week1-day2 exercise

week1/Guide to Jupyter.ipynb

@@ -32,10 +32,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "33d37cd8-55c9-4e03-868c-34aa9cab2c80",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# Click anywhere in this cell and press Shift + Return\n",
     "\n",
@@ -54,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "585eb9c1-85ee-4c27-8dc2-b4d8d022eda0",
    "metadata": {},
    "outputs": [],
@@ -66,10 +77,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "07792faa-761d-46cb-b9b7-2bbf70bb1628",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'bananas'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# The result of the last statement is shown after you run it\n",
     "\n",
@@ -78,10 +100,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "a067d2b1-53d5-4aeb-8a3c-574d39ff654a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "My favorite fruit is anything but anything but bananas\n"
+     ]
+    }
+   ],
    "source": [
     "# Use the variable\n",
     "\n",
@@ -90,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "4c5a4e60-b7f4-4953-9e80-6d84ba4664ad",
    "metadata": {},
    "outputs": [],
@@ -116,10 +146,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "8e5ec81d-7c5b-4025-bd2e-468d67b581b6",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "My favorite fruit is anything but anything but bananas\n"
+     ]
+    }
+   ],
    "source": [
     "# Then run this cell twice, and see if you understand what's going on\n",
     "\n",
@@ -144,10 +182,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "84b1e410-5eda-4e2c-97ce-4eebcff816c5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "My favorite fruit is apples\n"
+     ]
+    }
+   ],
    "source": [
     "print(f\"My favorite fruit is {favorite_fruit}\")"
    ]

week1/day1.ipynb

@@ -162,10 +162,8 @@
     "        \"\"\"\n",
     "        self.url = url\n",
     "        response = requests.get(url)\n",
-    "        soup = BeautifulSoup(response.content, 'html.parser')\n",
-    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
-    "        for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
-    "            irrelevant.decompose()\n",
+    "       \n",
+    "        \n",
     "        self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
    ]
   },
@@ -178,7 +176,8 @@
    "source": [
     "# Let's try one out. Change the website and add print statements to follow along.\n",
     "\n",
-    "ed = Website(\"https://edwarddonner.com\")\n",
+    "ed = Website(\"https://jaivikhimalay.com\")\n",
+    "#ed = Website(\"https://edwarddonner.com\")\n",
     "print(ed.title)\n",
     "print(ed.text)"
    ]
@@ -308,6 +307,7 @@
     "def summarize(url):\n",
     "    website = Website(url)\n",
     "    response = openai.chat.completions.create(\n",
+    "        \n",
     "        model = \"gpt-4o-mini\",\n",
     "        messages = messages_for(website)\n",
     "    )\n",
@@ -474,6 +474,16 @@
    "id": "682eff74-55c4-4d4b-b267-703edbc293c7",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "display_summary(\"https://jaivikhimalay.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2df0c85f-3815-4c7b-bc17-3fb61aeb75f6",
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],

week1/day2 EXERCISE.ipynb

@@ -167,6 +167,178 @@
     "\n",
     "Take the code from day1 and incorporate it here, to build a website summarizer that uses Llama 3.2 running locally instead of OpenAI"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00496450-b078-469c-8072-4cb633df9928",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "37aea1a6-2d35-4c8b-9264-43da5884d069",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Constants\n",
+    "MODEL = \"llama3.2\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "383f8e2a-c98d-48bc-9c3f-ece4ef077ec9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A class to represent a Webpage\n",
+    "\n",
+    "class Website:\n",
+    "    \"\"\"\n",
+    "    A utility class to represent a Website that we have scraped\n",
+    "    \"\"\"\n",
+    "    url: str\n",
+    "    title: str\n",
+    "    text: str\n",
+    "\n",
+    "    def __init__(self, url):\n",
+    "        \"\"\"\n",
+    "        Create this Website object from the given url using the BeautifulSoup library\n",
+    "        \"\"\"\n",
+    "        self.url = url\n",
+    "        response = requests.get(url)\n",
+    "        soup = BeautifulSoup(response.content, 'html.parser')\n",
+    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
+    "        for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
+    "            irrelevant.decompose()\n",
+    "        self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36e99eba-5758-4471-8860-2f5a42771e6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ed = Website(\"https://jaivikhimalay.com\")\n",
+    "print(ed.url)\n",
+    "print(ed.title)\n",
+    "print(ed.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "793f8c35-fbde-4160-90b5-a2fd8ea5f5e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n",
+    "\n",
+    "system_prompt = \"You are an assistant that analyzes the contents of a website \\\n",
+    "and provides a short summary, ignoring text that might be navigation related. \\\n",
+    "Respond in markdown.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ecbfa0e2-39c2-4467-989b-4ab9810de72d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A function that writes a User Prompt that asks for summaries of websites:\n",
+    "\n",
+    "def user_prompt_for(website):\n",
+    "    user_prompt = f\"You are looking at a website titled {website.title}\"\n",
+    "    user_prompt += \"The contents of this website is as follows; \\\n",
+    "please provide a short summary of this website in markdown. \\\n",
+    "If it includes news or announcements, then summarize these too.\\n\\n\"\n",
+    "    user_prompt += website.text\n",
+    "    return user_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf5a1da8-1628-4bbb-a2f8-e06409fe4e45",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# See how this function creates exactly the format above\n",
+    "\n",
+    "def messages_for(website):\n",
+    "    return [\n",
+    "        {\"role\": \"system\", \"content\": system_prompt},\n",
+    "        {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
+    "    ]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc9040a8-0a62-4658-94d9-0674b9045986",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now: call the Ollama function instead of OpenAI\n",
+    "\n",
+    "def summarize(url):\n",
+    "    website = Website(url)\n",
+    "    messages = messages_for(website)\n",
+    "    response = ollama.chat(model=MODEL, messages=messages)\n",
+    "    return response['message']['content']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc2aff45-ba1d-44f8-8b5d-f34934eb1ee8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "summarize(\"https://jaivikhimalay.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ef0e940d-fed4-417b-8d95-4a0fd3b9b3d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def display_summary(url):\n",
+    "    summary = summarize(url)\n",
+    "    display(Markdown(summary))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "086296f1-c748-4747-93d2-554732392400",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display_summary(\"https://jaivikhimalay.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83e150e1-5b2c-45b7-9154-aae5b55943af",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {