296 lines
11 KiB
Plaintext
296 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "a98030af-fcd1-4d63-a36e-38ba053498fa",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Week 2 Practice Gradio by Creating Brochure\n",
|
|
"\n",
|
|
"- **Author**: [stoneskin](https://www.github.com/stoneskin)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "1c104f45",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Implementation\n",
|
|
"\n",
|
|
"- Use OpenRouter.ai for all different types of LLM models, include many free models from Google,Meta and Deepseek\n",
|
|
"\n",
|
|
"Full code for the Week2 Gradio practice is below:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 19,
|
|
"id": "b8d3e1a1-ba54-4907-97c5-30f89a24775b",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"API key looks good so far\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import os\n",
|
|
"import json\n",
|
|
"import requests\n",
|
|
"from bs4 import BeautifulSoup\n",
|
|
"from typing import List\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"from openai import OpenAI\n",
|
|
"import gradio as gr \n",
|
|
"\n",
|
|
"load_dotenv(override=True)\n",
|
|
"\n",
|
|
"api_key = os.getenv('Open_Router_Key')\n",
|
|
"if api_key and api_key.startswith('sk-or-v1') and len(api_key)>10:\n",
|
|
" print(\"API key looks good so far\")\n",
|
|
"else:\n",
|
|
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n",
|
|
" \n",
|
|
" \n",
|
|
"openai = OpenAI(\n",
|
|
" api_key=api_key,\n",
|
|
" base_url=\"https://openrouter.ai/api/v1\"\n",
|
|
")\n",
|
|
"\n",
|
|
"MODEL_Gemini2FlashThink = 'google/gemini-2.0-flash-thinking-exp:free'\n",
|
|
"MODEL_Gemini2Pro ='google/gemini-2.0-pro-exp-02-05:free'\n",
|
|
"MODEL_Gemini2FlashLite = 'google/gemini-2.0-flash-lite-preview-02-05:free'\n",
|
|
"MODEL_Meta_Llama33 ='meta-llama/llama-3.3-70b-instruct:free'\n",
|
|
"MODEL_Deepseek_V3='deepseek/deepseek-chat:free'\n",
|
|
"MODEL_Deepseek_R1='deepseek/deepseek-r1-distill-llama-70b:free'\n",
|
|
"MODEL_Qwen_vlplus='qwen/qwen-vl-plus:free'\n",
|
|
"MODEL_OpenAi_o3mini = 'openai/o3-mini'\n",
|
|
"MODEL_OpenAi_4o = 'openai/gpt-4o-2024-11-20'\n",
|
|
"MODEL_Claude_Haiku = 'anthropic/claude-3.5-haiku-20241022'\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
" \n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "24866034",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"MODEL=MODEL_Gemini2Pro # choice the model you want to use\n",
|
|
"\n",
|
|
"####################\n",
|
|
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
|
"and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
|
"Include details of company culture, customers and careers/jobs if you have the information.\"\n",
|
|
"\n",
|
|
"##############################\n",
|
|
"link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n",
|
|
"You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n",
|
|
"such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n",
|
|
"link_system_prompt += \"You should respond in JSON as in this example:\"\n",
|
|
"link_system_prompt += \"\"\"\n",
|
|
"{\n",
|
|
" \"links\": [\n",
|
|
" {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n",
|
|
" {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"\"\"\"\n",
|
|
"\n",
|
|
"##############################\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",
|
|
"##############################\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",
|
|
"def get_links_user_prompt(website):\n",
|
|
" user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n",
|
|
" user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n",
|
|
"Do not include Terms of Service, Privacy, email links.\\n\"\n",
|
|
" user_prompt += \"Links (some might be relative links):\\n\"\n",
|
|
" user_prompt += \"\\n\".join(website.links)\n",
|
|
" return user_prompt\n",
|
|
"\n",
|
|
"##############################\n",
|
|
"def get_links(url):\n",
|
|
" website = Website(url)\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": link_system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n",
|
|
" ],\n",
|
|
" response_format={\"type\": \"json_object\"}\n",
|
|
" )\n",
|
|
" result = response.choices[0].message.content\n",
|
|
" print(\"get_links:\", result)\n",
|
|
" return json.loads(result)\n",
|
|
"\n",
|
|
"##############################\n",
|
|
"def get_brochure_user_prompt(company_name, url):\n",
|
|
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n",
|
|
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n",
|
|
" user_prompt += get_all_details(url)\n",
|
|
" user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n",
|
|
" return user_prompt\n",
|
|
"\n",
|
|
"##############################\n",
|
|
"def get_all_details(url):\n",
|
|
" print(\"get_all_details:\", url) \n",
|
|
" result = \"Landing page:\\n\"\n",
|
|
" result += Website(url).get_contents()\n",
|
|
" links = get_links(url)\n",
|
|
" print(\"Found links:\", links)\n",
|
|
" for link in links[\"links\"]:\n",
|
|
" result += f\"\\n\\n{link['type']}\\n\"\n",
|
|
" result += Website(link[\"url\"]).get_contents()\n",
|
|
" return result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "82abe132",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"########### modified stream brochure function for gradio ###################\n",
|
|
"def stream_brochure(company_name, url):\n",
|
|
" stream = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
|
|
" ],\n",
|
|
" stream=True\n",
|
|
" )\n",
|
|
" \n",
|
|
"\n",
|
|
" result = \"\"\n",
|
|
" for chunk in stream:\n",
|
|
" result += chunk.choices[0].delta.content or \"\"\n",
|
|
" yield result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "902f203b",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"* Running on local URL: http://127.0.0.1:7872\n",
|
|
"\n",
|
|
"To create a public link, set `share=True` in `launch()`.\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><iframe src=\"http://127.0.0.1:7872/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
|
|
],
|
|
"text/plain": [
|
|
"<IPython.core.display.HTML object>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": []
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"get_all_details: https://mlccc.herokuapp.com/\n",
|
|
"get_links: {\n",
|
|
" \"links\": [\n",
|
|
" {\"type\": \"about page\", \"url\": \"https://mlccc.herokuapp.com/about.html\"},\n",
|
|
" {\"type\": \"programs\", \"url\": \"https://mlccc.herokuapp.com/program.html\"},\n",
|
|
" {\"type\": \"camps\", \"url\": \"https://mlccc.herokuapp.com/camps.html\"},\n",
|
|
" {\"type\": \"community\", \"url\": \"https://mlccc.herokuapp.com/community.html\"},\n",
|
|
" {\"type\": \"support\", \"url\": \"https://mlccc.herokuapp.com/support.html\"},\n",
|
|
" {\"type\": \"press\", \"url\": \"https://mlccc.herokuapp.com/press.html\"},\n",
|
|
" {\"type\": \"newsletter\", \"url\": \"https://mlccc.herokuapp.com/newsletter.html\"},\n",
|
|
" {\"type\": \"testimonials\", \"url\": \"https://mlccc.herokuapp.com/testimonial.html\"}\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://mlccc.herokuapp.com/about.html'}, {'type': 'programs', 'url': 'https://mlccc.herokuapp.com/program.html'}, {'type': 'camps', 'url': 'https://mlccc.herokuapp.com/camps.html'}, {'type': 'community', 'url': 'https://mlccc.herokuapp.com/community.html'}, {'type': 'support', 'url': 'https://mlccc.herokuapp.com/support.html'}, {'type': 'press', 'url': 'https://mlccc.herokuapp.com/press.html'}, {'type': 'newsletter', 'url': 'https://mlccc.herokuapp.com/newsletter.html'}, {'type': 'testimonials', 'url': 'https://mlccc.herokuapp.com/testimonial.html'}]}\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"view = gr.Interface(\n",
|
|
" fn=stream_brochure,\n",
|
|
" inputs=[gr.Textbox(label=\"company Name\"), gr.Textbox(label=\"URL\")],\n",
|
|
" outputs=[gr.Markdown(label=\"Response:\")],\n",
|
|
" flagging_mode=\"never\"\n",
|
|
")\n",
|
|
"view.launch()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "llms",
|
|
"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
|
|
}
|