Don't limit your RAG knowledge base to text only | by Marcos Santiago | August, 2024

Steal this plug-n-play Python script to easily implement images into your chatbot's knowledge base

When creating a knowledge base, a common challenge is converting everything into plain text. This can be limiting when working with multimedia sources such as slides, PDFs, images, and more.

So how can we make proper use of data that is not in plain text?

Don't have a Medium membership? I can help you: use this Free article linkPlease consider leaving highlights, applause, continueand comments

Thanks to recent advances in artificial intelligence, it’s now easier and cheaper than ever. By using large language models (LLMs) with vision capabilities, we can transcribe thousands of images, not only capturing the text, but also understanding how the content is related. These models can even describe visual objects within an image if needed, offering a much richer and more detailed transcription than OCR could ever offer.

We will start with these three simple steps:

1. Collecting data:Gather the images you plan to use, making sure they are well organized and not overloaded with information.
2. Upload data:Set up an AWS S3 bucket to store your images, ensuring that your cloud-based ai model can…