C4: Container, Code, Cloud & Context
Designing intelligent systems, one layer at a time. ~ Nithin Mohan T K
After two decades of building data systems, I’ve watched Natural Language Processing evolve from a research curiosity into an indispensable tool for extracting value from the vast ocean of unstructured text that enterprises generate daily. The convergence of transformer architectures, cloud-scale computing, and mature NLP libraries has fundamentally changed how we approach data analytics, enabling… Continue reading
Introduction: Observability is essential for production LLM applications—you need visibility into latency, token usage, costs, error rates, and output quality. Unlike traditional applications where you can rely on status codes and response times, LLM applications require tracking prompt versions, model behavior, and semantic quality metrics. This guide covers practical observability: distributed tracing for multi-step LLM… Continue reading
The Data Deluge at the Edge After two decades of building data systems, I’ve watched the IoT revolution transform from a buzzword into the backbone of modern enterprise operations. The convergence of connected devices and real-time analytics has created opportunities that seemed impossible just a few years ago. But it has also introduced architectural challenges… Continue reading
Introduction: Natural language to SQL is one of the most practical LLM applications. Business users can query databases without knowing SQL, analysts can explore data faster, and developers can prototype queries quickly. But naive implementations fail spectacularly—generating invalid SQL, hallucinating table names, or producing queries that return wrong results. This guide covers building robust text-to-SQL… Continue reading
Introduction: Knowledge graphs represent information as entities and relationships, enabling powerful reasoning and querying capabilities. LLMs excel at extracting structured knowledge from unstructured text—identifying entities, relationships, and attributes that can be stored in graph databases. This guide covers building knowledge graphs with LLMs: entity and relation extraction, graph schema design, populating Neo4j and other graph… Continue reading
Introduction: Ollama has revolutionized how developers run large language models locally. With a simple command-line interface and seamless hardware acceleration, you can have Llama 3.2, Mistral, or CodeLlama running on your laptop in minutes—no cloud API keys, no usage costs, complete privacy. Built on llama.cpp, Ollama abstracts away the complexity of model quantization, memory management,… Continue reading
Introduction: LLMs generate text, but applications need structured data. Parsing LLM output reliably is surprisingly tricky—models don’t always follow instructions, JSON can be malformed, and edge cases abound. This guide covers robust output parsing strategies: using JSON mode for guaranteed valid JSON, Pydantic for type-safe parsing, handling partial and streaming outputs, implementing retry logic for… Continue reading
Introduction: Conversational AI applications need to track state across turns—remembering what users said, what information has been collected, and where they are in multi-step workflows. Unlike simple Q&A, task-oriented conversations require slot filling, context tracking, and flow control. This guide covers practical state management patterns: conversation context objects, slot-based information extraction, finite state machines for… Continue reading
The journey from experimental machine learning models to production-grade systems represents one of the most challenging transitions in modern software engineering. After spending two decades building distributed systems and watching countless ML projects struggle to move beyond proof-of-concept, I’ve developed a deep appreciation for cloud-native approaches that treat machine learning infrastructure with the same rigor… Continue reading
Introduction: Documents are everywhere—PDFs, Word files, scanned images, spreadsheets. Extracting structured information from unstructured documents is one of the most valuable LLM applications. This guide covers building document processing pipelines: extracting text from various formats, chunking strategies for long documents, processing with LLMs for extraction and summarization, and handling edge cases like tables, images, and… Continue reading