How to Integrate Amazon AI with Google Slides

Integrating Amazon AI with Google Slides

• Ensure you have administrative access to both an Amazon Web Services (AWS) account and a Google account to access Google Slides.

 

• Obtain necessary credentials for both platforms: AWS Access Key ID, Secret Access Key, and Google OAuth 2.0 credentials.

Set Up AWS SDK

• Install the AWS SDK for your preferred programming language. In this example, we'll use Python. You can install the AWS SDK using pip:

pip install boto3

• Configure your AWS credentials on your local machine:

aws configure

• Input your Access Key ID, Secret Access Key, region, and output format when prompted.

Authorize Access to Google Slides API

• Go to the Google Cloud Console and create a new project or select an existing one.

 

• Enable the Google Slides API from the API Library.

 

• Under "Credentials," click "Create credentials" and select "OAuth client ID". Follow the instructions to set up the consent screen and create the credentials.

 

• Download the JSON file containing your client secrets and save it as `credentials.json` in your project directory.

Set Up Google Slides API

• Install the Google client library for Python:

pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib

• Follow the prompt to authorize access when running the app for the first time, this will involve a browser verification step.

Connect and Integrate Both Services

• Start by importing necessary libraries. Establish connections to AWS and Google Slides API using their respective SDKs.

import boto3
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
import os
import pickle

# AWS Client
aws_client = boto3.client('comprehend', region_name='us-east-1')

# Google Slides API
SCOPES = ['https://www.googleapis.com/auth/presentations']
creds = None

if os.path.exists('token.pickle'):
    with open('token.pickle', 'rb') as token:
        creds = pickle.load(token)

if not creds or not creds.valid:
    if creds and creds.expired and creds.refresh_token:
        creds.refresh(Request())
    else:
        flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
        creds = flow.run_local_server(port=0)

    with open('token.pickle', 'wb') as token:
        pickle.dump(creds, token)

slides_service = build('slides', 'v1', credentials=creds)

• Create a function to extract text from Google Slides, pass it to an AWS AI service (e.g., Amazon Comprehend for natural language processing), and return the result.

def analyze_presentation(presentation_id):
    presentation = slides_service.presentations().get(presentationId=presentation_id).execute()
    slides = presentation.get('slides')

    for slide in slides:
        for element in slide['pageElements']:
            if 'shape' in element and 'text' in element['shape']:
                text = element['shape']['text']['textElements']
                full_text = ''.join([te.get('textRun', {}).get('content', '') for te in text if 'textRun' in te])
                
                if full_text.strip():
                    response = aws_client.detect_dominant_language(Text=full_text)
                    languages = response['Languages']
                    print('Detected languages:', languages)

• Replace `presentation_id` with your Google Slide presentation ID and run the function to analyze text using Amazon AI capabilities.

Test and Implement Your Integration

• Run your script to ensure both the AWS and Google APIs are responding correctly and you are receiving the expected analysis results.

 

• Debug any issues by checking credentials, permissions, and existing API service configurations.

 

• Once successful, expand the integration to include more sophisticated use cases, such as enrichments or embedding results back into slides.