Add ollama model for open-source functionality to website summarization.

week1/day2 EXERCISE_ollama_llama3.ipynb

@@ -220,7 +220,12 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "cf9eb44e-fe5b-47aa-b719-0bb63669ab3d",
-   "metadata": {},
+   "metadata": {
+    "collapsed": true,
+    "jupyter": {
+     "outputs_hidden": true
+    }
+   },
    "outputs": [],
    "source": [
     "!ollama pull deepseek-r1:1.5b"
@@ -253,10 +258,230 @@
     "Take the code from day1 and incorporate it here, to build a website summarizer that uses Llama 3.2 running locally instead of OpenAI; use either of the above approaches."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ffaa3470-884c-467e-b4ce-c1b8d39294da",
+   "metadata": {},
+   "source": [
+    "This is the code from day 1 notebook. Here we create the class to extract the text from the website, using BeautifulSoup library, and the we execute it to see the the results"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6de38216-6d1c-48c4-877b-86d403f4e0f8",
+   "id": "8d8c9f01-ca12-4018-b7fa-698c9fa1aa93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A class to represent a Webpage\n",
+    "# If you're not familiar with Classes, check out the \"Intermediate Python\" notebook\n",
+    "\n",
+    "# Some websites need you to use proper headers when fetching them:\n",
+    "headers = {\n",
+    " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
+    "}\n",
+    "\n",
+    "class Website:\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, headers=headers)\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": "6fd198df-bac5-42c5-83a0-06c5f71fb76a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's try one out. Change the website and add print statements to follow along.\n",
+    "\n",
+    "ed = Website(\"https://edwarddonner.com\")\n",
+    "print(ed.title)\n",
+    "print(ed.text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "995b637d-a5db-4ad9-ac78-5980fd7ef112",
+   "metadata": {},
+   "source": [
+    "#### Define the system prompt, to instruct the model how we want to respond to our query. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee810d49-e88a-4137-a4be-98812e0d0748",
+   "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": "482b5d4c-69ed-4332-abb5-8b0986dcf368",
+   "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 += \"\\nThe 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": "d966cb09-3ca2-49f7-8462-f6ef26c01159",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(user_prompt_for(ed))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f9be84f-4cd7-4ce7-8f33-e60d16f02852",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# For test purpose\n",
+    "\n",
+    "messages = [\n",
+    "    {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n",
+    "    {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f5cb0e9f-eb56-4633-ba4c-76817be98856",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# To give you a preview -- calling ollama with system and user messages:\n",
+    "\n",
+    "import ollama\n",
+    "\n",
+    "response = ollama.chat(model=MODEL, messages=messages)\n",
+    "print(response['message']['content'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c554903f-eb04-4a16-87fc-f1d9ff58f6d9",
+   "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": "6b64b814-123f-436d-9366-4c762ac4b89a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Try this out, and then try for a few more websites\n",
+    "\n",
+    "messages_for(ed)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ef4be2-ef3a-4b5d-8d18-f2eafa9d6a93",
+   "metadata": {},
+   "source": [
+    "### So, here let's run the summarize by using ollama and see how appears."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c46edc5-c85d-4ad0-89fd-39c4fdc44a5d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now: call the ollama API. \n",
+    "\n",
+    "def summarize(url):\n",
+    "    website = Website(url)\n",
+    "    response = ollama.chat(\n",
+    "        model = MODEL,\n",
+    "        messages = messages_for(website)\n",
+    "    )\n",
+    "    return response['message']['content']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "466c2f78-91ca-4ed2-b60b-40661d0b6f68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "summarize(\"https://edwarddonner.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7ab7c9a1-70fd-421c-be06-c36eb6c9aedf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A function to display this nicely in the Jupyter output, using markdown\n",
+    "\n",
+    "def display_summary(url):\n",
+    "    summary = summarize(url)\n",
+    "    display(Markdown(summary))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1cedc9d9-6a76-4225-82c1-82240da16260",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display_summary(\"https://edwarddonner.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82c48586-33c8-4797-a24f-41602c1297b3",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -264,7 +489,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "llms",
    "language": "python",
    "name": "python3"
   },