Summarize text with LLMs

%pip install -qU pixeltable openai

import getpass
import os

if 'OPENAI_API_KEY' not in os.environ:
    os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key: ')

import pixeltable as pxt
from pixeltable.functions import openai

# Create a fresh directory
pxt.drop_dir('summarize_demo', force=True)
pxt.create_dir('summarize_demo')

# Create table for articles
articles = pxt.create_table(
    'summarize_demo/articles',
    {'title': pxt.String, 'content': pxt.String},
)

# Sample articles to summarize
sample_articles = [
    {
        'title': 'The Rise of Electric Vehicles',
        'content': """Electric vehicles (EVs) have seen unprecedented growth in recent years,
        transforming the automotive industry. Sales increased by 60% globally in 2023,
        with China leading the market followed by Europe and North America. Major automakers
        like Tesla, BYD, and traditional manufacturers have invested billions in EV technology.
        Battery costs have dropped significantly, making EVs more affordable for consumers.
        Government incentives and stricter emissions regulations continue to drive adoption.
        Charging infrastructure is expanding rapidly, with new fast-charging networks being
        deployed across major highways. Despite challenges like range anxiety and charging
        times, consumer acceptance is growing steadily.""",
    },
    {
        'title': 'Advances in Renewable Energy',
        'content': """Solar and wind power capacity reached record levels in 2023, accounting
        for over 30% of global electricity generation. The cost of solar panels has fallen
        by 90% over the past decade, making renewable energy competitive with fossil fuels.
        Offshore wind farms are being built at scale, with turbines now reaching heights
        of over 250 meters. Energy storage solutions, particularly lithium-ion batteries,
        are addressing intermittency challenges. Countries like Denmark and Scotland have
        achieved periods of 100% renewable electricity. Corporate power purchase agreements
        are accelerating the transition, with tech giants committing to carbon-neutral operations.""",
    },
]

articles.insert(sample_articles)

# View articles
articles.select(articles.title, articles.content).collect()

# Create prompt template for summarization
prompt = (
    'Summarize the following article in 2-3 sentences:\n\n'
    + articles.content
)

# Add computed column for LLM response
articles.add_computed_column(
    response=openai.chat_completions(
        messages=[{'role': 'user', 'content': prompt}],
        model='gpt-4o-mini',
    )
)

# Extract the summary text from the response
articles.add_computed_column(
    summary=articles.response.choices[0].message.content
)

# View titles and summaries
articles.select(articles.title, articles.summary).collect()

# Add bullet-point summary
bullet_prompt = (
    'List the 3 key points from this article as bullet points:\n\n'
    + articles.content
)

articles.add_computed_column(
    bullet_response=openai.chat_completions(
        messages=[{'role': 'user', 'content': bullet_prompt}],
        model='gpt-4o-mini',
    )
)

articles.add_computed_column(
    key_points=articles.bullet_response.choices[0].message.content
)

# View bullet-point summaries
articles.select(articles.title, articles.key_points).collect()

# Insert a new article - summaries are generated automatically
articles.insert(
    [
        {
            'title': 'AI in Healthcare',
            'content': """Artificial intelligence is revolutionizing healthcare diagnostics
    and treatment planning. Machine learning models can now detect diseases from
    medical images with accuracy matching or exceeding human specialists. AI-powered
    drug discovery is accelerating the development of new treatments. Natural language
    processing is being used to extract insights from clinical notes and research papers.""",
        }
    ]
)

# View all summaries including the new article
articles.select(articles.title, articles.summary).collect()