Achyuth Kumar's video 🐩

Hi this is Achit Kumar.

This is my submission for round two which is book cover validation automation.

So I built this automation in N8N for book cover validation.

So I used 8 n as the orchestration layer for this automation and I have used the other tools like Google Drive Convert Hub for converting PDF to png.

I've used Airtable for storing the data and Gmail for sending emails and vision models Gemini and GPT4O.

So let me show you how the table tables look.

So I've created two tables.

One is the COVID reviews which includes all the records that the automation creates.

So it includes ISBN, book title, author name, status, all the scores percentages.

It's a pass or fail.

we have image quality, critical issues, summary of the issues here and corrections suggested by our automation.

It also has the date and the second table I created is automatic author directory.

I've created a sample for our tests.

It includes ISBN, author name and email id.

it is useful for the automation to pick up the email and send the emails to the authors.

to show the demo I'm taking these two book covers.

On the left side we have Benny James SDB which is example for a good cover.

On the right side we have Ogil Jain which is example for bad cover.

It has critical issues in the bottom.

So let's see how it works.

So I will upload these two images to Google Drive this folder and once I upload will this automation will process it.

So let me just upload these two.

So I uploaded them this will trigger the automation.

You can see that it is running right now.

Once it completes the run I will receive the emails automatically.

So looks like I already got one.

So this is the approved example for approved email it will look like this.

So your book cover has been approved.

there's nothing more to do and this is the template I created for pass.

let's look at the review needed.

So this is the example for review needed which is Ojal Jain's cover.

So here it includes everything what issued issues are detected, how to fix the issues and it also has pre submission deadline.

So here if you can see it is flagging the critical error which is the batch overlap.

Yeah this is the example for review needed email.

So let me quickly show you the how each node is working here.

So this Google Drive trigger is working whenever a new file is uploaded to that folder and it will pick up all the new files and process each one through this loop.

And we are here, we are extracting the ISBN and metadata of that file.

We download the file next and then we check whether the file is a PDF or PDF png.

If it is an image, we directly process it for vision processing.

But if it's a png, we convert the file first using converthub API and then process the file using our vision models, which is Gemini and GPT4O.

So once it's processed, it will parse the output.

Then we look up the email ID in the authors table based on the ISBN.

And then we create a validation record with all the output we got from this vision model.

And then we check if it is, pass or review needed.

So if it is a pass, we send this template.

If it is review needed, we send this template.

So that's how it's working right now.

and if I had more time to improve this, maybe I would, add a second validation check using OpenCV, and also maybe provide the exact markings, where exactly the error has happened, using, markers automatically.

And then maybe a review dashboard, to manage all the flagged covers.

Yeah.

Thank you.