From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
193 lines
7.4 KiB
193 lines
7.4 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "a9e05d2a", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# ----- (My project)\n", |
|
"# Date: 09.01.25\n", |
|
"# Plan: Make a Gradio UI, that lets you pick a job on seek.com, then scape key words and come up with a \n", |
|
"# plan on how to land jobs of the type selected." |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "312c3746", |
|
"metadata": {}, |
|
"source": [ |
|
"# My project" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "394dbcfc", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"#pip install markdown" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "15f1024d", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"\n", |
|
"import os\n", |
|
"import requests\n", |
|
"import json\n", |
|
"from typing import List\n", |
|
"from dotenv import load_dotenv\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display, update_display\n", |
|
"import gradio as gr\n", |
|
"import markdown\n", |
|
"\n", |
|
"# ---- 1\n", |
|
"# Initialize and constants & set up Gemini Flash LLM\n", |
|
"load_dotenv()\n", |
|
"api_key = os.getenv('GOOGLE_API_KEY')\n", |
|
"import os\n", |
|
"import google.generativeai as genai\n", |
|
"genai.configure(api_key= api_key)\n", |
|
"# Create the model\n", |
|
"generation_config = {\n", |
|
" \"temperature\": 1,\n", |
|
" \"top_p\": 0.95,\n", |
|
" \"top_k\": 40,\n", |
|
" \"max_output_tokens\": 8192,\n", |
|
" \"response_mime_type\": \"text/plain\",}\n", |
|
"model = genai.GenerativeModel(model_name=\"gemini-1.5-flash\",\n", |
|
" generation_config=generation_config,)\n", |
|
"chat_session = model.start_chat(history=[ ])\n", |
|
"\n", |
|
"\n", |
|
"# ---- 2\n", |
|
"# A class to represent a Webpage\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", |
|
" A utility class to represent a Website that we have scraped, now with links\n", |
|
" \"\"\"\n", |
|
"\n", |
|
" def __init__(self, url):\n", |
|
" self.url = url\n", |
|
" response = requests.get(url, headers=headers)\n", |
|
" self.body = response.content\n", |
|
" soup = BeautifulSoup(self.body, 'html.parser')\n", |
|
" self.title = soup.title.string if soup.title else \"No title found\"\n", |
|
" if soup.body:\n", |
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", |
|
" irrelevant.decompose()\n", |
|
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", |
|
" else:\n", |
|
" self.text = \"\"\n", |
|
" links = [link.get('href') for link in soup.find_all('a')]\n", |
|
" self.links = [link for link in links if link]\n", |
|
"\n", |
|
" def get_contents(self):\n", |
|
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"\n", |
|
"\n", |
|
"\n", |
|
"# ---- 3\n", |
|
"# Data + set up\n", |
|
"def get_all_details(url):\n", |
|
" result = \"Landing page:\\n\"\n", |
|
" result += Website(url).get_contents()\n", |
|
" return result\n", |
|
"\n", |
|
"system_prompt = \"You are an experience recrutiment and talent management assistant, who will be provided a list of roles on offer.\\\n", |
|
"You will display those roles along with a high level summary of the key steps you suggest to land those roles. \\\n", |
|
"Output is to be in markdown (i.e. a professional format, with bold headders, proper spacing between different sections, etc.)\\\n", |
|
"Include suggested next steps on how to successfully apply for and land each of these jobs.\"\n", |
|
"\n", |
|
"def get_brochure_user_prompt(url):\n", |
|
" user_prompt = f\"Here are the contents of your recruitment search. Please list out individual roles and your best advise on landing those roles.\"\n", |
|
" user_prompt += f\"Please provide output in a professional style with bold text for headings, content nicely layed out under headings, different content split out into sections, etc.)\\n\"\n", |
|
" user_prompt += get_all_details(url)\n", |
|
" #user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n", |
|
" user_prompt = user_prompt[:7_500] # Truncate if more than 5,000 characters\n", |
|
" return user_prompt\n", |
|
"\n", |
|
"def create_brochure(url):\n", |
|
" response = chat_session.send_message(system_prompt + get_brochure_user_prompt(url))\n", |
|
" result = response.text\n", |
|
" html_output = markdown.markdown(result)\n", |
|
" return html_output\n", |
|
"\n", |
|
"# ---- 4 \n", |
|
"# Gradio UI\n", |
|
"with gr.Blocks(css=\"\"\"\n", |
|
" #header-container { text-align: left; position: fixed; top: 10px; left: 0; padding: 10px; background-color: #f0f0f0; }\n", |
|
" #input-container { text-align: left; position: fixed; top: 100px; left: 0; right: 0; background: white; z-index: 100; padding: 8px; line-height: 0.5;}\n", |
|
" #output-container { margin-top: 160px; height: calc(100vh - 280px); overflow-y: auto; }\n", |
|
" #output-html { white-space: pre-wrap; font-family: monospace; border: 1px solid #ccc; padding: 5px; line-height: 1.2;}\n", |
|
" .button-container { margin-top: 10px; } /* Space above the button */\n", |
|
" .output-label { margin-top: 10px; font-weight: bold; } /* Style for output label */\n", |
|
"\"\"\") as iface:\n", |
|
" with gr.Column(elem_id=\"main-container\"):\n", |
|
" # Add header and description\n", |
|
" with gr.Row(elem_id=\"header-container\"):\n", |
|
" gr.Markdown(\"# Job seeker guide\")\n", |
|
" gr.Markdown(\"1.0 Works best with recruitment site https://www.seek.com.au/ (but can try others).\")\n", |
|
" gr.Markdown(\"2.0 Search for jobs of your choice, copy URL from that search & paste in input field below to get helpful advice on how to land those roles.\")\n", |
|
"\n", |
|
"\n", |
|
" \n", |
|
" with gr.Row(elem_id=\"input-container\"):\n", |
|
" input_text = gr.Textbox(label=\"Input\", elem_id=\"input-box\")\n", |
|
" \n", |
|
" with gr.Column(elem_id=\"output-container\"):\n", |
|
" output_label = gr.Markdown(\"<div class='output-label'>Output:</div>\")\n", |
|
" output_text = gr.HTML(elem_id=\"output-html\")\n", |
|
" \n", |
|
" # Move the button below the output box\n", |
|
" submit_btn = gr.Button(\"Generate\", elem_id=\"generate-button\", elem_classes=\"button-container\")\n", |
|
" \n", |
|
" submit_btn.click(fn=create_brochure, inputs=input_text, outputs=output_text)\n", |
|
"\n", |
|
"iface.launch(share=True)\n", |
|
"\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "21c4b557", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [] |
|
} |
|
], |
|
"metadata": { |
|
"kernelspec": { |
|
"display_name": ".venv", |
|
"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": "3.12.8" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|