Category/Tag: Machine Learning

Hybrid Search for Retrieval Augmented Generation

Hybrid Search for Retrieval Augmented Generation

In a previous blog post, we introduced our "Book Search Archive," which we have been using to experiment with using AI to search and extrapolate information. In today's blog post with Bruce Nielson, we'll be discussing "hybrid searches" to better improve upon our AI model and showcase the power of an AI-driven search.


Our Open-Source AI Stack: The Book Search Archive

Our Open-Source AI Stack: The Book Search Archive

For much of this year, we have been publishing blog articles that showcase how to create an AI powered search and query engine that can extrapolate information or answers to questions directly from archived books, specifically the Federalist Papers. In today's article, we have a quick re-cap of what we have so far accomplished.


An AI Tech Support Agent

An AI Tech Support Agent

Large companies love to talk about AI and how they are trying to incorporate it into their business model. However, especially for smaller companies, some business owners may assume that there just isn't any real use for AI in their industry, causing them to feel like they are falling behind everyone else in modernizing their company. In today's article by Bruce Nielson, we'll dive into one real-world example of how any business can take advantage of AI: An AI Tech Support Agent.


Haystack Streaming Text Generation

Haystack Streaming Text Generation

In this post, we're going to give our sample Retrieval Augmented Generation (RAG) Pipeline a bit of a makeover. Specifically, we’ll tweak it to “stream” results from multiple nodes, letting us show off what we’ve got as soon as it rolls in—no more waiting for everything to pile up at the end.


Avoiding Text Truncations in RAG

Avoiding Text Truncations in RAG

In our series of articles on AI, we have been exploring cost-effective ways of building AI and ML models ourselves, helping anyone get into AI right now. However, a downside of the sentence embedder model we have been using is a tendency for text to get truncated, reducing overall performance of the RAG system. In today's article, we will explore how to overcome that problem.


Using Hugging Face API Generators for RAG

Using Hugging Face API Generators for RAG

Want to take advantage of AI and ML, but don't want to break the bank while doing so? Mindfire TECH is eager to help you and your business enter the future. Part of that includes our ongoing free series of tutorials and demos showcasing how you can get started with AI and ML right now. In this one, join Bruce Nielson as he explored how to use Hugging Face Generators for RAG.


Google AI Integration with Haystack

Google AI Integration with Haystack

AI and LLMs like ChatGPT can be quite expensive, even when you are paying a small amount per token it can still add up to big dollars very quickly. Mindfire TECH is committed to providing cost efficient Artificial Intelligence solutions to our customers, and in today’s blog we’ll explore one of the ways to get into AI without breaking the bank. The solution: Google Gemini.


Retrieval Augmented Generation with Haystack and pgvector - Part 2

Retrieval Augmented Generation with Haystack and pgvector - Part 2

Continuing on from last week's article on Retrieval Augmented Generation (RAG for short), Bruce Nielson continues to expand on his series of AI and ML articles with a Part 2 on RAG. If you're interested in learning the ins and outs of how AI works, look no further than Bruce's ongoing series of tutorials and demos.


Retrieval Augmented Generation with Haystack and pgvector

Retrieval Augmented Generation with Haystack and pgvector

Interested in learning more about how ML actually works? Look no further than our continuing series of tutorials and demos on ML and AI, including this blog post by Bruce Nielson, where he continues breaking down how Retrieval Augmented Generation (RAG) works with Haystack and pgvector.


Getting Started with Stable Diffusion: A Beginner's Guide

Getting Started with Stable Diffusion: A Beginner's Guide

Most people who know about AI have heard of Stable Diffusion, one of the leading AI models in text-to-image generation. In today's article our in-house expert on ML and AI, Bruce Nielson, will walk you through the steps of setting up a working version of Stable Diffusion right on your own laptop.