File size: 8,097 Bytes
5fdb69e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9ae10427-6ca2-4ac0-b6a0-e9206dd3cb52",
   "metadata": {},
   "source": [
    "### Using OpenAI gpt-4o-mini model to generate social media posts for events"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "477fe060-a11f-424f-bac4-34c5121cf437",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import requests\n",
    "from dotenv import load_dotenv\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display\n",
    "from openai import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "61f012e5-cdba-48cb-ae74-df9659c23d90",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "API key found and looks good so far!\n"
     ]
    }
   ],
   "source": [
    "# Load environment variables in a file called .env\n",
    "\n",
    "load_dotenv()\n",
    "api_key = os.getenv('OPENAI_API_KEY')\n",
    "\n",
    "# Check the key\n",
    "\n",
    "if not api_key:\n",
    "    print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
    "elif not api_key.startswith(\"sk-proj-\"):\n",
    "    print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
    "elif api_key.strip() != api_key:\n",
    "    print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
    "else:\n",
    "    print(\"API key found and looks good so far!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "19c79615-57aa-40e0-a83b-891f43df4f65",
   "metadata": {},
   "outputs": [],
   "source": [
    "openai = OpenAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "68ad05f8-dfcc-47b1-ba16-b35bedeff48b",
   "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": 14,
   "id": "acff6c95-77a5-40f0-bf9f-7d47cec987fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# See how this function creates exactly the format above\n",
    "\n",
    "def messages_for(website):\n",
    "    return [\n",
    "        {\"role\": \"system\", \"content\": \"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.\"},\n",
    "        {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
    "    ]\n",
    "\n",
    "# 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\n",
    "    \n",
    "# Generate a summary of content fetched by scraping the website\n",
    "\n",
    "def summarize(url):\n",
    "    website = Website(url)\n",
    "    response = openai.chat.completions.create(\n",
    "        model = \"gpt-4o-mini\",\n",
    "        messages = messages_for(website)\n",
    "    )\n",
    "    return response.choices[0].message.content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b43f8cda-8a61-4773-83b2-bb8fe55a0cb2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "**Twitter Post:**  \n",
       "πŸš€ Join us online for #StartupMastery on Jan 7, 6-9 PM GMT! Explore Lean Startup, Agile, & Design Thinking methodologies. Gain practical skills, access resources, and earn a certificate! Tickets from €74.98. Don't miss out! 🎟️🌟\n",
       "\n",
       "**Instagram Post:**  \n",
       "🌟 Ready to boost your startup skills? Join us for **Startup Mastery**! πŸ’‘ On January 7 from 6 PM to 9 PM GMT, dive into Lean Startup, Agile, and Design Thinking with top-notch experts. Access recorded sessions, worksheets, and get certified! 🎟️ Tickets from €74.98. See you online! πŸš€βœ¨ #StartupMastery #LeanStartup #Agile #DesignThinking\n",
       "\n",
       "**Facebook Post:**  \n",
       "πŸ—“οΈ Exciting opportunity for entrepreneurs and startup enthusiasts! Attend our **Startup Mastery** online workshop on January 7, from 6 PM to 9 PM GMT. Learn about Lean Startup, Agile, and Design Thinking methodologies to enhance your startup journey. Enjoy a transformative experience with insights on MVP development, rapid prototyping, and feedback loops. Plus, you'll get access to recorded sessions and can earn a certificate! Limited tickets available from €74.98. Organizers: Lean Agile Zone. Don’t miss out! πŸš€ #StartupMastery #Entrepreneurship"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Step 1: Create your prompts\n",
    "WEBSITE_LINK = \"https://www.eventbrite.ie/e/startup-mastery-leveraging-lean-startup-agile-and-design-thinking-tickets-920474252267?aff=ebdssbcategorybrowse&keep_tld=1\"\n",
    "\n",
    "system_prompt = \"You are an assistant that analyzes the contents of an event \\\n",
    "and provides short summaries for a Twitter post, an instagram post and a facebook post.\\\n",
    "Ensure the summaries abide by the platform rules for each of the platforms.\"\n",
    "\n",
    "website_summary = summarize(WEBSITE_LINK)\n",
    "user_prompt = f\"The events details are as follows: {website_summary}. Please summarize the above. Capture details like time and location, please capture them as well.\"\n",
    "\n",
    "# Step 2: Make the messages list\n",
    "\n",
    "messages = [\n",
    "    {\"role\": \"system\", \"content\": system_prompt},\n",
    "    {\"role\": \"user\", \"content\": user_prompt},\n",
    "]\n",
    "\n",
    "# Step 3: Call OpenAI\n",
    "\n",
    "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
    "\n",
    "# Step 4: print the result\n",
    "\n",
    "display(Markdown(response.choices[0].message.content))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}