Recent Issues of The Tech Toolbox
Introducing PydanticAI: A Cleaner Way to Build AI Agents
Stephen Collins
•
Dec 7, 2024
Explore PydanticAI, a type-safe Python framework that simplifies building production-grade AI agents. Learn how it brings str...
Read More
Unlocking Insights: Using Multimodal LLMs to Parse and Extract Structured Data from Complex PDFs
Stephen Collins
•
Nov 29, 2024
This newsletter explores how to extract structured data from complex PDFs containing text, images, charts, and tables. Discov...
Read More
From Simple Scripts to Scalable AI: Building Smarter Data Pipelines
Stephen Collins
•
Nov 23, 2024
In this edition, I share lessons learned from transitioning from simple scripts to scalable AI data pipelines. Explore how a ...
Read More
The Real Cost of Hosted LLM Applications: Time, Money, and Sanity
Stephen Collins
•
Nov 16, 2024
In this edition, we dive into the hidden challenges of building applications with hosted LLMs, from latency and cost overruns...
Read More
Tracking AI-Driven Processes with Activity Logs and LLMs
Stephen Collins
•
Nov 2, 2024
In this edition, we explore how activity logs enhance transparency, accountability, and troubleshooting in AI-powered systems...
Read More
How to Optimize LLM Calls for Cost-effective SaaS Operations
Stephen Collins
•
Oct 26, 2024
In this edition, I dive into strategies for optimizing LLM API calls to keep SaaS operations lean and sustainable. Discover p...
Read More
Navigating the Landscape of Multi-Agent Systems: Distributed vs. In-Process Approaches
Stephen Collins
•
Oct 19, 2024
In this edition, I explore the dynamics of multi-agent systems, comparing distributed applications to in-process approaches l...
Read More
Maximizing LLM Efficiency with JSON Schemas
Stephen Collins
•
Oct 12, 2024
In this edition, we explore how JSON schemas can enhance the efficiency of data pipelines for large language models (LLMs). L...
Read More
Unlocking Hidden Performance in Vector Search: Practical Tips
Stephen Collins
•
Oct 5, 2024
This edition shares actionable tips to optimize the performance of your vector search setup. From efficient indexing and batc...
Read More
SQLite for GraphRAG: Lightweight Graph Database for Document Retrieval
Stephen Collins
•
Sep 28, 2024
This edition explores the use of SQLite as a graph database for small-scale GraphRAG applications. With its simplicity, flexi...
Read More
Contextual Retrieval: Elevating AI with Context-Aware Information Retrieval
Stephen Collins
•
Sep 21, 2024
This edition covers Anthropic’s Contextual Retrieval, a breakthrough in Retrieval-Augmented Generation (RAG) that leverages c...
Read More
MemoRAG: A Memory-Enhanced Approach to Next-Gen RAG
Stephen Collins
•
Sep 14, 2024
This edition discusses MemoRAG, a novel Retrieval-Augmented Generation (RAG) framework that leverages long-term memory to enh...
Read More
Using Graph Databases to Implement GraphRAG
Stephen Collins
•
Sep 7, 2024
This edition explores how to leverage graph databases like Neo4j to implement GraphRAG for query-focused summarization tasks....
Read More
Comparing Multimodal LLM Models - Which One Fits Your Use Case?
Stephen Collins
•
Aug 31, 2024
In this edition, I'm diving into the world of multimodal LLMs, comparing leading models like CLIP, DALL-E 3, VILT, and Gemini...
Read More
The Future of Vector Databases - What's Next After Milvus, Chroma, and Pinecone?
Stephen Collins
•
Aug 24, 2024
In this edition, I'm exploring the next wave of innovation in vector databases, beyond the current leaders like Milvus, Chrom...
Read More
The Rise of Multimodal LLMs - What You Need to Know
Stephen Collins
•
Aug 17, 2024
In this edition, I'm diving into the evolution and significance of multimodal large language models (LLMs). These models are ...
Read More
Why Less is More in Software Architecture
Stephen Collins
•
Aug 10, 2024
In this edition, I'm exploring the critical importance of simplicity in software architecture. Simpler designs are not just e...
Read More
Introducing Retrieval-Augmented Language Models (RALMs)
Stephen Collins
•
Aug 3, 2024
In this newsletter, we explore the innovative concept of Retrieval-Augmented Language Models (RALMs). These models integrate ...
Read More
Breaking Boundaries with Mistral Large 2
Stephen Collins
•
Jul 27, 2024
The release of Mistral Large 2 by Mistral AI marks a significant advancement in AI capabilities, promising enhanced performan...
Read More
Introducing GPT-4o Mini - The Race to Cost-Efficient AI
Stephen Collins
•
Jul 20, 2024
As AI models become increasingly powerful, there's a notable trend towards making these advanced technologies more affordable...
Read More
Developing an AI-Driven SaaS Roadmap for Startups
Stephen Collins
•
Jul 13, 2024
In today's competitive market, startups must leverage foundational AI models to create value and stay ahead. This newsletter ...
Read More
Designing Event-Driven Systems for LLMs
Stephen Collins
•
Jul 6, 2024
Managing the asynchronous nature of large language models (LLMs) is crucial for efficient AI systems. This newsletter explore...
Read More
Fine-Tuning Your AI - The Role of Performance Monitoring in Voting Systems
Stephen Collins
•
Jun 29, 2024
Enhancing the reliability and accuracy of AI applications requires more than just integrating multiple models. This newslette...
Read More
The Coming AI Boom - How You Can Benefit from the Explosion of AI Adoption
Stephen Collins
•
Jun 22, 2024
We are on the verge of a massive shift in the economy driven by the rapid adoption of artificial intelligence (AI). This news...
Read More
LLMs Perform Better When You Ask Them to Do Less
Stephen Collins
•
Jun 15, 2024
Discover the secret to enhancing the performance of Large Language Models (LLMs) by keeping requests simple and focused. This...
Read More
Enhancing AI System Reliability with Voting Mechanisms
Stephen Collins
•
Jun 8, 2024
Learn how implementing voting systems can significantly enhance the reliability of AI systems. This newsletter discusses the ...
Read More
xLSTM - The Next Leap in AI Model Architecture
Stephen Collins
•
Jun 1, 2024
Discover the exciting advancements in machine learning with the introduction of the xLSTM model. This newsletter explores how...
Read More
The AI Displacement Dilemma - What Lies Ahead
Stephen Collins
•
May 25, 2024
Dive into the profound implications of AI on the job market, as highlighted in the thought-provoking video 'About 50% Of Jobs...
Read More
Improving Summarization Tasks with GraphRAG and RaptorRAG
Stephen Collins
•
May 18, 2024
Explore and compare GraphRAG and RaptorRAG, two innovative approaches for improving query-focused summarization, enhancing ou...
Read More
Introducing GraphRAG - Transforming Data Analysis with LLMs
Stephen Collins
•
May 11, 2024
Explore GraphRAG, a transformative technology developed by Microsoft Research to enhance LLM capabilities for sophisticated d...
Read More
The Artistic Dimensions of Software Architecture
Stephen Collins
•
May 4, 2024
In this issue, I explain why software architecture should be viewed as an art just as much as a science. Discover how blendin...
Read More
Boosting Contextual Relevance in LLMs with LlamaIndex
Stephen Collins
•
Apr 27, 2024
In this issue, I explore LlamaIndex, a framework that dramatically improves the integration of specific, private data into la...
Read More
Unleashing the Potential of Hugging Face's AutoModel in AI Development
Stephen Collins
•
Apr 20, 2024
In this issue, I discuss the convenient yet powerful capabilities of Hugging Face's AutoModel class, one of several "AutoClas...
Read More
Milvus vs Pinecone: A Comparison of Vector Databases
Stephen Collins
•
Apr 13, 2024
This issue explores the specialized world of vector databases, focusing on a comparative analysis between Pinecone and Milvus...
Read More
Embracing the Role of AI Overseers in Modern Engineering
Stephen Collins
•
Apr 12, 2024
This edition considers the emergent role of 'AI Overseers', pivotal in harnessing AI for superior engineering achievements. I...
Read More
The Unyielding Developer - Persistence, Learning, and Communication
Stephen Collins
•
Mar 30, 2024
In this issue, I explore the pivotal role of stubbornness, the insatiable appetite for learning, and the paramount importance...
Read More
Managing the AI Hype Cycle
Stephen Collins
•
Mar 23, 2024
Navigate the swirling hype surrounding artificial intelligence breakthroughs. This issue examines the financial incentives dr...
Read More
Exploring Multi-Modal LLMs - Beyond Text
Stephen Collins
•
Mar 14, 2024
Dive into the intricate workings of Multi-Modal Large Language Models, the advanced AI systems capable of understanding and g...
Read More
Decoding LLMs - The Enterprise Need for Mechanistic Interpretability
Stephen Collins
•
Mar 8, 2024
Explore the pivotal role of mechanistic interpretability in merging large language models with enterprise software, advancing...
Read More
Improving Content Discovery - A Look at Semantify's Approach
Stephen Collins
•
Mar 2, 2024
Dive into the transformative approach of using vector embeddings in recommender systems, spotlighting Semantify's innovative ...
Read More
Exploring Evolutionary Architecture in Software Development
Stephen Collins
•
Feb 24, 2024
In this issue, I discuss Evolutionary Architecture, a methodology to help with designing software applications. Explore how E...
Read More
Mastering Software Testing in LLM Development with Promptfoo
Stephen Collins
•
Feb 17, 2024
This issue introduces concepts in systematic software testing for LLM development with Promptfoo, a CLI tool designed for pre...
Read More
Cursor - Revolutionizing Code Editing with AI
Stephen Collins
•
Feb 10, 2024
This issue introduces Cursor, an innovative AI-powered code editor built on the foundation of Visual Studio Code. It enhances...
Read More
Database Security Showdown - SQLite vs. PostgreSQL
Stephen Collins
•
Feb 3, 2024
This issue covers security features of SQLite and PostgreSQL, providing a comparative analysis to help database administrator...
Read More
AI's Political Play - Understanding and Countering Misinformation
Stephen Collins
•
Jan 27, 2024
In this newsletter, I consider the intricate role of AI in political interference. I share my personal journey and insights i...
Read More
Exploring the Basics of Multi-Agent LLM Frameworks
Stephen Collins
•
Jan 20, 2024
In this issue, I explore the fascinating world of Multi-Agent Large Language Model (LLM) Frameworks, an advanced area in AI t...
Read More
The Importance of a Financial Safety Net in Tech
Stephen Collins
•
Jan 13, 2024
Amidst recent layoff news in the tech industry, this issue deviates slightly from AI topics to discuss the importance of buil...
Read More
Vector Databases Showdown: Milvus vs Chroma
Stephen Collins
•
Jan 6, 2024
This issue dives into the dynamic world of vector databases, presenting a detailed comparison between Milvus and Chroma, two ...
Read More
Navigating the AI-Assisted Coding Landscape with GitHub Copilot
Stephen Collins
•
Dec 30, 2023
Exploring the world of AI-assisted coding, this issue brings a firsthand review of GitHub Copilot, highlighting its strengths...
Read More
Mixtral 8x7B vs. ChatGPT - A Detailed Comparison
Stephen Collins
•
Dec 16, 2023
This issue explores an in-depth comparison between Mixtral 8x7B and ChatGPT, focusing on their operational costs, instruction...
Read More