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.
393 lines
11 KiB
393 lines
11 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "1b89f103-fc49-487e-930e-14abff8bfab1", |
|
"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" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "1a40e64b-14c6-4589-a671-6817f9cb09f0", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"import gradio as gr" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "c0990b15-313d-4cf8-bc5b-fc14d263ba27", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Load environment variables in a file called .env\n", |
|
"\n", |
|
"load_dotenv()\n", |
|
"os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY', 'your-key-if-not-using-env')" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 4, |
|
"id": "66a38e1f-db7e-4697-aa9c-a303f9828531", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"google.generativeai.configure()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 5, |
|
"id": "beb9606e-9be9-4f2e-adfe-4e41fb99566e", |
|
"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": 10, |
|
"id": "19ab23bc-59cf-48a3-8651-f7b1c52874db", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def message_gemini(prompt):\n", |
|
" messages = [\n", |
|
" {\"role\": \"system\", \"content\": system_message},\n", |
|
" {\"role\": \"user\", \"content\": prompt}\n", |
|
" ]\n", |
|
" gemini = google.generativeai.GenerativeModel(\n", |
|
" model_name='gemini-1.5-flash',\n", |
|
" system_instruction=system_message\n", |
|
")\n", |
|
" response = gemini.generate_content(prompt)\n", |
|
" return response.text\n", |
|
"\n", |
|
"\n", |
|
"# gemini = google.generativeai.GenerativeModel(\n", |
|
"# model_name='gemini-1.5-flash',\n", |
|
"# system_instruction=system_message\n", |
|
"# )\n", |
|
"# response = gemini.generate_content(user_prompt)\n", |
|
"# print(response.text)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "8fe3c66c-d25d-4627-a401-d84c7d6613e7", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"message_gemini(\"What is today's date?\")\n", |
|
"# message_gemini(\"tell me a funny machine learning joke\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "b27027ed-4bff-493c-a41e-8318003e0387", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"import google.generativeai as genai\n", |
|
"for model in genai.list_models():\n", |
|
" print(model.name)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 17, |
|
"id": "2f82d61b-a7cd-4bee-994d-2e83d0a01bfc", |
|
"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": null, |
|
"id": "5941fe3f-aab9-47ba-b29f-d99aa3b40aed", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"shout(\"hello\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "d6470847-1cce-4bf0-8364-199504a5335f", |
|
"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": "69715604-cc64-4563-967f-b5720462ac69", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", js=force_dark_mode).launch()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "dede1d8c-fb7a-456a-923b-e221eaa30bd9", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", flagging_mode=\"never\").launch(share=True)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "55ae11b9-e7af-449f-b737-48dd7dc1a5b2", |
|
"metadata": { |
|
"scrolled": true |
|
}, |
|
"outputs": [], |
|
"source": [ |
|
"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": "cba667cf-d270-426e-b940-a01083352ecb", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"view = gr.Interface(\n", |
|
" fn=message_gemini,\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": "b8bb7885-740f-41f0-95e3-dabe864cea14", |
|
"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_gemini,\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": 29, |
|
"id": "43d17b00-f4bc-45ad-a679-3112a170f5fb", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"import google.generativeai as genai\n", |
|
"\n", |
|
"def stream_gemini(prompt):\n", |
|
" gemini = genai.GenerativeModel(\n", |
|
" model_name='gemini-1.5-flash',\n", |
|
" safety_settings=None,\n", |
|
" system_instruction=system_message\n", |
|
" )\n", |
|
"\n", |
|
" response = gemini.generate_content(prompt, safety_settings=[\n", |
|
" {\"category\": \"HARM_CATEGORY_DANGEROUS_CONTENT\", \"threshold\": \"BLOCK_NONE\"},\n", |
|
" {\"category\": \"HARM_CATEGORY_SEXUALLY_EXPLICIT\", \"threshold\": \"BLOCK_NONE\"},\n", |
|
" {\"category\": \"HARM_CATEGORY_HATE_SPEECH\", \"threshold\": \"BLOCK_NONE\"},\n", |
|
" {\"category\": \"HARM_CATEGORY_HARASSMENT\", \"threshold\": \"BLOCK_NONE\"}], stream=True)\n", |
|
" \n", |
|
" result = \"\"\n", |
|
" for chunk in response:\n", |
|
" result += chunk.text\n", |
|
" yield result\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "840f3d11-e66b-4b6b-9b98-70e0f02be9e6", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"view = gr.Interface(\n", |
|
" fn=stream_gemini,\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": "ea8a0081-8d2e-4960-b479-7c1ef346f524", |
|
"metadata": {}, |
|
"source": [ |
|
"# Building a company brochure generator\n", |
|
"\n", |
|
"Now you know how - it's simple!" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 32, |
|
"id": "2d43360a-515e-4008-9eef-7a3c4e47cfba", |
|
"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": 34, |
|
"id": "08a07e55-b05d-4360-8e05-61dd39cc019b", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def stream_brochure(company_name, url, model, response_tone):\n", |
|
" prompt = f\"Please generate a {response_tone} 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", |
|
" elif model==\"Gemini\":\n", |
|
" result = stream_gemini(prompt)\n", |
|
" else:\n", |
|
" raise ValueError(\"Unknown model\")\n", |
|
" yield from result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "d9554211-c832-4558-90c8-fceab95fd23c", |
|
"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\", \"Gemini\"], label=\"Select model\"),\n", |
|
" gr.Dropdown([\"Informational\", \"Promotional\", \"Humorous\"], label=\"Select tone\")],\n", |
|
" outputs=[gr.Markdown(label=\"Brochure:\")],\n", |
|
" flagging_mode=\"never\"\n", |
|
")\n", |
|
"view.launch()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "4d4e6efd-66e8-4388-bfc3-782bde4babfb", |
|
"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 |
|
}
|
|
|