Browse Source

Add week2 with openrouter.ai and day 2 brochure practice

pull/192/head
wsun 3 months ago
parent
commit
ef0444a99d
  1. 295
      week2/community-contributions/Week2_day2_openRouter_gradio_brochure.ipynb
  2. 614
      week2/community-contributions/day2-openrouterAi.ipynb

295
week2/community-contributions/Week2_day2_openRouter_gradio_brochure.ipynb

@ -0,0 +1,295 @@
{
"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
}

614
week2/community-contributions/day2-openrouterAi.ipynb

@ -0,0 +1,614 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "8b0e11f2-9ea4-48c2-b8d2-d0a4ba967827",
"metadata": {},
"source": [
"# Gradio Day!\n",
"\n",
"Today we will build User Interfaces using the outrageously simple Gradio framework.\n",
"\n",
"Prepare for joy!\n",
"\n",
"Please note: your Gradio screens may appear in 'dark mode' or 'light mode' depending on your computer settings."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "c44c5494-950d-4d2f-8d4f-b87b57c5b330",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\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 google.generativeai\n",
"#import anthropic\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d1715421-cead-400b-99af-986388a97aff",
"metadata": {},
"outputs": [],
"source": [
"import gradio as gr # oh yeah!"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "22586021-1795-4929-8079-63f5bb4edd4c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"API key looks good so far\n"
]
}
],
"source": [
"# Connect to OpenAI, Anthropic and Google; comment out the Claude or Google lines if you're not using them\n",
"\n",
"# openai = OpenAI()\n",
"\n",
"# claude = anthropic.Anthropic()\n",
"\n",
"# google.generativeai.configure()\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_Gemini2FlashLite = 'google/gemini-2.0-flash-lite-preview-02-05:free'\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_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",
"Default_Model = MODEL_Deepseek_V3\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b16e6021-6dc4-4397-985a-6679d6c8ffd5",
"metadata": {},
"outputs": [],
"source": [
"# A generic system message - no more snarky adversarial AIs!\n",
"\n",
"system_message = \"You are a helpful assistant\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "02ef9b69-ef31-427d-86d0-b8c799e1c1b1",
"metadata": {},
"outputs": [],
"source": [
"# Let's wrap a call to GPT-4o-mini in a simple function\n",
"\n",
"def message_gpt(prompt):\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_message},\n",
" {\"role\": \"user\", \"content\": prompt}\n",
" ]\n",
" completion = openai.chat.completions.create(\n",
" model=Default_Model,\n",
" messages=messages,\n",
" )\n",
" return completion.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "aef7d314-2b13-436b-b02d-8de3b72b193f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Today is October 26, 2023.\\n'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This can reveal the \"training cut off\", or the most recent date in the training data\n",
"\n",
"message_gpt(\"What is today's date?\")"
]
},
{
"cell_type": "markdown",
"id": "f94013d1-4f27-4329-97e8-8c58db93636a",
"metadata": {},
"source": [
"## User Interface time!"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "bc664b7a-c01d-4fea-a1de-ae22cdd5141a",
"metadata": {},
"outputs": [],
"source": [
"# here's a simple function\n",
"\n",
"def shout(text):\n",
" print(f\"Shout has been called with input {text}\")\n",
" return text.upper()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "083ea451-d3a0-4d13-b599-93ed49b975e4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Shout has been called with input hello\n"
]
},
{
"data": {
"text/plain": [
"'HELLO'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"shout(\"hello\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "08f1f15a-122e-4502-b112-6ee2817dda32",
"metadata": {},
"outputs": [],
"source": [
"# The simplicty of gradio. This might appear in \"light mode\" - I'll show you how to make this in dark mode later.\n",
"\n",
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\").launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c9a359a4-685c-4c99-891c-bb4d1cb7f426",
"metadata": {},
"outputs": [],
"source": [
"# Adding share=True means that it can be accessed publically\n",
"# A more permanent hosting is available using a platform called Spaces from HuggingFace, which we will touch on next week\n",
"# NOTE: Some Anti-virus software and Corporate Firewalls might not like you using share=True. If you're at work on on a work network, I suggest skip this test.\n",
"\n",
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", flagging_mode=\"never\").launch(share=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cd87533a-ff3a-4188-8998-5bedd5ba2da3",
"metadata": {},
"outputs": [],
"source": [
"# Adding inbrowser=True opens up a new browser window automatically\n",
"\n",
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", flagging_mode=\"never\").launch(inbrowser=True)"
]
},
{
"cell_type": "markdown",
"id": "b42ec007-0314-48bf-84a4-a65943649215",
"metadata": {},
"source": [
"## Forcing dark mode\n",
"\n",
"Gradio appears in light mode or dark mode depending on the settings of the browser and computer. There is a way to force gradio to appear in dark mode, but Gradio recommends against this as it should be a user preference (particularly for accessibility reasons). But if you wish to force dark mode for your screens, below is how to do it."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e8129afa-532b-4b15-b93c-aa9cca23a546",
"metadata": {},
"outputs": [],
"source": [
"# Define this variable and then pass js=force_dark_mode when creating the Interface\n",
"\n",
"force_dark_mode = \"\"\"\n",
"function refresh() {\n",
" const url = new URL(window.location);\n",
" if (url.searchParams.get('__theme') !== 'dark') {\n",
" url.searchParams.set('__theme', 'dark');\n",
" window.location.href = url.href;\n",
" }\n",
"}\n",
"\"\"\"\n",
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", flagging_mode=\"never\", js=force_dark_mode).launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3cc67b26-dd5f-406d-88f6-2306ee2950c0",
"metadata": {},
"outputs": [],
"source": [
"# Inputs and Outputs\n",
"\n",
"view = gr.Interface(\n",
" fn=shout,\n",
" inputs=[gr.Textbox(label=\"Your message:\", lines=6)],\n",
" outputs=[gr.Textbox(label=\"Response:\", lines=8)],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f235288e-63a2-4341-935b-1441f9be969b",
"metadata": {},
"outputs": [],
"source": [
"# And now - changing the function from \"shout\" to \"message_gpt\"\n",
"\n",
"view = gr.Interface(\n",
" fn=message_gpt,\n",
" inputs=[gr.Textbox(label=\"Your message:\", lines=6)],\n",
" outputs=[gr.Textbox(label=\"Response:\", lines=8)],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "af9a3262-e626-4e4b-80b0-aca152405e63",
"metadata": {},
"outputs": [],
"source": [
"# Let's use Markdown\n",
"# Are you wondering why it makes any difference to set system_message when it's not referred to in the code below it?\n",
"# I'm taking advantage of system_message being a global variable, used back in the message_gpt function (go take a look)\n",
"# Not a great software engineering practice, but quite sommon during Jupyter Lab R&D!\n",
"\n",
"system_message = \"You are a helpful assistant that responds in markdown\"\n",
"\n",
"view = gr.Interface(\n",
" fn=message_gpt,\n",
" inputs=[gr.Textbox(label=\"Your message:\")],\n",
" outputs=[gr.Markdown(label=\"Response:\")],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "88c04ebf-0671-4fea-95c9-bc1565d4bb4f",
"metadata": {},
"outputs": [],
"source": [
"# Let's create a call that streams back results\n",
"# If you'd like a refresher on Generators (the \"yield\" keyword),\n",
"# Please take a look at the Intermediate Python notebook in week1 folder.\n",
"\n",
"def stream_gpt(prompt):\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_message},\n",
" {\"role\": \"user\", \"content\": prompt}\n",
" ]\n",
" stream = openai.chat.completions.create(\n",
" model=Default_Model,\n",
" messages=messages,\n",
" stream=True\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": "0bb1f789-ff11-4cba-ac67-11b815e29d09",
"metadata": {},
"outputs": [],
"source": [
"view = gr.Interface(\n",
" fn=stream_gpt,\n",
" inputs=[gr.Textbox(label=\"Your message:\")],\n",
" outputs=[gr.Markdown(label=\"Response:\")],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bbc8e930-ba2a-4194-8f7c-044659150626",
"metadata": {},
"outputs": [],
"source": [
"# def stream_claude(prompt):\n",
"# result = claude.messages.stream(\n",
"# model=\"claude-3-haiku-20240307\",\n",
"# max_tokens=1000,\n",
"# temperature=0.7,\n",
"# system=system_message,\n",
"# messages=[\n",
"# {\"role\": \"user\", \"content\": prompt},\n",
"# ],\n",
"# )\n",
"# response = \"\"\n",
"# with result as stream:\n",
"# for text in stream.text_stream:\n",
"# response += text or \"\"\n",
"# yield response"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a0066ffd-196e-4eaf-ad1e-d492958b62af",
"metadata": {},
"outputs": [],
"source": [
"Default_Model=MODEL_Claude_Haiku\n",
"view = gr.Interface(\n",
" fn=stream_gpt,\n",
" inputs=[gr.Textbox(label=\"Your message:\")],\n",
" outputs=[gr.Markdown(label=\"Response:\")],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "markdown",
"id": "bc5a70b9-2afe-4a7c-9bed-2429229e021b",
"metadata": {},
"source": [
"## Minor improvement\n",
"\n",
"I've made a small improvement to this code.\n",
"\n",
"Previously, it had these lines:\n",
"\n",
"```\n",
"for chunk in result:\n",
" yield chunk\n",
"```\n",
"\n",
"There's actually a more elegant way to achieve this (which Python people might call more 'Pythonic'):\n",
"\n",
"`yield from result`\n",
"\n",
"I cover this in more detail in the Intermediate Python notebook in the week1 folder - take a look if you'd like more."
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "0087623a-4e31-470b-b2e6-d8d16fc7bcf5",
"metadata": {},
"outputs": [],
"source": [
"def stream_model(prompt, model):\n",
" if model==\"GPT\":\n",
" Default_Model=MODEL_Gemini2FlashThink\n",
" result = stream_gpt(prompt)\n",
" elif model==\"Claude\":\n",
" Default_Model=MODEL_Claude_Haiku\n",
" result = stream_gpt(prompt)\n",
" else:\n",
" raise ValueError(\"Unknown model\")\n",
" yield from result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8d8ce810-997c-4b6a-bc4f-1fc847ac8855",
"metadata": {},
"outputs": [],
"source": [
"view = gr.Interface(\n",
" fn=stream_model,\n",
" inputs=[gr.Textbox(label=\"Your message:\"), gr.Dropdown([\"GPT\", \"Claude\"], label=\"Select model\", value=\"GPT\")],\n",
" outputs=[gr.Markdown(label=\"Response:\")],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "markdown",
"id": "d933865b-654c-4b92-aa45-cf389f1eda3d",
"metadata": {},
"source": [
"# Building a company brochure generator\n",
"\n",
"Now you know how - it's simple!"
]
},
{
"cell_type": "markdown",
"id": "92d7c49b-2e0e-45b3-92ce-93ca9f962ef4",
"metadata": {},
"source": [
"<table style=\"margin: 0; text-align: left;\">\n",
" <tr>\n",
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
" <img src=\"../../important.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
" </td>\n",
" <td>\n",
" <h2 style=\"color:#900;\">Before you read the next few cells</h2>\n",
" <span style=\"color:#900;\">\n",
" Try to do this yourself - go back to the company brochure in week1, day5 and add a Gradio UI to the end. Then come and look at the solution.\n",
" </span>\n",
" </td>\n",
" </tr>\n",
"</table>"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1626eb2e-eee8-4183-bda5-1591b58ae3cf",
"metadata": {},
"outputs": [],
"source": [
"# A class to represent a Webpage\n",
"\n",
"class Website:\n",
" url: str\n",
" title: str\n",
" text: str\n",
"\n",
" def __init__(self, url):\n",
" self.url = url\n",
" response = requests.get(url)\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",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
"\n",
" def get_contents(self):\n",
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c701ec17-ecd5-4000-9f68-34634c8ed49d",
"metadata": {},
"outputs": [],
"source": [
"# With massive thanks to Bill G. who noticed that a prior version of this had a bug! Now fixed.\n",
"\n",
"system_message = \"You are an assistant that analyzes the contents of a company website landing page \\\n",
"and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5def90e0-4343-4f58-9d4a-0e36e445efa4",
"metadata": {},
"outputs": [],
"source": [
"def stream_brochure(company_name, url, model):\n",
" prompt = f\"Please generate a company brochure for {company_name}. Here is their landing page:\\n\"\n",
" prompt += Website(url).get_contents()\n",
" if model==\"GPT\":\n",
" result = stream_gpt(prompt)\n",
" elif model==\"Claude\":\n",
" result = stream_claude(prompt)\n",
" else:\n",
" raise ValueError(\"Unknown model\")\n",
" yield from result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "66399365-5d67-4984-9d47-93ed26c0bd3d",
"metadata": {},
"outputs": [],
"source": [
"view = gr.Interface(\n",
" fn=stream_brochure,\n",
" inputs=[\n",
" gr.Textbox(label=\"Company name:\"),\n",
" gr.Textbox(label=\"Landing page URL including http:// or https://\"),\n",
" gr.Dropdown([\"GPT\", \"Claude\"], label=\"Select model\")],\n",
" outputs=[gr.Markdown(label=\"Brochure:\")],\n",
" flagging_mode=\"never\"\n",
")\n",
"view.launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ede97ca3-a0f8-4f6e-be17-d1de7fef9cc0",
"metadata": {},
"outputs": [],
"source": []
}
],
"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
}
Loading…
Cancel
Save