Introduction to Generative AI. In the fascinating world of artificial… | by Madhuri | Jan, 2025

In the fascinating world of artificial intelligence (AI), Generative AI emerges as a powerful player, transforming the landscape of creativity and automation. From generating realistic images and composing music to writing text and designing new concepts, Generative AI is revolutionizing how we approach creative tasks. In this article, we’ll dive into what Generative AI is, explore its real-world applications, and see how it simplifies complex tasks with a practical code example.

What is Generative AI?

Generative AI is a branch of AI that focuses on creating new content by learning patterns from existing data. Unlike traditional AI models, which are typically used for tasks like classification or regression, Generative AI models generate new data instances that closely resemble their training data. These models can produce a wide range of content, including images, text, audio, and even video.

Real-World Applications

1. Code Generation and Autocompletion

Generative AI can be a developer’s best friend, generating code snippets and offering intelligent autocompletion. Tools like GitHub Copilot, powered by OpenAI’s Codex, suggest code as developers type, speeding up the coding process and reducing errors.

2. Automated Testing

Generative AI can streamline the testing process by creating unit tests, integration tests, and even UI tests. It analyzes existing codebases to identify critical paths, ensuring thorough test coverage and saving time that would otherwise be spent on manual test creation.

3. Bug Detection and Fixing

Generative AI models excel at analyzing code to detect potential bugs and suggest fixes. By learning from vast amounts of code and bug reports, these models can identify patterns and recommend solutions, improving code quality and reducing debugging time.

4. Documentation Generation

Writing comprehensive documentation can be a daunting task. Generative AI can automatically generate documentation from code comments, function names, and even by understanding the code’s functionality. This ensures that documentation is up-to-date and accurate with minimal effort.

Simple Example:

Traditional Approach: Rule-Based Methods

In a traditional approach, text summarization can be achieved using rule-based methods. This involves extracting key sentences based on predefined rules such as sentence length, keyword frequency, or position in the text.

from nltk.tokenize import sent_tokenize
from nltk.corpus import stopwords
from nltk.probability import FreqDist
from nltk.tokenize import word_tokenize
def summarize_text(text):
# Tokenize the text into sentences
sentences = sent_tokenize(text)
# Tokenize the text into words
words = word_tokenize(text.lower())
# Remove stopwords
stop_words = set(stopwords.words('english'))
filtered_words = [word for word in words if word.isalnum() and word not in stop_words]
# Calculate word frequencies
word_freq = FreqDist(filtered_words)
# Score sentences based on word frequencies
sentence_scores = {}
for sentence in sentences:
for word in word_tokenize(sentence.lower()):
if word in word_freq:
if sentence not in sentence_scores:
sentence_scores[sentence] = word_freq[word]
else:
sentence_scores[sentence] += word_freq[word]
# Select top 3 sentences as summary
summary_sentences = sorted(sentence_scores, key=sentence_scores.get, reverse=True)[:3]
summary = ' '.join(summary_sentences)
return summary
# Example usage
text = """
Artificial intelligence (AI) is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Leading AI textbooks define the field as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term "artificial intelligence" is often used to describe machines (or computers) that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem-solving".
"""
print(summarize_text(text))

Generative AI Approach: Using Transformer Models

With Generative AI, text summarization can be performed using transformer-based models like BERT or GPT-3. These models understand context and generate coherent summaries effortlessly.

import requests
from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer
# Disable SSL verification
requests.packages.urllib3.disable_warnings(requests.packages.urllib3.exceptions.InsecureRequestWarning)
# Specify the local directory where you saved the model and tokenizer files
local_model_dir = ""
# Load the model and tokenizer from the local directory
model = AutoModelForSeq2SeqLM.from_pretrained(local_model_dir)
tokenizer = AutoTokenizer.from_pretrained(local_model_dir)
summarizer = pipeline("summarization", model=model, tokenizer=tokenizer)
def summarize_text(text):
summary = summarizer(text, max_length=50, min_length=25, do_sample=False)
return summary[0]['summary_text']
# Example usage
text = """
Artificial intelligence (AI) is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Leading AI textbooks define the field as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term "artificial intelligence" is often used to describe machines (or computers) that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem-solving".
"""
print(summarize_text(text))

Feel free to clap 👏 or leave a comment if you found this helpful ❤️🙏