Class 1 Homework — MCP, Ollama & LangChain (geomingical)

Class1/class1/.mcp.json

@@ -0,0 +1,55 @@
+{
+  "mcpServers": {
+    "filesystem": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-filesystem",
+        "/Users/ming/Desktop/Learning/MLE_in_Gen_AI-Course/Class1/class1"
+      ]
+    },
+    "sequential-thinking": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-sequential-thinking"
+      ]
+    },
+    "puppeteer": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-puppeteer"
+      ]
+    },
+    "brave-search": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-brave-search"
+      ],
+      "env": {
+        "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY"
+      }
+    },
+    "github": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-github"
+      ],
+      "env": {
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PERSONAL_ACCESS_TOKEN"
+      }
+    },
+    "notion": {
+      "type": "http",
+      "url": "https://mcp.notion.com/mcp"
+    }
+  }
+}

Class1/class1/Class 1 Homework.ipynb

@@ -118,12 +118,16 @@
   },
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "curl http://localhost:11434/v1/chat/completions \\\n",
     "    -H \"Content-Type: application/json\" \\\n",
     "    -d '{\n",
-    "        \"model\": \"llama2\",\n",
+    "        \"model\": \"gemma4:26b\",\n",
     "        \"messages\": [\n",
     "            {\n",
     "                \"role\": \"system\",\n",
@@ -146,9 +150,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The 2020 World Series was played at **Globe Life Field** in Arlington, Texas. \n",
+      "\n",
+      "Because of the COVID-19 pandemic, Major League Baseball decided to host the entire postseason at a single site to minimize travel and reduce the risk of virus transmission.\n"
+     ]
+    }
+   ],
    "source": [
     "from openai import OpenAI\n",
     "\n",
@@ -158,7 +172,7 @@
     ")\n",
     "\n",
     "response = client.chat.completions.create(\n",
-    "  model=\"llama2\",\n",
+    "  model=\"gemma4:26b\",\n",
     "  messages=[\n",
     "    {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
     "    {\"role\": \"user\", \"content\": \"Who won the world series in 2020?\"},\n",
@@ -169,6 +183,69 @@
     "print(response.choices[0].message.content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Note\n",
+    "# `base_url` 筆記\n",
+    "## 1. 把 `base_url` 拆成四段看\n",
+    "```python\n",
+    "base_url=\"http://localhost:11434/v1\"\n",
+    "```\n",
+    "可以拆成：\n",
+    "```text\n",
+    "http://localhost:11434/v1\n",
+    "│      │         │     │\n",
+    "│      │         │     └─ OpenAI-compatible API 路徑\n",
+    "│      │         └────── Ollama 預設 port\n",
+    "│      └──────────────── 你的本機電腦\n",
+    "└─────────────────────── HTTP 協定\n",
+    "```\n",
+    "意思是：這段網址不是連到 OpenAI 官方 API，而是連到你自己電腦上正在執行的 Ollama server。\n",
+    "\n",
+    "## 2. `base_url` 像是模型倉庫的地址\n",
+    "可以把：\n",
+    "```python\n",
+    "base_url=\"http://localhost:11434/v1\"\n",
+    "```\n",
+    "想成「模型倉庫的地址」。而：\n",
+    "\n",
+    "```python\n",
+    "model=\"gemma4:26b\"\n",
+    "model=\"qwen3.6:35b\"\n",
+    "```\n",
+    "\n",
+    "則是「你要叫哪一個模型出來工作」。\n",
+    "所以如果 `gemma4:26b` 和 `qwen3.6:35b` 都在同一個 Ollama 裡面，只需要一個 `base_url`：\n",
+    "```python\n",
+    "client = OpenAI(\n",
+    "    base_url=\"http://localhost:11434/v1\",\n",
+    "    api_key=\"ollama\",\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "每次呼叫時，只要換 `model` 名稱就好：\n",
+    "```python\n",
+    "response = client.chat.completions.create(\n",
+    "    model=\"gemma4:26b\",\n",
+    "    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n",
+    ")\n",
+    "\n",
+    "response = client.chat.completions.create(\n",
+    "    model=\"qwen3.6:35b\",\n",
+    "    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "## 3. 核心觀念\n",
+    "\n",
+    "* 同一個 Ollama server 裡有多個模型時，通常只需要一個 `base_url`。\n",
+    "* `base_url` 決定要連到哪一個模型服務。\n",
+    "* `model` 決定要使用該服務裡面的哪一個模型。\n",
+    "* 只有當模型放在不同服務或不同機器上時，才需要不同的 `base_url`。\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -220,9 +297,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "User prompt: 'What is the capital of Germany?'\n",
+      "Model answer: The capital of Germany is **Berlin**.\n"
+     ]
+    }
+   ],
    "source": [
     "# Example: Using LCEL to reproduce a \"Basic Prompting\" scenario\n",
     "from langchain_core.prompts import PromptTemplate\n",
@@ -236,7 +322,7 @@
     ")\n",
     "\n",
     "# 3. Define the model\n",
-    "model = ChatOllama(model = [\"llama2\"])  # Using Ollama \n",
+    "model = ChatOllama(model = \"gemma4:26b\")  # Using Ollama \n",
     "\n",
     "# 4. Chain the components together using LCEL\n",
     "chain = (\n",
@@ -253,6 +339,85 @@
     "print(\"Model answer:\", result)\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#%pip install -U langchain-ollama\n",
+    "#%pip show langchain langchain-core langchain-community langchain-ollama"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7862\n",
+      "* To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7862/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "from langchain_ollama import ChatOllama\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "llm = ChatOllama(\n",
+    "    model=\"gemma4:26b\",\n",
+    "    base_url=\"http://localhost:11434\",\n",
+    "    temperature=0.7\n",
+    ")\n",
+    "\n",
+    "def chat_with_ollama(user_input):\n",
+    "    try:\n",
+    "        if not user_input.strip():\n",
+    "            return \"Please enter a message.\"\n",
+    "\n",
+    "        response = llm.invoke([\n",
+    "            HumanMessage(content=user_input)\n",
+    "        ])\n",
+    "\n",
+    "        return response.content\n",
+    "\n",
+    "    except Exception as e:\n",
+    "        return f\"Error: {type(e).__name__}\\n\\n{str(e)}\"\n",
+    "\n",
+    "demo = gr.Interface(\n",
+    "    fn=chat_with_ollama,\n",
+    "    inputs=gr.Textbox(lines=5, label=\"Your prompt\"),\n",
+    "    outputs=gr.Textbox(lines=10, label=\"Ollama response\"),\n",
+    "    title=\"Ollama + LangChain + Gradio\"\n",
+    ")\n",
+    "\n",
+    "demo.launch()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -266,8 +431,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "llm_course_env",
+   "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": "3.12.11"
   }
  },
  "nbformat": 4,

Class1/class1/hw_output/hello.txt

@@ -0,0 +1 @@
+Hello MCP!

Class1/class1/hw_output/notion.txt

@@ -0,0 +1 @@
+https://www.notion.so/MCP-Automation-Test-36970be48b76812fbfeaca71d47e808d?source=copy_link

Class1/class1/hw_output/table_no_outline_h2.csv

@@ -0,0 +1,6 @@
+Day,Time,Location
+Wednesday,3-6 pm,Cal Poly Campus (follow U-Pick Signs)
+Thursday,2:30-5pm,Morro Bay Farmer's Market
+Thursday,6:10-9pm,Downtown SLO Farmer's Market
+Saturday,8-10:30am,Farmer's Market new Embassy Suites
+Saturday,11am-2pm,Cal Poly Campus (follow U-Pick signs)

Class1/class1/hw_output/table_no_outline_h2.md

@@ -0,0 +1,13 @@
+# Table No Outline - H2
+
+> **Source:** https://afd.calpoly.edu/web/sample-tables
+> **Caption:** No Style Table Listing
+> **Extracted by:** Puppeteer MCP — 2026-05-23
+
+| Day | Time | Location |
+|-----|------|----------|
+| Wednesday | 3-6 pm | Cal Poly Campus (follow U-Pick Signs) |
+| Thursday | 2:30-5pm | Morro Bay Farmer's Market |
+| Thursday | 6:10-9pm | Downtown SLO Farmer's Market |
+| Saturday | 8-10:30am | Farmer's Market new Embassy Suites |
+| Saturday | 11am-2pm | Cal Poly Campus (follow U-Pick signs) |