by crc

AI Eye

Test this app for free
55
import logging
from gunicorn.app.base import BaseApplication
from app_init import create_initialized_flask_app

# Flask app creation should be done by create_initialized_flask_app to avoid circular dependency problems.
app = create_initialized_flask_app()

# Setup logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

class StandaloneApplication(BaseApplication):
    def __init__(self, app, options=None):
        self.application = app
        self.options = options or {}
        super().__init__()

    def load_config(self):
        # Apply configuration to Gunicorn
        for key, value in self.options.items():
            if key in self.cfg.settings and value is not None:
                self.cfg.set(key.lower(), value)

    def load(self):
Get full code

AI Eye

Created: | Last Updated:

Web app for blind users to navigate by capturing images with a single button, utilizing AI for image description and text-to-speech conversion. I hope other people out there can extend this template and make it really useful for people that could benefit from it.

Here's a step-by-step guide for using the AI Eye template:

Introduction

The AI Eye template provides a web application designed to assist blind users in navigating their environment. It captures images with a single button press, utilizes AI for image description, and converts text to speech. This guide will walk you through setting up and using the template.

Getting Started

  1. Click "Start with this Template" to begin using the AI Eye template in the Lazy Builder interface.

Initial Setup

To use this template, you'll need to set up an OpenAI API key:

  1. Go to OpenAI's website and create an account or log in.
  2. Navigate to the API section and generate a new API key.
  3. In the Lazy Builder, go to the Environment Secrets tab.
  4. Add a new secret with the key OPENAI_API_KEY and paste your OpenAI API key as the value.

Test the Application

  1. Click the "Test" button in the Lazy Builder interface to deploy the application.
  2. Wait for the deployment process to complete.
  3. Once deployed, you'll receive a server link to access the web application.

Using the App

  1. Open the provided server link in a web browser on a mobile device.
  2. The entire screen acts as a capture button.
  3. To use the app:
  4. Tap anywhere on the screen to capture an image.
  5. The app will process the image and provide an audio description of the environment.
  6. Listen to the description to understand your surroundings.

Features

  • The app uses the device's rear-facing camera for image capture.
  • Image descriptions are provided in the user's preferred language (based on browser settings).
  • The screen is kept awake to prevent sleep during use.
  • The app works as a Progressive Web App (PWA) and can be installed on supported devices.

By following these steps, you'll have a functional AI-powered navigation assistant for blind users. The app captures images, processes them using AI, and provides audio descriptions to help users understand their environment.

Technologies

Flask Flask
Google Cloud Platform Google Cloud Platform