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 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.
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.
China's new AI, DeepSeek R1, is causing all sorts of upset in the AI market right now, and so we've decided to break down exactly what it is, why it's causing such an uproar, and how you can try it out for yourself.
Interested in getting your own LLM up and running? Ollama, an alternative to software like LM Studio, is a relatively easy and simple tool to get started with. In this article, we'll be going through how to get it set up on Windows.
It's important to ensure that your AI is presenting the absolute best results from your searches with it. In today's AI/ML tutorial by Bruce Nielson, we'll be looking at something called a Reranker, which will allow us to turn good results into best results.
In two previous posts, we talked about how to install Neo4j Graph Database for use with the Book Search Archive, our sample project using the Mindfire Technology open-source AI stack. In this post we'll cover the code necessary to use Neo4j as a document store for Retrieval Augmented Generation (RAG).
Last time in our series of AI tutorials, we covered how to install Neo4J (graph database). For the Mindfire stack, we’re aiming to stick with open-source software, and Neo4j Server Community Edition fits the bill. However, there’s also a free Enterprise edition available (with some limitations) if you use Neo4J Desktop, which we'll be looking at today.
In previous posts, we learned how to install PosgreSQL and then how to install pgvector (a vector search extension for PostgreSQL.) The Book Search Archive (our toy app to show off Mindfire’s growing low-cost open-source AI stack) currently utilizes a PostgreSQL database with vectors handled by pgvector to do our semantic searches using a HNSW index built-into pgvector. In this post, we'll be looking at how to use Neo4J, a graph database with vector support, to do RAG.
It can often be helpful to use git as a way to compare text, especially when using git to compare versions of output, so you can then use git-filter-repo to remove that part of the git history. However, it isn't the easiest tool to figure out. Suppose you need to remove a file from a GitHub repo, how would you do that? If you just remove the file and check it in the older commits still contain that file, which means it is still part of the overall repo, what to do? In today's blog, we'll explore how to remove a file from your GitHub repo history.
