1 changed files with 119 additions and 0 deletions
@ -0,0 +1,119 @@ |
|||||||
|
{ |
||||||
|
"cells": [ |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "a767b6bc-65fe-42b2-988f-efd54125114f", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"import os\n", |
||||||
|
"import requests\n", |
||||||
|
"from dotenv import load_dotenv\n", |
||||||
|
"from bs4 import BeautifulSoup\n", |
||||||
|
"from IPython.display import Markdown, display\n", |
||||||
|
"from openai import OpenAI\n", |
||||||
|
"import time\n", |
||||||
|
"\n", |
||||||
|
"load_dotenv(override=True)\n", |
||||||
|
"api_key = os.getenv('DEEPSEEK_API_KEY')\n", |
||||||
|
"base_url=os.getenv('DEEPSEEK_BASE_URL')\n", |
||||||
|
"start_time = time.time()\n", |
||||||
|
"\n", |
||||||
|
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n", |
||||||
|
"and provides a short summary, ignoring text that might be navigation related. \\\n", |
||||||
|
"Respond in markdown.\"\n", |
||||||
|
"\n", |
||||||
|
"messages = [\n", |
||||||
|
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", |
||||||
|
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", |
||||||
|
"]\n", |
||||||
|
" \n", |
||||||
|
"# Check the key\n", |
||||||
|
"if not api_key:\n", |
||||||
|
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n", |
||||||
|
"elif not api_key.startswith(\"sk-proj-\"):\n", |
||||||
|
" print(\"An API key was found, but it doesn't start sk-proj-; Looks like you are using DeepSeek (R1) model.\")\n", |
||||||
|
"elif api_key.strip() != api_key:\n", |
||||||
|
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n", |
||||||
|
"else:\n", |
||||||
|
" print(\"API key found and looks good so far!\")\n", |
||||||
|
" \n", |
||||||
|
"openai = OpenAI(api_key=api_key, base_url=base_url)\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", |
||||||
|
" def __init__(self, url):\n", |
||||||
|
" \"\"\"\n", |
||||||
|
" Create this Website object from the given url using the BeautifulSoup library\n", |
||||||
|
" \"\"\"\n", |
||||||
|
" self.url = url\n", |
||||||
|
" response = requests.get(url, headers=headers)\n", |
||||||
|
" soup = BeautifulSoup(response.content, '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 user_prompt_for(website):\n", |
||||||
|
" user_prompt = f\"You are looking at a website titled {website.title}\"\n", |
||||||
|
" user_prompt += \"\\nThe contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\\n\\n\"\n", |
||||||
|
" user_prompt += website.text\n", |
||||||
|
" return user_prompt\n", |
||||||
|
"\n", |
||||||
|
"def messages_for(website):\n", |
||||||
|
" return [\n", |
||||||
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
||||||
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
||||||
|
" ]\n", |
||||||
|
" \n", |
||||||
|
"def summarize(url):\n", |
||||||
|
" website = Website(url)\n", |
||||||
|
" response = openai.chat.completions.create(\n", |
||||||
|
" model=\"deepseek-chat\",\n", |
||||||
|
" messages=messages_for(website),\n", |
||||||
|
" stream=True\n", |
||||||
|
" )\n", |
||||||
|
" print(\"Streaming response:\")\n", |
||||||
|
" accumulated_content = \"\" # Accumulate the content here\n", |
||||||
|
" for chunk in response:\n", |
||||||
|
" if chunk.choices[0].delta.content: # Check if there's content in the chunk\n", |
||||||
|
" accumulated_content += chunk.choices[0].delta.content # Append the chunk to the accumulated content\n", |
||||||
|
" \n", |
||||||
|
" # Display the accumulated content as a single Markdown block\n", |
||||||
|
" display(Markdown(accumulated_content))\n", |
||||||
|
"\n", |
||||||
|
"def display_summary():\n", |
||||||
|
" url = str(input(\"Enter the URL of the website you want to summarize: \"))\n", |
||||||
|
" summarize(url)\n", |
||||||
|
"\n", |
||||||
|
"display_summary()" |
||||||
|
] |
||||||
|
} |
||||||
|
], |
||||||
|
"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…
Reference in new issue