The Bumbling Electron

Friday, July 18, 2025

Using AI to retrieve genre and synopsis from book titles

Programmer Taps AI to Tame Sprawling Digital Book Collection

TORONTO – A local programmer has developed a novel approach to a uniquely 21st-century problem: how to bring order to a sprawling personal library of several thousand e-book files. By integrating Google's Gemini AI, he has created a system to automatically retrieve the genre and synopsis for each title, transforming a disorganized collection into a meticulously cataloged digital library.

The project began with the challenge of files named with inconsistent author and title information. Using the epub-metadata library for Python, the developer first built a tool to reliably extract the title from each file. The next step was to enrich this basic data. "I wanted to be able to use AI and Google to get the genre and synopsis," he stated, outlining his goal.

To accomplish this, he turned to Google's AI Studio to acquire an API key, granting his script access to the powerful Gemini Pro model. In a proof-of-concept script, he demonstrated how the AI could be queried with a book's title to return structured metadata. The system is designed for a streamlined workflow; the Python script securely accesses the API key from an environment variable, a standard practice for managing credentials in software development.

This innovative solution showcases the growing accessibility of advanced artificial intelligence, allowing individuals to build powerful, custom tools to manage personal data and automate complex organizational tasks. The programmer's initial tests have proven successful, paving the way for the full-scale cataloging of his extensive collection.

Title: the emperors new mind

('Genre: Science, Physics, Mathematics, Computer Science, Philosophy of Mind, ' 'Artificial Intelligence\n' 'Synopsys: Roger Penrose, a renowned physicist and mathematician, presents a ' 'controversial argument that human consciousness cannot be fully explained by ' 'classical computation or algorithms, directly challenging the foundations of ' "'strong AI.' Drawing upon concepts from quantum mechanics, general " "relativity, and Gödel's incompleteness theorems, he proposes that " 'non-computable processes are essential to understanding the mind, suggesting ' 'a deeper connection between consciousness and the fundamental laws of ' 'physics.')
""" Google Books API Integration Script This script uses Google's Gemini AI API to retrieve genre and synopsis information for books based on their titles. It constructs a query using the book title and the Google Books URL format, then uses the Gemini AI model to generate a response with genre and synopsis information. Requirements: - Google Gemini API key set as environment variable 'GEMINI_API_KEY' - google-generativeai package installed Usage: python test_google_book_api.py (The script will prompt for a book title) """ import pprint # For pretty-printing the API response from google import genai # Google's Generative AI library # The client gets the API key from the environment variable `GEMINI_API_KEY`. # Google Books URL format: https://www.google.ca/books/edition/title def aibook(title): """ Query the Gemini AI model for book genre and synopsis information. This function creates a Gemini AI client, constructs a prompt with the book title and desired output format, then returns the generated text response. Args: title (str): The title of the book to query Returns: str: The formatted response text containing genre and synopsis information Example output format: Genre: Fiction, Science Fiction, Dystopian Synopsis: A story about... """ # Initialize the Gemini AI client client = genai.Client() # Generate content using the Gemini model with a formatted prompt response = client.models.generate_content( model="gemini-2.5-flash", # Using the Gemini 2.5 Flash model for fast responses contents=f""" book url https://www.google.ca/books/edition/{title}/ provide the genre and synopsis of the book use the format line 1 Genre: genre1, genre2, etc line 2 Synopsys: the synopsys """ ) # Return the text portion of the response return response.text # Execute only if run as a script, not when imported as a module if __name__ == "__main__": # Prompt the user for a book title, pass it to the aibook function, # and pretty-print the results pprint.pp(aibook(input('Title: ')))

Github link

Saturday, July 5, 2025

You Are Not Expected to Understand This - How 26 Lines of Code Changed the World

This collection of texts explores the **profound impact of code and software on various aspects of society**, from its early conceptualisation to modern-day applications. It discusses how **human decisions, biases, and ingenious solutions are embedded within code**, influencing everything from space exploration and the internet's structure to social interactions and public safety. The sources examine **pivotal moments in computing history**, such as the development of programming languages like BASIC and COBOL, the invention of email, and the rise of digital gaming. Furthermore, they highlight **critical challenges like software vulnerabilities and ethical dilemmas**, including the unintended consequences of algorithms in policing and advertising, and the ongoing struggle for digital privacy and inclusivity. Ultimately, the compilation underscores that **code is not merely technical but a deeply human endeavour** with far-reaching societal implications.

Saturday, June 28, 2025

Raspberry Pi Weather Clock

I have a 2 line by 16 character LCD display with a I2C interface. I wanted to use it as a clock and date display which also could display the current weather.

Date and Time Display

Weather Display

I am using a raspberry pi 5 to run a python script to drive the display using the GPIO pins

Rapsberry Pi 5 clock/weather

You will need an API key to open weather openweatherapi. Put your api key in an .env file as openweathermapapikey=yourkey. The python script uses the dotenv library to read this and use your API key. This is a free service with usage limitations. You will need to change the parameters to the open weather API to use you city and units.

params = {

"q": "Etobicoke,Ontario,CA",

"units": "metric", # For Celsius

"appid": OPENWEATHERMAPAPIKEY # API key

}

#!/usr/bin/env python3
"""
lcd_weatherclock.py - A program that displays a clock on an LCD screen
and shows weather information for 10 seconds when a button is pressed.
"""

from LCD import LCD
import datetime
import time
import requests
import os
from dotenv import load_dotenv
from gpiozero import Button
import threading

# Load environment variables from .env file
load_dotenv()

# Initialize LCD
lcd = LCD(2, 0x27, True)
lcd.clear()

# Initialize button with debounce
button = Button(21, pull_up=True, bounce_time=0.2) # 200ms debounce time

# Global variables
display_mode = "clock" # Can be "clock" or "weather"
weather_timer = None

def get_etobicoke_weather():
"""
Get current weather for Etobicoke, Ontario, Canada using OpenWeatherMap API
"""
try:
# OpenWeatherMap API endpoint for current weather
url = "https://api.openweathermap.org/data/2.5/weather"

# Get APP ID for weather api
OPENWEATHERMAPAPIKEY = os.getenv("openweathermapapikey")
# Parameters for Etobicoke, Ontario, Canada
params = {
"q": "Etobicoke,Ontario,CA",
"units": "metric", # For Celsius
"appid": OPENWEATHERMAPAPIKEY # API key
}

# Make the API request
response = requests.get(url, params=params)

# Check if the request was successful
if response.status_code == 200:
# Parse the JSON response
weather_data = response.json()

# Extract relevant information
temperature = weather_data["main"]["temp"]
condition = weather_data["weather"][0]["main"]
humidity = weather_data["main"]["humidity"]

return {
"temperature": temperature,
"condition": condition,
"humidity": humidity
}
else:
return {"error": f"API Error: {response.status_code}"}

except Exception as e:
return {"error": f"Error: {str(e)}"}

def display_weather(lcd):
"""
Display weather data on the LCD
"""
global display_mode

# Set display mode to weather
display_mode = "weather"

# Show loading message
lcd.clear()
lcd.message("Weather...")

# Get weather data
weather_data = get_etobicoke_weather()

lcd.clear()
if "error" in weather_data:
lcd.message("Weather Error")
lcd.message(weather_data["error"][:16], 2) # Truncate to fit LCD width
else:
# Format and display weather information
temp_str = f"Temp: {weather_data['temperature']:.1f}C"
cond_str = f"{weather_data['condition']} {weather_data['humidity']}%"

lcd.message(temp_str)
lcd.message(cond_str, 2)

# Set a timer to switch back to clock after 10 seconds
global weather_timer
if weather_timer:
weather_timer.cancel()
weather_timer = threading.Timer(10.0, switch_to_clock)
weather_timer.start()

def switch_to_clock():
"""
Switch display back to clock mode
"""
global display_mode
display_mode = "clock"
# The main loop will update the display on the next iteration

def display_clock(lcd, force_update=False):
"""
Display clock on the LCD
"""
now = datetime.datetime.now()
currenttime = now.strftime("%H:%M:%S")
currentdate = now.strftime("%d-%m-%Y")

# Only update if time/date changed or force update is requested
if force_update or currenttime != display_clock.lasttime or currentdate != display_clock.lastdate:
lcd.clear()
lcd.message('%02d:%02d:%02d' % (now.hour, now.minute, now.second), 1)
lcd.message('%02d-%02d-%04d' % (now.day, now.month, now.year), 2)
display_clock.lasttime = currenttime
display_clock.lastdate = currentdate

# Initialize static variables for display_clock function
display_clock.lasttime = ''
display_clock.lastdate = ''

def button_pressed():
"""Function called when button is pressed"""
global display_mode
if display_mode == "clock":
display_weather(lcd)

# Assign callback function to button press event
button.when_pressed = button_pressed

# Display welcome message
lcd.message("Weather Clock")
lcd.message("Starting...", 2)
time.sleep(2)
lcd.clear()

# Main loop
try:
while True:
if display_mode == "clock":
display_clock(lcd)
time.sleep(0.1)
except KeyboardInterrupt:
# Clean up on exit
if weather_timer:
weather_timer.cancel()
lcd.clear()
print("\nExiting program")

Thursday, April 17, 2025

Vegetative Electron Microscopy

In episode 64 of the AI Inside podcast, titled "Vegetative Electron Microscopy Doesn't Exist", Jason and Jeff discuss the hallucination of "Vegetative Electron Microscopy" by leading AI tools.

I decided to see what the latest Gemini deep research 2.5 pro thinks it is.

I asked it to explain the meaning of Vegetative Electron Microscopy.

I copied the result to a Google Doc.

Scroll down to the conclusion and the first paragraph states,

The investigation undertaken in this report confirms that the phrase "Vegetative Electron Microscopy" is not a standard, recognised term within the scientific field of electron microscopy.1 Its appearance in the scientific literature is anomalous and has been linked to several potential sources, including technical errors in digital text processing (AI/OCR errors), mistranslations from other languages (specifically Persian), or its use as a marker or artifact associated with fraudulent publications generated by paper mills.1 The fact that the phrase has been explicitly corrected to "scanning electron microscopy" in at least one publication further underscores its erroneous nature.

Monday, March 17, 2025

GIMP 3.0 Released

After 7 years, the new version, 3.0, of GIMP (GNU Image Manipulation Program) has been released.

Death Is Not Final - The Debate

The Open To Debate site debated the statement "Death is not finale". The moderator-in-chief John Donvan does his usual great moderator job.

For the statement is Eben Alexander, Neurosurgeon, Author of ‘Proof of Heaven’ and Raymond Moody, Medical Doctor, Author of ‘Life After Life’.

Against is Sean Carroll, Physicist & writer and Steven Novella, Academic Neurologist at the Yale School of Medicine.

From the web site "If consciousness is just the workings of neurons and synapses, how do we explain the phenomenon of near-death experience? By some accounts, about 3% of the U.S. population has had one: an out-of-body experience often characterized by remarkable visions and feelings of peace and joy, all while the physical body is close to death. To skeptics, there are more plausible, natural explanations, like oxygen deprivation. Is the prospect of an existence after death “real” and provable by science, or a construct of wishful thinking about our own mortality?"