{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "771cb720-1a7c-4c63-aeba-503ee926fce9",
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"import gradio as gr\n",
"import requests\n",
"import json\n",
"from typing import List\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display, update_display"
]
},
{
"cell_type": "markdown",
"id": "f67efb4a-efc3-483e-84aa-60a31b888305",
"metadata": {},
"source": [
"The next 2 code blocks from [Ollama website](https://ollama.com/blog/openai-compatibility)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1d8b2464-352f-4df9-8ea9-796d1f886ddd",
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI(\n",
" base_url = 'http://localhost:11434/v1',\n",
" api_key='ollama', # required, but unused\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d629773a-c8cd-4ea9-a4c7-17e3d52f3415",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The 2020 World Series was played between the Los Angeles Dodgers and the Tampa Bay Rays at Globe Life Field, as well as Rogers Centre due to COVID-19 restrictions in Texas\n"
]
}
],
"source": [
"response = client.chat.completions.create(\n",
" model=\"llama3.2\",\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
" {\"role\": \"user\", \"content\": \"Who won the world series in 2020?\"},\n",
" {\"role\": \"assistant\", \"content\": \"The LA Dodgers won in 2020.\"},\n",
" {\"role\": \"user\", \"content\": \"Where was it played?\"}\n",
" ]\n",
")\n",
"\n",
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "c7d1eea8-cf7a-4f26-891f-f649e3ab6f03",
"metadata": {},
"outputs": [],
"source": [
"def get_chat_response(client, model, user_message, system_message=\"You are a helpful assistant.\"):\n",
" response = client.chat.completions.create(\n",
" model=model,\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": system_message},\n",
" {\"role\": \"user\", \"content\": user_message}\n",
" ]\n",
" )\n",
"\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "744ae925-fd10-48f7-ba5f-28b9c2467582",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"I'm not aware of the current date, as I'm a text-based AI model and do not have real-time access to the current date or time. My training data only goes up until December 2023, but I don't know what day of the week it is or what month it currently is.\n",
"\n",
"If you need to know the current date or time, I recommend checking your device's clock or searching online for \"current date\" or \"current time.\"\n"
]
}
],
"source": [
"print(get_chat_response(client, \"llama3.2\", \"What is today's date?\"))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "70e1608f-976c-4257-9a66-bb4cc19dec93",
"metadata": {},
"outputs": [],
"source": [
"#print(get_chat_response(client, \"gemma3\", \"What is your cutoff date?\"))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "9f9ca64a-c43d-4f7d-8fea-87a8d0a38835",
"metadata": {},
"outputs": [],
"source": [
"#print(get_chat_response(client, \"gemma3\", \"Are you able to generate images?\"))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4b7f8415-783b-4ebd-abec-852443abd87c",
"metadata": {
"editable": true,
"slideshow": {
"slide_type": ""
},
"tags": []
},
"outputs": [],
"source": [
"#\n",
"# from Ed Donner's github repo for LLM Engineering course on Udemy: \n",
"# https://github.com/ed-donner/llm_engineering/blob/main/week1/day5.ipynb\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",
"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"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "badd4eac-8b1c-4068-ba46-01ef60948c59",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of links: 194\n"
]
}
],
"source": [
"eventarc_website = Website(\"https://cloud.google.com/eventarc/docs\")\n",
"eventarc_links = eventarc_website.links\n",
"print('Number of links: {}'.format(len(eventarc_links)))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "6b0b2f4c-027f-48aa-875a-24939a5120c1",
"metadata": {},
"outputs": [],
"source": [
"system_message = \"You are an helpful assistant and an expert in determining if links are related to \"\n",
"system_message += \"Google Cloud eventarcs. Decide which links are relevant to the Google Cloud Professional \"\n",
"system_message += \"Developer certification and return only those links. respond with the full https URL in JSON format. \"\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f9f9b6d5-04cd-465f-a16a-6b8757ab7ec9",
"metadata": {},
"outputs": [],
"source": [
"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"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "6ceccbf7-156e-40bd-ac85-a84125c850bb",
"metadata": {},
"outputs": [],
"source": [
"def get_links(client, url, model, user_prompt, system_prompt):\n",
" website = Website(url)\n",
" response = client.chat.completions.create(\n",
" model=model,\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt}\n",
" ],\n",
" response_format={\"type\": \"json_object\"}\n",
" )\n",
" result = response.choices[0].message.content\n",
" return json.loads(result)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "99fd93c8-6443-4b98-9e1f-5f1b24e92940",
"metadata": {},
"outputs": [],
"source": [
"user_prompt = get_links_user_prompt(eventarc_website)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "a733e5cc-0e22-47e0-84eb-0d6a4bbbf4f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'links': ['https://cloud.google.com/eventarc/docs', 'https://cloud.google.com/eventarcStandard/docs/overview', 'https://cloud.google.com/eventarcAdvanced/docs/overview', 'https://cloud.google.com/eventarcStandard/docs/apis', 'https://cloud.google.com/eventarcStandard/docs/samples', 'https://cloud.google.com/eventarcaAdvanced/docs/resources', 'https://www.apache.org/licenses/LICENSE-2.0', 'https://github.com/googlecloudPlatform']}\n"
]
}
],
"source": [
"llama32_relevant_links = get_links(client, eventarc_website.url, \"llama3.2\", user_prompt, system_message)\n",
"print(llama32_relevant_links)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "423642fe-fb0e-4c8a-96bc-11e6416048dd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of relevant links found by llama3.2: 8\n"
]
}
],
"source": [
"print(\"Number of relevant links found by llama3.2: {}\".format(len(llama32_relevant_links['links'])))"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "16511679-7b47-451e-b469-4ca9b23d3576",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{}\n"
]
}
],
"source": [
"gemma3_relevant_links = get_links(client, eventarc_website.url, \"gemma3\", user_prompt, system_message)\n",
"print(gemma3_relevant_links)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "66db5fe2-6a51-48d0-80d0-85abb6afec21",
"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": "3.10.17"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
