Category/Tag: Machine Learning

Using Kokoro-82M to Convert a PDF to an Audiobook

Using Kokoro-82M to Convert a PDF to an Audiobook

In previous posts, we've discussed the usefulness of IBM's Docling for use in AI projects. Today, we want to dive deeper and showcase how you can use Docling with a nifty light-weight resource called Kokoro-82M to convert PDFs into complete AI-voiced Audiobooks.

AI Karl Popper – A RAG Chatbot

AI Karl Popper – A RAG Chatbot

In a previous post, we introduced Gradio, a great way to quickly build a UI for your AI projects. In that post we built a Dungeon Master chatbot. Now we’re ready to pull together everything we’ve learned and create a chatbot can emulate a real person, in this case philosopher, Karl Popper.

Hugging Face Spaces

Hugging Face Spaces

We’ve talked a lot about Hugging Face’s ecosystem in past post. One thing I’ve not touched on yet—that deserves some attention—is Hugging Face’s “Spaces.” Hugging Face Spaces is a free (cpu) or paid

Google Gemini with Gradio

Google Gemini with Gradio

Gradio is an amazing little library that allows you to quickly build a UI for AI Chatbots or other AI related projects. Better yet, you can then either run that chatbot locally or share it out on the web with Gradio hosting it for you. In today's article, we'll be having a quick look at Gradio and showcasing a neat way to use it with Google's Gemini.

Pulling It All Together: Docling for Loading PDFs

Pulling It All Together: Docling for Loading PDFs

Over the course of the last few weeks, we have been releasing a number of articles on Docling and how it can be used to improve your AI tools. In this article, we will be putting together everything we have learned so far so you can start converting and loading your PDFs into machine readable text.

Finding Paragraphs in PDFs - Using IBM’s Docling

Finding Paragraphs in PDFs - Using IBM’s Docling

IBM's Docling is a fantastic tool and resource that allows for easier conversions of PDF documents into machine-readable text. However, sometimes it can fall short when it comes to grouping text into paragraphs. In this article, we'll discuss how we can better improve our text conversion process so we can keep our paragraphs together.

IBM’s Docling for Superior Text Loading from PDFs

IBM’s Docling for Superior Text Loading from PDFs

Converting documents such as PDFs into clean and accurate machine-readable text can sometimes be more difficult than expected. This is why we use IBM's Docling to help us with our PDF to Markdown conversions. In today's article, we'll be talking a bit more about how to use Docling and why it should always be a consideration for your AI toolbox.

Using NLTK to Improve RAG (Retrieval Augmented Generation) Text Quality

Using NLTK to Improve RAG (Retrieval Augmented Generation) Text Quality

Last week, we discussed Docling and how it can easily allow you to turn your PDFs and other documents into machine-readable text. Sometimes, this conversion can result in errors like broken lines or misplaced hyphens. In today's tutorial, Bruce Nielson will walk us through NLTK, a library and tool that will help us automatically fix those mistakes.

Docling for PDF to Markdown Conversion

Docling for PDF to Markdown Conversion

Docling is IBM's open-source library for reading popular document formats (such as PDF) and exporting them into Markdown. In this article, we'll be looking at how to use it and how it performs compared to other options.

Llama.cpp for Large Language Models

Llama.cpp for Large Language Models

In a previous article, our in-house expert on AI, Bruce Nielson, explained how to set up a LLM using Ollama. This week, we'll be going over Llama.cpp, a similar system to Ollama but running on C++ and using some very efficient techniques to improve performance.