♻️ refactor(代码): 重构数据库优化器逻辑

- 移除不必要的DatabaseOptimizer类及其配置
- 添加WebsiteKnowledgeBase以支持网页知识库
- 优化MCPTools的使用，合并多个工具的初始化

.gitignore

@@ -0,0 +1,4 @@
+.env
+.idea
+.venv
+tmp

pyproject.toml

@@ -4,4 +4,18 @@ version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.12"
-dependencies = []
+dependencies = [
+    "agno>=1.2.6",
+    "anthropic>=0.49.0",
+    "ipywidgets>=8.1.5",
+    "lancedb>=0.21.2",
+    "mcp>=1.6.0",
+    "notebook>=7.3.3",
+    "numpy>=2.2.4",
+    "openai>=1.69.0",
+    "pandas>=2.2.3",
+    "pypdf>=5.4.0",
+    "python-dotenv>=1.1.0",
+    "sqlalchemy>=2.0.40",
+    "tantivy>=0.22.2",
+]

数据库优化工程师.ipynb

@@ -16,11 +16,68 @@
     "- [ ] 精通关系型数据库系统的理论知识以及`postgresql`的实现细节(知识库)\n",
     "- [ ] 能够使用`postgresql mcp server`来分析现有数据库设计(行为)\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-30T15:44:44.236141Z",
+     "start_time": "2025-03-30T15:44:44.223728Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# 然后在notebook中加载\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "# 加载当前目录下的.env文件\n",
+    "load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-30T15:44:58.492402Z",
+     "start_time": "2025-03-30T15:44:45.695125Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from agno.agent import Agent, RunResponse  # noqa\n",
+    "from agno.models.deepseek import DeepSeek\n",
+    "\n",
+    "agent = Agent(model=DeepSeek(id=\"deepseek-chat\"), markdown=True)\n",
+    "\n",
+    "# Get the response in a variable\n",
+    "# run: RunResponse = agent.run(\"Share a 2 sentence horror story\")\n",
+    "# print(run.content)\n",
+    "\n",
+    "# Print the response in the terminal\n",
+    "agent.print_response(\"傻狗\")\n",
+    "# 用jupyter的话输出有问题，妈的,转到py文件"
+   ]
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

数据库优化工程师.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+"""
+PostgreSQL 数据库优化工程师智能体
+
+功能:
+- 使用 DeepSeek 模型进行智能分析
+- 集成 PostgreSQL MCP 服务器工具
+- 加载数据库知识库
+- 提供数据库优化建议
+"""
+
+import asyncio
+import os
+from typing import Optional
+from dataclasses import dataclass
+from dotenv import load_dotenv
+
+from agno.agent import Agent
+from agno.models.deepseek import DeepSeek
+from agno.knowledge.pdf import PDFKnowledgeBase
+from agno.vectordb.lancedb import LanceDb, SearchType
+from agno.embedder.openai import OpenAIEmbedder
+from agno.knowledge.combined import CombinedKnowledgeBase
+from agno.tools.mcp import MCPTools
+from mcp.client.stdio import stdio_client
+from mcp import ClientSession, StdioServerParameters
+from agno.knowledge.website import WebsiteKnowledgeBase
+
+ 
+
+async def main():
+    load_dotenv()
+    """设置知识库"""
+    local_pdf_kb = PDFKnowledgeBase(
+        path="D:\\Sources\\DONGJAK-TOOLS\\pdfs\\Database Fundamentals.pdf",
+        vector_db=LanceDb(
+            table_name="database_fundamentals",
+            uri="tmp/lancedb",
+            search_type=SearchType.vector,
+            embedder=OpenAIEmbedder(id="text-embedding-3-small"),
+        ),
+    )
+    # Create Website knowledge base
+    website_kb = WebsiteKnowledgeBase(
+        urls=["https://www.lucidchart.com/blog/database-design-best-practices"],
+        max_links=10,
+        vector_db=LanceDb(
+            table_name="website_documents",
+            uri="tmp/lancedb",
+            search_type=SearchType.vector,
+            embedder=OpenAIEmbedder(id="text-embedding-3-small"),
+        ),
+    )
+
+    knowledge_base = CombinedKnowledgeBase(
+        sources=[local_pdf_kb, website_kb],
+        vector_db=LanceDb(
+            table_name="combined_documents",
+            uri="tmp/lancedb",
+            search_type=SearchType.vector,
+            embedder=OpenAIEmbedder(id="text-embedding-3-small"),
+        ),
+    )
+    knowledge_base.load()
+
+    postgres_server_params = StdioServerParameters(
+        command="cmd",
+        args=[
+            "/c",
+            "npx",
+            "-y",
+            "@modelcontextprotocol/server-postgres",
+            "postgresql://postgres:postgres@192.168.1.7:5432/aq",
+        ],
+        env={},
+    )
+
+    searxng_server_params = StdioServerParameters(
+        command="cmd",
+        args=[
+            "/c",
+            "npx",
+            "-y",
+            "https://github.com/ihor-sokoliuk/mcp-searxng.git",
+        ],
+        env={
+            "SEARXNG_URL": "https://searchxng.ailoveworld.cn",
+        },
+    )
+    # Create a client session to connect to the MCP server
+    async with (
+        MCPTools(server_params=postgres_server_params) as postgres_tools,
+        MCPTools(server_params=searxng_server_params) as searxng_tools,
+    ):
+        agent = Agent(
+            model=DeepSeek(id="deepseek-chat"),
+            markdown=True,
+            knowledge=knowledge_base,
+            search_knowledge=True,
+            show_tool_calls=True,
+            tools=[postgres_tools, searxng_tools],
+        )
+        await agent.aprint_response("帮我分析一下aq.public数据库,并给出优化建议", stream=True)
+        # await agent.aprint_response("阅读下 https://www.lucidchart.com/blog/database-design-best-practices 这篇文章", stream=True)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())