Skillenai
Introduction: Why Fine-Tune Pretrained Models? In the realm of Natural Language Processing (NLP), Large Language Models (LLMs) like GPT-3, BERT, and LLaMA have revolutionized the way machines understand and generate human language. However, while these models are trained on vast datasets, they might not always align perfectly with specific tasks or domains. This is where […]
How machines learn to speak our language one token at a time. Imagine you’re trying to learn a new language say, Japanese. On your first day, you’re handed a paragraph in kanji. No spaces. No familiar letters. Just symbols. How do you even begin? That’s exactly how computers feel when we throw raw text at […]
Diffusion models have become the dominant method of image generation in the last few years. But what are they? And how do they work? In this article, I will explain this intuitively and with some mathematics. This does require some mathematical and machine learning background, but I try here to abstract the complexity as much […]
🔊 “What if your voice assistant could truly understand and converse, not just respond?” In the summer of 2023, I yelled at my computer: “Play my favorite song!” Instead, it read my calendar out loud. Frustrating, right? That mishap planted the seed: I needed a voice agent that truly listens and replies on my terms. […]
Anthropic is redefining Retrieval-Augmented Generation (RAG) systems by addressing one of their most persistent limitations: lack of context. Traditional RAG pipelines rely on semantic similarity and keyword matching to retrieve relevant information chunks, but they often miss critical details hidden in surrounding content. Anthropic’s new approach—built on contextual embeddings and chunk-aware prompting—improves precision, reduces retrieval […]
A concise, personal comparison of key LLM architectures developed over the past few years. This document reflects my individual understanding and curiosity-driven research from the year 2017 to February 2025. This is by no means an exhaustive list, and many other excellent models exist in the field. 🎯 List of LLMs Covered (2017–2025) Transformer, BERT, […]
In the AI Agents world of Retrieval-Augmented Generation (Agentic-RAG), one challenge that persists is how Agents chunk our source documents to optimize response accuracy and relevance. This blog series dives into how different chunking strategies — Fixed, Semantic, Agentic, and Recursive Chunking— impact the performance of Agentic RAG systems. Using Agno for creating agent and orchestration and […]
Burr – a stateful AI decision engine that allows developers to build structured, interactive AI workflows efficiently. In this article, we will: ✅ Explore Burr’s stateful AI workflow✅ Build an AI-powered chatbot using Burr✅ Deploy the chatbot with structured transitions and state updates✅ Compare Burr with other AI orchestration tools By the end, you’ll have […]
Building AI applications that truly deliver has been my obsession lately, and I’ve finally cracked something worth sharing. By creating a Kafka-MCP server and connecting it with our existing Qdrant-MCP server, we’ve transformed how our team handles communication and data retrieval. The real magic happened when we linked this setup to Claude for Desktop — suddenly our […]
Experience the latest Google open-source model on your laptop with Ollama, Docker, Open WebUI, and GPU acceleration for optimal performance. In this tutorial, we will learn to run Gemma 3 locally using Open WebUI, a user-friendly interface that simplifies deploying large language models on personal hardware. Open WebUI, alongside tools like Ollama, makes it possible […]