1 changed files with 128 additions and 122 deletions
@ -1,125 +1,131 @@ |
|||||||
{ |
{ |
||||||
"cells": [ |
"cells": [ |
||||||
{ |
{ |
||||||
"cell_type": "code", |
"cell_type": "code", |
||||||
"execution_count": null, |
"execution_count": null, |
||||||
"id": "a767b6bc-65fe-42b2-988f-efd54125114f", |
"id": "a767b6bc-65fe-42b2-988f-efd54125114f", |
||||||
"metadata": {}, |
"metadata": {}, |
||||||
"outputs": [], |
"outputs": [], |
||||||
"source": [ |
"source": [ |
||||||
"import os\n", |
"import os\n", |
||||||
"import requests\n", |
"import requests\n", |
||||||
"from dotenv import load_dotenv\n", |
"from dotenv import load_dotenv\n", |
||||||
"from bs4 import BeautifulSoup\n", |
"from bs4 import BeautifulSoup\n", |
||||||
"from IPython.display import Markdown, display, clear_output\n", |
"from IPython.display import Markdown, display, clear_output\n", |
||||||
"from openai import OpenAI\n", |
"from openai import OpenAI\n", |
||||||
"\n", |
"\n", |
||||||
"load_dotenv(override=True)\n", |
"load_dotenv(override=True)\n", |
||||||
"api_key = os.getenv('DEEPSEEK_API_KEY')\n", |
"# Deep seek API payload\n", |
||||||
"base_url=os.getenv('DEEPSEEK_BASE_URL')\n", |
"# api_key = os.getenv('DEEPSEEK_API_KEY')\n", |
||||||
"MODEL = \"deepseek-chat\"\n", |
"# base_url=os.getenv('DEEPSEEK_BASE_URL')\n", |
||||||
"\n", |
"# MODEL = \"deepseek-chat\"\n", |
||||||
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n", |
"\n", |
||||||
"and provides a short summary, ignoring text that might be navigation related. \\\n", |
"# Day 2 Exercise with Ollama API\n", |
||||||
"Respond in markdown.\"\n", |
"api_key = os.getenv('OLLAMA_API_KEY')\n", |
||||||
"\n", |
"base_url = os.getenv('OLLAMA_BASE_URL')\n", |
||||||
"messages = [\n", |
"MODEL = \"llama3.2\"\n", |
||||||
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", |
"\n", |
||||||
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", |
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n", |
||||||
"]\n", |
"and provides a short summary, ignoring text that might be navigation related. \\\n", |
||||||
" \n", |
"Respond in markdown.\"\n", |
||||||
"# Check the key\n", |
"\n", |
||||||
"if not api_key:\n", |
"messages = [\n", |
||||||
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n", |
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", |
||||||
"elif not api_key.startswith(\"sk-proj-\"):\n", |
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", |
||||||
" print(\"An API key was found, but it doesn't start sk-proj-; Looks like you are using DeepSeek (R1) model.\")\n", |
"]\n", |
||||||
"elif api_key.strip() != api_key:\n", |
" \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", |
"# Check the key\n", |
||||||
"else:\n", |
"if not api_key:\n", |
||||||
" print(\"API key found and looks good so far!\")\n", |
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n", |
||||||
" \n", |
"elif not api_key.startswith(\"sk-proj-\"):\n", |
||||||
"openai = OpenAI(api_key=api_key, base_url=base_url)\n", |
" print(\"An API key was found, but it doesn't start sk-proj-; Looks like you are using DeepSeek (R1) model.\")\n", |
||||||
"\n", |
"elif api_key.strip() != api_key:\n", |
||||||
"headers = {\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", |
||||||
" \"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", |
"else:\n", |
||||||
"}\n", |
" print(\"API key found and looks good so far!\")\n", |
||||||
"\n", |
" \n", |
||||||
"class Website:\n", |
"openai = OpenAI(api_key=api_key, base_url=base_url)\n", |
||||||
"\n", |
"\n", |
||||||
" def __init__(self, url):\n", |
"headers = {\n", |
||||||
" \"\"\"\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", |
||||||
" Create this Website object from the given url using the BeautifulSoup library\n", |
"}\n", |
||||||
" \"\"\"\n", |
"\n", |
||||||
" self.url = url\n", |
"class Website:\n", |
||||||
" response = requests.get(url, headers=headers)\n", |
"\n", |
||||||
" soup = BeautifulSoup(response.content, 'html.parser')\n", |
" def __init__(self, url):\n", |
||||||
" self.title = soup.title.string if soup.title else \"No title found\"\n", |
" \"\"\"\n", |
||||||
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", |
" Create this Website object from the given url using the BeautifulSoup library\n", |
||||||
" irrelevant.decompose()\n", |
" \"\"\"\n", |
||||||
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", |
" self.url = url\n", |
||||||
" \n", |
" response = requests.get(url, headers=headers)\n", |
||||||
"def user_prompt_for(website):\n", |
" soup = BeautifulSoup(response.content, 'html.parser')\n", |
||||||
" user_prompt = f\"You are looking at a website titled {website.title}\"\n", |
" self.title = soup.title.string if soup.title else \"No title found\"\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", |
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", |
||||||
" user_prompt += website.text\n", |
" irrelevant.decompose()\n", |
||||||
" return user_prompt\n", |
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", |
||||||
"\n", |
" \n", |
||||||
"def messages_for(website):\n", |
"def user_prompt_for(website):\n", |
||||||
" return [\n", |
" user_prompt = f\"You are looking at a website titled {website.title}\"\n", |
||||||
" {\"role\": \"system\", \"content\": system_prompt},\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", |
||||||
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
" user_prompt += website.text\n", |
||||||
" ]\n", |
" return user_prompt\n", |
||||||
" \n", |
"\n", |
||||||
"def summarize(url):\n", |
"def messages_for(website):\n", |
||||||
" website = Website(url)\n", |
" return [\n", |
||||||
" response = openai.chat.completions.create(\n", |
" {\"role\": \"system\", \"content\": system_prompt},\n", |
||||||
" model=MODEL,\n", |
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
||||||
" messages=messages_for(website),\n", |
" ]\n", |
||||||
" stream=True\n", |
" \n", |
||||||
" )\n", |
"def summarize(url):\n", |
||||||
" print(\"Streaming response:\")\n", |
" website = Website(url)\n", |
||||||
" accumulated_content = \"\" # Accumulate the content here\n", |
" response = openai.chat.completions.create(\n", |
||||||
" for chunk in response:\n", |
" model=MODEL,\n", |
||||||
" if chunk.choices[0].delta.content: # Check if there's content in the chunk\n", |
" messages=messages_for(website),\n", |
||||||
" accumulated_content += chunk.choices[0].delta.content # Append the chunk to the accumulated content\n", |
" stream=True\n", |
||||||
" clear_output(wait=True) # Clear the previous output\n", |
" )\n", |
||||||
" display(Markdown(accumulated_content)) # Display the updated content\n", |
" print(\"Streaming response:\")\n", |
||||||
"\n", |
" accumulated_content = \"\" # Accumulate the content here\n", |
||||||
"def display_summary():\n", |
" for chunk in response:\n", |
||||||
" url = str(input(\"Enter the URL of the website you want to summarize: \"))\n", |
" if chunk.choices[0].delta.content: # Check if there's content in the chunk\n", |
||||||
" summarize(url)\n", |
" accumulated_content += chunk.choices[0].delta.content # Append the chunk to the accumulated content\n", |
||||||
"\n", |
" clear_output(wait=True) # Clear the previous output\n", |
||||||
"display_summary()" |
" display(Markdown(accumulated_content)) # Display the updated 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()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "01c9e5e7-7510-43ef-bb9c-aa44b15d39a7", |
||||||
|
"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, |
||||||
"cell_type": "code", |
"nbformat_minor": 5 |
||||||
"execution_count": null, |
|
||||||
"id": "01c9e5e7-7510-43ef-bb9c-aa44b15d39a7", |
|
||||||
"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 |
|
||||||
} |
} |
||||||
|
Loading…
Reference in new issue