Spaces:
Sleeping
Sleeping
File size: 7,720 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 |
{
"cells": [
{
"cell_type": "markdown",
"id": "603cd418-504a-4b4d-b1c3-be04febf3e79",
"metadata": {},
"source": [
"# Article Title Generator\n",
"\n",
"Summarization use-case in which the user provides an article, which the LLM will analyze to suggest an SEO-optimized title.\n",
"\n",
"**NOTES**:\n",
"\n",
"1. This version does NOT support website scrapping. You must copy and paste the required article.\n",
"2. The following models were configured:\n",
" a. OpenAI gpt-4o-mini\n",
" b. Llama llama3.2\n",
" c. Deepseek deepseek-r1:1.5b\n",
" It is possible to configure additional models by adding the new model to the MODELS dictionary and its\n",
" initialization to the CLIENTS dictionary. Then, call the model with --> ***answer =\n",
" get_answer('NEW_MODEL')***.\n",
"3. Users are encouraged to assess and rank the suggested titles using any headline analyzer tool online.\n",
" Example: https://www.isitwp.com/headline-analyzer/. "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e773daa6-d05e-49bf-ad8e-a8ed4882b77e",
"metadata": {},
"outputs": [],
"source": [
"# Confirming Llama is loaded\n",
"!ollama pull llama3.2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "279b0c00-9bb0-4c7f-9c6d-aa0b108274b9",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"import os\n",
"from dotenv import load_dotenv\n",
"from IPython.display import Markdown, display\n",
"from openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d4730d8d-3e20-4f3c-a4ff-ed2ac0a8aa27",
"metadata": {},
"outputs": [],
"source": [
"# set environment variables for OpenAi\n",
"load_dotenv(override=True)\n",
"api_key = os.getenv('OPENAI_API_KEY')\n",
"\n",
"# validate API Key\n",
"if not api_key:\n",
" raise ValueError(\"No API key was found! Please check the .env file.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1abbb826-de66-498c-94d8-33369ad01885",
"metadata": {},
"outputs": [],
"source": [
"# constants\n",
"MODELS = { 'GPT': 'gpt-4o-mini', \n",
" 'LLAMA': 'llama3.2', \n",
" 'DEEPSEEK': 'deepseek-r1:1.5b'\n",
" }\n",
"\n",
"CLIENTS = { 'GPT': OpenAI(), \n",
" 'LLAMA': OpenAI(base_url='http://localhost:11434/v1', api_key='ollama'),\n",
" 'DEEPSEEK': OpenAI(base_url='http://localhost:11434/v1', api_key='ollama') \n",
" }"
]
},
{
"cell_type": "markdown",
"id": "6f490fe4-32d5-41f3-890d-ecf4e5e01dd4",
"metadata": {},
"source": [
"### Copy & paste your article (without a title)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ddd76319-13ce-480b-baa7-cab6a5c88168",
"metadata": {},
"outputs": [],
"source": [
"# article - copy & paste your article\n",
"article = \"\"\"\n",
" REPLACE WITH YOUR ARTICLE CONTENT\n",
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1914afad-dbd8-4c1f-8e68-80b0e5d743a9",
"metadata": {},
"outputs": [],
"source": [
"# system prompt\n",
"system_prompt = \"\"\"\n",
" You are an experienced SEO-focused copywriter. The user will provide an article, and your task is to analyze its content and generate the most effective, keyword-optimized title to maximize SEO performance.Respond in Markdown format.\n",
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "176cfac7-5e6d-4d4a-a1c4-1b63b60de1f7",
"metadata": {},
"outputs": [],
"source": [
"# user prompt\n",
"user_prompt = f\"Following the article to be analyzed. Respond in Markdown format./n/n{article}\"\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c45fc7d7-08c9-4e34-b427-b928a219bb94",
"metadata": {},
"outputs": [],
"source": [
"# message list\n",
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f67b881f-1040-4cf7-82c5-e85f4c0bd252",
"metadata": {},
"outputs": [],
"source": [
"# call model and get answer\n",
"def get_answer(model):\n",
" # set required client\n",
" client = CLIENTS[model]\n",
"\n",
" # call model\n",
" response = client.chat.completions.create(\n",
" model=MODELS[model],\n",
" messages=messages\n",
" )\n",
" \n",
" # return answer\n",
" return response.choices[0].message.content\n",
" "
]
},
{
"cell_type": "markdown",
"id": "947b42ed-5b43-486d-8af3-e5b671c1fd0e",
"metadata": {},
"source": [
"### Get OpenAI Suggested Title"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb6f66e3-ab99-4f76-9358-896cb43c1fa1",
"metadata": {},
"outputs": [],
"source": [
"# get openAi answer\n",
"answer = get_answer('GPT')\n",
"\n",
"# display openAi answer\n",
"display(Markdown(f\"### {MODELS['GPT']} Answer\\n\\n{answer}\" ))"
]
},
{
"cell_type": "markdown",
"id": "70073ebf-a00a-416b-854d-642d450cd99b",
"metadata": {},
"source": [
"### Get Llama Suggested Title"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "caa190bb-de5f-45cc-b671-5d62688f7b25",
"metadata": {},
"outputs": [],
"source": [
"# get Llama answer\n",
"answer = get_answer('LLAMA')\n",
"\n",
"# display Llama answer\n",
"display(Markdown(f\"### {MODELS['LLAMA']} Answer\\n\\n{answer}\" ))"
]
},
{
"cell_type": "markdown",
"id": "811edc4f-20e2-482d-ac89-fae9d1b70bed",
"metadata": {},
"source": [
"### Get Deepseek Suggested Title"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "082628e4-ff4c-46dd-ae5f-76578eb017ad",
"metadata": {},
"outputs": [],
"source": [
"# get Deepseek answer\n",
"answer = get_answer('DEEPSEEK')\n",
"\n",
"# display Deepseek answer\n",
"display(Markdown(f\"### {MODELS['DEEPSEEK']} Answer\\n\\n{answer}\" ))"
]
},
{
"cell_type": "markdown",
"id": "7fc404a6-3a91-4c09-89de-867d3d69b4b2",
"metadata": {},
"source": [
"### Suggested future improvements\n",
"\n",
"1. Add website scrapping support to replace copy/pasting of articles.\n",
"2. Improve the system_prompt to provide specific SEO best practices to adopt during the title generation.\n",
"3. Rephrase the system_prompt to ensure the model provides a single Title (not a list of suggestions). \n",
"4. Add the logic that would allow each model to assess the recommendations from the different models and \n",
" select the best among these. "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cf7403ac-d43b-4493-98bb-6fee94950cb0",
"metadata": {},
"outputs": [],
"source": []
}
],
"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
}
|