Generating Keywords Automatically With llama-cli and Phi-3

Published
Author
Dr. Phil Winder
CEO

Automate keyword generation for your Hugo blog with llama-cli and Phi-3. Learn how Dr. Phil Winder used local language models to generate SEO-friendly keywords for Winder.AI, enhancing related content linking and site performance. Get the complete script and code explanation for effortless keyword management.

Read more

Build a Voice-Based Chatbot with OpenAI, Vocode, and ElevenLabs

Published
Author
Natalia Kuzminykh
Associate Data Science Content Editor

Why might we want to make an LLM talk? The concept of having a human-like conversation with an advanced AI model is an interesting idea that has many practical applications. Voice-based models are transforming how we interact with technology, making interactions more natural and intuitive. By enabling AI to talk, we open the door to numerous practical applications, from accessibility to enhanced human-machine interactions. This guide explores how to create a voice-based chatbot using OpenAI, Vocode and ElevenLabs.

Read more

LLM Architecture: RAG Implementation and Design Patterns

Published
Author
Dr. Phil Winder
CEO

This presentation investigates several common production-ready architectures for RAG and discusses the pros and cons of each. At the end of this talk you will be able to help design RAG augmented LLM architectures that best fit your use case.

Read more

Exploring Small Language Models

Published
Author
Natalia Kuzminykh
Associate Data Science Content Editor

Large language models (LLMs) are powerful but demand significant resources, making them less ideal for smaller setups. Small language models (SLMs) are a practical, resource-efficient alternative, offering quicker deployment and easier maintenance. This article discusses the benefits and applications of SLMs, focusing on their efficiency, speed, robustness, and security in contexts where LLMs are not feasible.

Read more

Big Data in LLMs with Retrieval-Augmented Generation (RAG)

Published
Author
Natalia Kuzminykh
Associate Data Science Content Editor

Retrieval-Augmented Generation (RAG) improves Language Large Models (LLMs) by integrating external data through indexing, retrieval, and generation steps. This method allows LLMs to access up-to-date information and specific details, enhancing their applicability across various domains by providing more accurate, relevant responses and enabling real-time updates and domain-specific customization.

Read more

LLM Prompt Best Practices For Large Context Windows

Published
Author
Natalia Kuzminykh
Associate Data Science Content Editor

This article delves into the nuances of using large language models (LLMs) with large context windows, highlighting the benefits and challenges they present, from enhancing coherence and relevance to demanding more computational resources. Learn practical strategies for prompt design, maintaining narrative coherence, and utilizing attention mechanisms effectively.

Read more

Calculating LLM Token Counts: A Practical Guide

Published
Author
Natalia Kuzminykh
Associate Data Science Content Editor

This article discusses the concept of token counts in large language models (LLMs) and their impact. Tokens are fragments of language used for text processing, representing words, parts of words, or punctuation marks. Code walkthroughs demonstrate how to calculate token counts and examples provide insight.

Read more

The Problem of Big Data in Small Context Windows (Part 2)

Published
Author
Dr. Phil Winder
CEO

An introduction to the challenge of fitting big data into the context windows of LLMs. In this second installment, discover the key strategies involved to improve your use of the context window. Subsequent articles will provide more examples.

Read more

ChatGPT from Scratch: How to Train an Enterprise AI Assistant

Published
Author
Dr. Phil Winder
CEO

This is a video of a presentation investigating how large language models are built and how to use them, inspired by our large language model consulting work. First presented at GOTO Copenhagen in 2023, the video investigates the history, the technology, and the use of large language models. The demo at the end is borderline cringe, but it’s a fun and demonstrates how you would fine-tune a language model on your proprietary data.

Read more
}