The Problem: PDFs and Word Docs Are Binary Blobs

If you try to use the original workflow with PDF or DOCX files, you’ll end up with something like this in your database:

PK DciZ word/numbering.xmlí�[nã6 †WÐ= zOt±,;Æ8ƒ` )Z E�N @K´MD" R²"n¡ }k_»¶¤ÔÕ·±*y¢zRÿOŠ ùÿä¡ŽùÑ�!¿{ÿ …ƒ5•Š >3ì[Ë Pî‹€ñåÌøåÓãÍÄ ¨„ð€„‚ÓñB•ñþþ›w›)O£9•ºß@[p5�ü±J'xjšÊ_ш¨[ S BF$Ñ/åÒŒˆ|Jã *D1IØœ…,y1

Yikes! That’s raw binary data, not the text content that our RAG system needs. The AI can’t extract any meaningful information from this jumble.

The Solution: File Type Detection and Conversion

To fix this, I needed to add a few key improvements to the workflow:

1. Update the Set File ID node
2. Add a Switch node to detect file types
3. Implement ConvertAPI integration to transform PDFs/DOCXs to plain text
4. Use a Code node to ensure filenames have proper extensions

Here’s how I implemented each part:

1. Add mime_type to the Set File ID Node

First, I updated the Set File ID node to set the mime_type. This is used to drive the logic in the new Switch node below.

2. Detecting File Types with the Switch Node

Next, I added a Switch node after downloading the file from Google Drive. This node checks the MIME type (mime_type) of the file and routes it accordingly:

• application/pdf → PDF conversion path
• application/vnd.openxmlformats-officedocument.wordprocessingml.document → DOCX conversion path
• application/vnd.google-apps.document → Google Docs path (the original flow)

This routing ensures each file type gets handled appropriately. If you had more file types that you wanted to support, you could easily add them here.

3. Converting Files with ConvertAPI

For both PDF and DOCX paths, I integrated with ConvertAPI, a service that handles file conversions elegantly. You’ll need to:

1. Sign up for a free ConvertAPI account (you get 250 free conversions)
2. Copy your secret key from the dashboard
3. Add the ConvertAPI (HTTP Request) nodes as shown in my workflow
4. Configure your Credential for ConvertAPI with the secret from #2

For PDFs:

POST https://v2.convertapi.com/convert/pdf/to/txt

For DOCX:

POST https://v2.convertapi.com/convert/docx/to/txt

The beauty of this approach is that ConvertAPI handles all the complex conversion logic, including OCR for scanned PDFs if needed.

4. Adding File Extensions with a Code Node

I discovered a quirk: ConvertAPI expects files to have proper extensions in their filenames. Since my Google Docs file names did not include a file extension, I added a Code node with this simple JavaScript:

$input.item.binary.data.fileName = `${$input.item.binary.data.fileName}.${$input.item.binary.data.fileExtension}`; 
return $input.item;

This ensures the filename has an extension before we send it to ConvertAPI. Ideally, you’d check to see if a file extension exists before adding one, but I know my Google Docs did not include one.

The Complete Workflow

After these modifications, the workflow now does the following:

1. Detects when a file is created or updated in Google Drive
2. Identifies the file type
3. Converts PDFs and DOCX files to plain text
4. Extracts the text content
5. Stores it in Supabase with proper embeddings
6. Makes it available for the RAG AI agent to query

Check out the full workflow in the screenshot:

Why This Matters

Having your RAG system work with PDFs and Word documents is game-changing for several reasons:

• Most business knowledge is locked in these formats
• Legacy documents don’t need to be converted manually
• You can ingest reports, contracts, manuals, and more
• The system becomes practical for real-world use

Additional Considerations

While implementing this enhanced RAG workflow with PDF and DOCX support, here are some important factors to keep in mind:

Cost Considerations

• ConvertAPI Pricing: The free tier includes 250 conversions, which is perfect for testing and small implementations. Beyond that, pricing starts at $30/month for 1,000 conversions and scales up based on volume.
• OpenAI Costs: Remember that each document processed generates embedding costs. For large document collections, these can add up quickly. Consider batching updates or implementing selective processing.
• Storage Costs: As your document database grows, Supabase storage and database costs may increase. Monitor your usage to avoid unexpected bills.

Technical Limitations

• Complex Document Formatting: While this solution works well for text-focused documents, highly formatted content with tables, charts, or complex layouts may lose structural information during conversion.
• Image-Heavy PDFs: If your PDFs primarily contain images or scanned text, ConvertAPI’s OCR capabilities will help, but may not be perfect. Consider testing with your specific documents.
• Large Files: Very large documents (over 25MB) might encounter timeout issues, and you may need to implement chunking strategies.
• Language Support: Non-English documents may have varying degrees of success depending on character sets and the OCR capabilities of ConvertAPI.

Security Considerations

• Data Privacy: This workflow sends document content to external services (ConvertAPI and OpenAI). Ensure this complies with your organization’s data policies.
• API Key Security: Store your ConvertAPI and OpenAI credentials securely. In n8n, use the credentials vault rather than hardcoding keys.
• Access Controls: Set appropriate permissions in Google Drive and Supabase to limit who can access the source documents and extracted content.
• Data Retention: Consider how long you need to keep both the original documents and their processed text. Implement a cleanup strategy for outdated material.

By addressing these considerations upfront, you’ll build a more robust, scalable, and secure document processing workflow that can handle real-world challenges.

Getting Started Yourself

If you want to implement this enhanced workflow:

1. You can download my modified workflow JSON from GitHub
2. Import it into your n8n instance
3. Set up your credentials for Google Drive, OpenAI, Supabase, and ConvertAPI
4. Configure the folder path in Google Drive where your documents live
5. Start adding files and chatting with your data!

If you’re new to n8n, I highly recommend using n8n Cloud for the easiest setup. Their free trial is perfect for testing, and you can upgrade as your needs grow.

I’d love to hear how you adapt this approach for your own needs! Have you found ways to handle other file types? Created interesting agent prompts? Drop me a comment below and let me know!

The post n8n RAG: Adding PDF & DOCX for Better Document Processing appeared first on Eric Martin.

• SimpleModal Contact Form (SMCF)
• SimpleModal Login
• WP-Paginate

It’s hard to believe that I released SMCF almost 7 years ago! In recent years, I have not been able to commit the time necessary for these plugins and I am glad that they will be going to a good home.

Happy Holidays!

The post WordPress Plugins Under New Ownership appeared first on Eric Martin.

This release addressed the removal of $.browser in jQuery 1.9 (deprecated since 1.3).

Changes in 1.4.4

• Removed $.browser calls due to removal in jQuery 1.9

If you have any questions regarding SimpleModal, I strongly suggest using stackoverflow. If you find any bugs, please report them on the issues page.

Thanks for using SimpleModal!

Links: Project Page | GitHub Page

The post SimpleModal 1.4.4 Released appeared first on Eric Martin.

I never created a post for the 1.4.2 release (back in December 2011), so the following is a summary of changes since 1.4.1:

Changes in 1.4.2

• Added a new ‘fixed’ option for fixed or absolute positioning
• Changed overlay to use the document dimensions instead of window
• Removed opera work-around for close() that was causing issues
• Added AMD support (thanks to https://github.com/jd-boyd)

Changes in 1.4.3

• Changed $.boxModel to $.support.boxModel (requires jQuery 1.3+)
• Fixed potential noConflict bug. Thanks to Erik Westra

If you have any questions regarding SimpleModal, I strongly suggest using stackoverflow. If you find any bugs, please report them on the issues page.

Thanks for using SimpleModal!

Links: Project Page | GitHub Page

The post SimpleModal 1.4.3 Released appeared first on Eric Martin.

I never created a post for the 1.4 release (back in August), so the following is a summary of changes since 1.3.5:

Changes in 1.4

• Changed the implementation of the autoResize, autoPosition, and focus options
• The default value for autoResize changed to true
• Added update() function
• Added “shortcut” functions for focus(), setContainerDimensions(), setPosition(), and update()
• Reworked the code in a number of functions
• Fixed Opera screen painting issues
• Updated jQuery requirement to 1.2.4
• Updated container to shrink/grow as window resizes
• Switched to Google compiler for minification

Changes in 1.4.1

• Resolved the container height issue in IE6 & IE7 with jQuery 1.4.3
• Fixed a bug where minWidth and minHeight were not being honored in certain cases

If you have any questions regarding SimpleModal, I strongly suggest using stackoverflow. If you find any bugs, please report them on the issues page.

Thanks for using SimpleModal!

Links: Project Page | jQuery Plugins Page

The post SimpleModal 1.4.1 Released appeared first on Eric Martin.

WP-Paginate is a simple and flexible pagination plugin which provides users with better navigation on your WordPress site. WP-Paginate supports pagination for both posts and comments.

Changes in 1.2:

• Added RTL language support
• Fixed a comments pagination bug
• Changed language domain name from wp_paginate to wp-paginate (this will affect translation file names)

If you have any feedback, feel free to leave a comment here. If you have a question or issue, please post it in the WordPress support forum.

Links:

• Project Page
• WordPress Page (Download, FAQ and Installation details)

The post WP-Paginate 1.2 Released appeared first on Eric Martin.

I’ve been working off-and-on since the beginning of the 2010 on adding new features, such as user registration, password reset and an activity indicator. All of those features are included in 1.0 as well as the following:

• Added support for Peter’s Login Redirect plugin
• Added additional error handling
• Added Keyboard Shortcut option and feature (Ctrl+Alt+L)
• Removed the ‘Redirect after login?’ option
• Updated POT file (I18n/simplemodal-login.pot)
• Added plugin update logic
• Upgraded to SimpleModal 1.4
• Added additional screenshots
• Added filters for each form (login, register, password reset) output HTML to allow for customization

If you have any feedback, feel free to leave a comment here. If you have a question or issue, please post it in the WordPress support forum.

Links:

• Project Page
• WordPress Page (Download, FAQ and Installation details)

The post SimpleModal Login 1.0 Released appeared first on Eric Martin.

The transient option, which was added in 1.3.4, was renamed to modal because transient is a reserved word and was causing issues.

Also, the reference to $.support.boxModal was changed back to $.boxModal to remain compatible with older versions of jQuery.

I’ve also been working on a new site for SimpleModal. It’s not ready yet, but I’ve included a preview below:

Also, if you have any feedback or input on what you’d like to see on the new site, please let me know. I want to make it as useful as possible.

If you have any questions regarding SimpleModal, I strongly suggest using stackoverflow. If you find any bugs, please report them on the issues page.

Thanks for using SimpleModal!

Links: Project Page | jQuery Plugins Page

The post SimpleModal 1.3.5 Released appeared first on Eric Martin.

A new option, transient, was added which allows you to disable the overlay, iframe, and certain events. This would allow the user to still interact with the page below the dialog.

Another container dimension fix was added to deal with Opera quirks. Lastly, a new internal placeholder was added to keep track of where the modal content came from (if it came from the DOM).

Complete list of features and changes since 1.3.3:

• Changed default values for minHeight and minWidth to null
• Added transient option which, if true, disables the overlay, iframe, and certain events, allowing the user to interace with the page below the dialog
• Changed $.boxModel to $.support.boxModel
• Fixed container dimension issues in Opera
• Added a placeholder element for modal content taken from the DOM
• Updated demo’s and added a new Flickr Badge Gallery demo

If you have any questions, I strongly suggest using stackoverflow. If you find any bugs, please report them on the issues page.

Thanks for using SimpleModal!

Links: Project Page | jQuery Plugins Page

The post SimpleModal 1.3.4 Released appeared first on Eric Martin.

My Review

I don’t usually buy technical books; I’m more of a hands-on learner and the books that I’ve purchased in the past just collect dust. It’s one of the reasons why I’m so impressed with jQuery Enlightenment. Besides being an eBook (and therefore can’t collect dust), Cody has structured the book in a way that makes it perfect to have as a learning tool as well as a reference.

You can read the book top-down or skim through the topics, find something you’re interested in, and get a detailed and easy to understand write-up on the subject. Cody takes the learning processes one step further by providing code examples, linked to JS BIN, that can be viewed and run in your browser. For someone like me, the concrete examples and ability to play with the concepts, helps reinforce the topics covered.

Whether you are a new jQuery users, or a seasoned jQuery developer, jQuery Enlightenment won’t disappoint!

jQuery 1.4

The current version of jQuery Enlightenment was written for jQuery 1.3.2. I spoke to Cody about the recent release of jQuery 1.4 and his plans for an update. He is working on a new version of the book that he estimates will have twice the content (or more) and is tentatively priced at $30. Lastly, he plans to offer a limited-time discount on the update for existing jQuery Enlightenment owners. [Note from Cody: All of this information is subject to change]

Giveaway

As mentioned previously, I have 3 coupons available for free copies of jQuery Enlightenment. If you would like a chance to win, leave a comment below and on Wednesday (1/20) at 2pm PST, I will randomly select 3 people.

Winners!

The random number generator has spoken and the following people have won a coupon for a free copy of jQuery Enlightenment:

• Jim
• Sam De La Garza
• Bjorn van der Neut

I’ll be sending the coupons codes out shortly. Congratulations, I know you’ll enjoy the book.

The post jQuery Enlightenment Review & Giveaway appeared first on Eric Martin.