🧠 AI with Python – 📝 Summarization using Transformers Pipeline

# =========================================================
# 📦 Install Required Libraries
# =========================================================

# Run this in terminal if not installed:
# pip install transformers torch sentencepiece


# =========================================================
# 📦 Import Required Libraries
# =========================================================

from transformers import pipeline


# =========================================================
# 🤖 Create Summarization Pipeline
# =========================================================

summarizer = pipeline(
    task="summarization",
    model="facebook/bart-large-cnn"
)


# =========================================================
# 📄 Create Sample Document
# =========================================================

document = """
Artificial Intelligence has transformed many industries over the past decade.
Machine Learning allows computers to learn from data without explicit programming.
Deep Learning has enabled significant advances in computer vision and natural
language processing. Today, transformer models power applications such as
chatbots, document summarization, translation, recommendation systems, and
intelligent search engines. As organizations adopt AI at scale, the demand for
efficient language models and automation continues to grow.
"""


# =========================================================
# 🚀 Generate Summary
# =========================================================

summary_result = summarizer(
    document,
    max_length=60,
    min_length=20,
    do_sample=False
)


# =========================================================
# 📖 Display Original and Summary
# =========================================================

print("=== Original Document ===\n")
print(document.strip())

print("\n=== Generated Summary ===\n")
print(
    summary_result[0]["summary_text"]
)


# =========================================================
# 📊 Compare Text Length
# =========================================================

original_word_count = len(
    document.split()
)

summary_word_count = len(
    summary_result[0]["summary_text"].split()
)

reduction_percentage = (
    (
        original_word_count
        - summary_word_count
    )
    /
    original_word_count
) * 100

print("\n=== Summary Statistics ===")

print(
    "Original Word Count:",
    original_word_count
)

print(
    "Summary Word Count:",
    summary_word_count
)

print(
    "Reduction Percentage:",
    round(reduction_percentage, 2),
    "%"
)


# =========================================================
# 🔄 Summarize Another Document
# =========================================================

another_document = """
Python has become one of the world's most popular programming languages because
of its simple syntax, large ecosystem, and versatility. It is widely used in
web development, automation, artificial intelligence, machine learning,
scientific computing, backend development, and data analysis. Its strong
community support and extensive collection of open-source libraries make it
suitable for both beginners and experienced developers.
"""

another_summary = summarizer(
    another_document,
    max_length=45,
    min_length=15,
    do_sample=False
)

print("\n=== Second Document ===\n")
print(another_document.strip())

print("\n=== Second Summary ===\n")
print(
    another_summary[0]["summary_text"]
)


# =========================================================
# 🔁 Summarize Multiple Documents
# =========================================================

documents = [
    """
    Cloud computing allows organizations to access computing resources such as
    servers, storage, databases, and applications over the internet. It helps
    businesses scale quickly, reduce infrastructure costs, and deploy services
    across multiple regions.
    """,

    """
    Cybersecurity protects systems, networks, and data from digital attacks.
    Organizations use encryption, access controls, monitoring, and security
    policies to reduce risk and protect sensitive information.
    """,

    """
    Data engineering focuses on collecting, transforming, storing, and
    delivering reliable data for analytics and machine learning. Data engineers
    build pipelines that move information from source systems into warehouses,
    lakes, and reporting platforms.
    """
]


print("\n=== Multiple Document Summaries ===")

for index, text in enumerate(
    documents,
    start=1
):

    result = summarizer(
        text,
        max_length=45,
        min_length=15,
        do_sample=False
    )

    print("\n" + "=" * 60)
    print(f"Document {index} Summary:")
    print("=" * 60)

    print(
        result[0]["summary_text"]
    )


# =========================================================
# ✅ Final Note
# =========================================================

print(
    "\nSummarization demo completed successfully."
)