像、学习进度、薄弱环节
|
|||
|
|
|
|||
|
|
## 当前学习配置
|
|||
|
|
- 学科领域：{SUBJECT}
|
|||
|
|
- 难度级别：{LEVEL}
|
|||
|
|
|
|||
|
|
## 工作流程（每次对话必须遵循）
|
|||
|
|
|
|||
|
|
### 阶段 1：理解与分析
|
|||
|
|
1. 理解用户的学习意图（提问 / 复习 / 练习 / 总结 / 规划）
|
|||
|
|
2. 用 `knowledge_graph_search` 检索相关知识图谱实体
|
|||
|
|
3. 如果用户提供了新的学习材料/知识点，用 `knowledge_graph_add` 自动提取并存储到知识图谱
|
|||
|
|
|
|||
|
|
### 阶段 2：知识检索与融合
|
|||
|
|
4. 结合图谱检索结果和历史向量记忆，构建完整的知识上下文
|
|||
|
|
5. 用 `entity_search` 查找特定概念的前置知识和扩展内容
|
|||
|
|
6. 如果需要学习路径建议，用 `learning_path` 分析依赖关系并给出学习顺序
|
|||
|
|
|
|||
|
|
### 阶段 3：生成与交付
|
|||
|
|
7. 基于融合后的知识上下文生成高质量回答
|
|||
|
|
8. 回答应包含：
|
|||
|
|
- **核心概念解释**（关联知识图谱中的实体）
|
|||
|
|
- **前置知识提醒**（如果有依赖关系）
|
|||
|
|
- **实例或练习题**（如适用）
|
|||
|
|
- **扩展阅读建议**（关联的扩展知识点）
|
|||
|
|
9. 用 `self_review` 自检回答质量，不达标则修正
|
|||
|
|
|
|||
|
|
### 阶段 4：巩固与记忆
|
|||
|
|
10. 将本轮对话中的重要知识点持久化到长期记忆
|
|||
|
|
11. 更新用户画像（掌握程度、薄弱环节、学习偏好）
|
|||
|
|
|
|||
|
|
## 知识图谱工具使用指南
|
|||
|
|
|
|||
|
|
| 工具 | 用途 | 何时使用 |
|
|||
|
|
|------|------|---------|
|
|||
|
|
| `knowledge_graph_search` | 向量+图谱混合检索 | 每次回答学习问题前 |
|
|||
|
|
| `knowledge_graph_add` | 从文本提取实体和关系 | 用户分享学习材料/新知识点时 |
|
|||
|
|
| `entity_search` | 关键词搜索实体 | 查找特定概念详情时 |
|
|||
|
|
| `learning_path` | 推荐学习路径 | 用户询问学习顺序/计划时 |
|
|||
|
|
|
|||
|
|
## 回答风格
|
|||
|
|
- 使用 Markdown 格式，层次分明
|
|||
|
|
- 关键概念用 **粗体** 标记
|
|||
|
|
- 公式用代码块或 LaTeX 表达
|
|||
|
|
- 每个回答末尾附上「📚 相关知识点」列表（来自图谱检索结果）
|
|||
|
|
- 必要时用 `task_plan` 为用户制定学习计划
|
|||
|
|
|
|||
|
|
## 记忆与个性化
|
|||
|
|
- 记住用户的学习进度和薄弱环节
|
|||
|
|
- 根据用户级别（{LEVEL}）调整解释深度
|
|||
|
|
- 对反复出错的知识点主动提醒和强化训练
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
你是学习者最可靠的 AI 伙伴。开始吧！"""
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _login() -> Optional[str]:
|
|||
|
|
"""登录获取 token。"""
|
|||
|
|
try:
|
|||
|
|
r = requests.post(
|
|||
|
|
f"{BASE}/api/v1/auth/login",
|
|||
|
|
data={"username": USER, "password": PWD},
|
|||
|
|
headers={"Content-Type": "application/x-www-form-urlencoded"},
|
|||
|
|
timeout=15,
|
|||
|
|
)
|
|||
|
|
if r.status_code == 200:
|
|||
|
|
return r.json().get("access_token")
|
|||
|
|
print(f"登录失败: {r.status_code} {r.text[:300]}", file=sys.stderr)
|
|||
|
|
return None
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f"登录异常: {e}", file=sys.stderr)
|
|||
|
|
return None
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _find_agent_by_name(token: str, name: str) -> Optional[Dict[str, Any]]:
|
|||
|
|
"""查找同名 Agent。"""
|
|||
|
|
h = {"Authorization": f"Bearer {token}"}
|
|||
|
|
r = requests.get(f"{BASE}/api/v1/agents", params={"search": name, "limit": 50}, headers=h, timeout=30)
|
|||
|
|
if r.status_code != 200:
|
|||
|
|
return None
|
|||
|
|
for a in r.json() or []:
|
|||
|
|
if a.get("name") == name:
|
|||
|
|
return a
|
|||
|
|
return None
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _build_workflow() -> Dict[str, Any]:
|
|||
|
|
"""构建学习助手工作流。"""
|
|||
|
|
return {
|
|||
|
|
"nodes": [
|
|||
|
|
{
|
|||
|
|
"id": "start-1",
|
|||
|
|
"type": "start",
|
|||
|
|
"position": {"x": 80, "y": 240},
|
|||
|
|
"data": {"label": "学习任务开始"},
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"id": "llm-learning",
|
|||
|
|
"type": "llm",
|
|||
|
|
"position": {"x": 380, "y": 240},
|
|||
|
|
"data": {
|
|||
|
|
"label": "智能学习助手 (KG+RAG)",
|
|||
|
|
"prompt": SYSTEM_PROMPT,
|
|||
|
|
"temperature": 0.7,
|
|||
|
|
"provider": "deepseek",
|
|||
|
|
"model": "deepseek-chat",
|
|||
|
|
"max_iterations": 20,
|
|||
|
|
"enable_tools": True,
|
|||
|
|
"tools": LEARNING_TOOLS,
|
|||
|
|
"selected_tools": LEARNING_TOOLS,
|
|||
|
|
"max_tool_iterations": 18,
|
|||
|
|
"memory": True,
|
|||
|
|
"memory_max_history": 30,
|
|||
|
|
"memory_vector_enabled": True,
|
|||
|
|
"memory_vector_top_k": 8,
|
|||
|
|
"memory_persist": True,
|
|||
|
|
"memory_learning": True,
|
|||
|
|
},
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"id": "end-1",
|
|||
|
|
"type": "end",
|
|||
|
|
"position": {"x": 680, "y": 240},
|
|||
|
|
"data": {"label": "学习完成"},
|
|||
|
|
},
|
|||
|
|
],
|
|||
|
|
"edges": [
|
|||
|
|
{
|
|||
|
|
"id": "e_start_learning",
|
|||
|
|
"source": "start-1",
|
|||
|
|
"target": "llm-learning",
|
|||
|
|
"sourceHandle": "right",
|
|||
|
|
"targetHandle": "left",
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"id": "e_learning_end",
|
|||
|
|
"source": "llm-learning",
|
|||
|
|
"target": "end-1",
|
|||
|
|
"sourceHandle": "right",
|
|||
|
|
"targetHandle": "left",
|
|||
|
|
},
|
|||
|
|
],
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main() -> int:
|
|||
|
|
token = _login()
|
|||
|
|
if not token:
|
|||
|
|
return 1
|
|||
|
|
|
|||
|
|
h = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
|
|||
|
|
|
|||
|
|
# 检查是否已存在
|
|||
|
|
existing = _find_agent_by_name(token, AGENT_NAME)
|
|||
|
|
if existing:
|
|||
|
|
print(f"Agent「{AGENT_NAME}」已存在 (id={existing['id']})，将更新工作流和工具配置")
|
|||
|
|
agent_id = existing["id"]
|
|||
|
|
else:
|
|||
|
|
# 创建新 Agent
|
|||
|
|
wf = _build_workflow()
|
|||
|
|
body = {
|
|||
|
|
"name": AGENT_NAME,
|
|||
|
|
"description": (
|
|||
|
|
f"知识图谱+RAG增强学习助手。学科：{SUBJECT}，难度：{LEVEL}。"
|
|||
|
|
"支持实体抽取、关系图谱构建、向量语义检索、学习路径推荐、永久记忆。"
|
|||
|
|
),
|
|||
|
|
"workflow_config": wf,
|
|||
|
|
}
|
|||
|
|
r = requests.post(f"{BASE}/api/v1/agents", headers=h, json=body, timeout=60)
|
|||
|
|
if r.status_code != 201:
|
|||
|
|
print(f"创建失败: {r.status_code} {r.text[:500]}", file=sys.stderr)
|
|||
|
|
return 1
|
|||
|
|
agent_id = r.json()["id"]
|
|||
|
|
print(f"Agent 创建成功: id={agent_id} name={AGENT_NAME}")
|
|||
|
|
|
|||
|
|
# 更新工作流配置（确保工具集是最新的）
|
|||
|
|
wf = _build_workflow()
|
|||
|
|
up = requests.put(
|
|||
|
|
f"{BASE}/api/v1/agents/{agent_id}",
|
|||
|
|
headers=h,
|
|||
|
|
json={
|
|||
|
|
"description": (
|
|||
|
|
f"知识图谱+RAG增强学习助手。学科：{SUBJECT}，难度：{LEVEL}。"
|
|||
|
|
"工作流：开始→智能学习助手(KG+RAG)→结束。"
|
|||
|
|
"核心能力：实体抽取、关系图谱构建、向量语义检索、学习路径推荐、永久记忆。"
|
|||
|
|
),
|
|||
|
|
"workflow_config": wf,
|
|||
|
|
},
|
|||
|
|
timeout=120,
|
|||
|
|
)
|
|||
|
|
if up.status_code != 200:
|
|||
|
|
print(f"更新失败: {up.status_code} {up.text[:500]}", file=sys.stderr)
|
|||
|
|
return 1
|
|||
|
|
|
|||
|
|
print(f"Agent「{AGENT_NAME}」配置完成")
|
|||
|
|
print(f" ID: {agent_id}")
|
|||
|
|
print(f" 学科: {SUBJECT}")
|
|||
|
|
print(f" 级别: {LEVEL}")
|
|||
|
|
print(f" 工具 ({len(LEARNING_TOOLS)}): {', '.join(LEARNING_TOOLS)}")
|
|||
|
|
print(f" 记忆: 向量记忆+长期记忆+自主学习 已启用")
|
|||
|
|
print(f" 知识图谱: 实体抽取+关系构建+混合检索 已启用")
|
|||
|
|
print()
|
|||
|
|
print("使用方法：")
|
|||
|
|
print(f" 1. 在 Agent 管理页面找到「{AGENT_NAME}」")
|
|||
|
|
print(f" 2. 点击「使用」开始对话")
|
|||
|
|
print(f" 3. 可以分享学习材料让助手自动构建知识图谱")
|
|||
|
|
print(f" 4. 查询知识点时会自动做图谱+向量混合检索")
|
|||
|
|
print()
|
|||
|
|
print(json.dumps({"id": agent_id, "name": AGENT_NAME}, ensure_ascii=False))
|
|||
|
|
return 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
raise SystemExit(main())
|