Introduction: Retrieval Augmented Generation (RAG) has become the standard pattern for grounding LLM responses in factual, up-to-date information. But basic RAG—retrieve chunks, stuff into prompt, generate—often falls short in production. Queries get misunderstood, irrelevant chunks pollute context, and answers lack coherence. This guide covers advanced RAG patterns that address these challenges: query transformation to improve […]
Read more →Author: Nithin Mohan TK
Hello Namaste! 👋🏻
I'm an accomplished Enterprise Solution Architect & Engineering Leader with 20+ years of progressive experience architecting, building, and scaling transformative enterprise solutions.
⚜️ Solution Architect / AI & Cloud 📌 Galway, Ireland
Advanced RAG Patterns: Query Rewriting and Self-Reflective Retrieval (Part 2 of 2)
Introduction: Basic RAG retrieves documents and stuffs them into context. Advanced RAG transforms retrieval into a sophisticated pipeline that dramatically improves answer quality. This guide covers the techniques that separate production RAG systems from prototypes: query rewriting to improve retrieval, hybrid search combining dense and sparse methods, cross-encoder reranking for precision, contextual compression to fit […]
Read more →Retrieval Evaluation Metrics: Measuring What Matters in Search and RAG Systems
Introduction: Retrieval evaluation is the foundation of building effective RAG systems and search applications. Without proper metrics, you’re flying blind—unable to tell if your retrieval improvements actually help or hurt end-user experience. This guide covers the essential metrics for evaluating retrieval systems: precision and recall at various cutoffs, Mean Reciprocal Rank (MRR), Normalized Discounted Cumulative […]
Read more →Retrieval Augmented Fine-Tuning (RAFT): Training LLMs to Excel at RAG Tasks
Introduction: Retrieval Augmented Fine-Tuning (RAFT) represents a powerful approach to improving LLM performance on domain-specific tasks by combining the benefits of fine-tuning with retrieval-augmented generation. Traditional RAG systems retrieve relevant documents at inference time and include them in the prompt, but the base model wasn’t trained to effectively use retrieved context. RAFT addresses this by […]
Read more →Large Language Models Deep Dive: Understanding the Engines Behind Modern AI
Go beyond the basics and understand how LLMs actually work. Master prompting techniques, compare models, and learn cost optimization strategies for production use.
Read more →Event-Driven Architecture on GCP: Mastering Cloud Pub/Sub for Real-Time Systems
Google Cloud Pub/Sub provides the foundation for event-driven architectures at any scale, offering globally distributed messaging with exactly-once delivery semantics and sub-second latency. This comprehensive guide explores Pub/Sub’s enterprise capabilities. Cloud Pub/Sub Architecture Overview Pub/Sub Architecture: Topics, Subscriptions, and Delivery Guarantees Pub/Sub implements a publish-subscribe pattern where publishers send messages to topics and subscribers receive […]
Read more →