Google Drive Integration Feature in CreateAI Builder
The Google Drive integration allows you to connect your Google Drive directly to CreateAI Builder so you can easily import your files (Docs, Sheets, PDFs, and other supported file types that live in your drive) into the platform. This removes the need to download and re-upload documents manually.
How do I access the google drive functionality in CreateAI Builder?
1. Go to your AI Project in CreateAI Builder.
2. Click on the Knowledge tab in the left-hand menu.
3. Select the Google Drive option (next to Files and URLs).
4. Click Add from Google Drive.
5. Sign in with your ASU Google account (ASURITE).
6. Select the files you’d like to import (max file size per file: 50MB).
7. Your files will now appear in your Knowledge Base and can be used for training, citations, referencing, or building new projects.
Screenshot of steps attached below.
Important note about accounts
Currently, the integration only works with your ASU Google account. Attempting to sign in with a personal Gmail (e.g., @gmail.com) will result in an **“Access blocked: org\_internal”** error. Please make sure your files are stored and shared under your ASU account to use them with Builder.
Are there any limitations
File size limits may apply (50MB per file).
You must have the right **sharing permissions** set in Google Drive (e.g., if the file is restricted, Builder won’t be able to access it).
Only supported file types can be processed.
Integration is limited to ASU accounts for now (personal Gmail is blocked).
No auto-sync (for now) 😣 If a file in Google Drive is updated, you’ll need to reupload it in the UI for changes to appear in CreateAI Builder. Auto sync feature coming soon though.
Keep Reading
Breakdown of RAG Model Parameters, Settings and Their Impact
Kofi Wood
Retrieval-Augmented Generation (RAG) is an advanced approach in natural language processing that integrates information retrieval and generative language modeling. Unlike traditional language models that generate responses solely based on their pre-trained knowledge, RAG combines retrieval mechanisms with generative models to enhance the relevance and accuracy of its responses. This hybrid framework works by first retrieving relevant documents or information from a predefined knowledge base (e.g., databases, documents, or PDFs) and then using a generative model (such as a transformer-based model) to synthesize a response that incorporates the retrieved context.