Designing intelligent systems, one layer at a time. ~ Nithin Mohan T K
The moment I truly understood tokenization was not when I read about it in a textbook, but when I watched a production NLP pipeline fail catastrophically because of an edge case the tokenizer could not handle. After two decades of building enterprise systems, I have learned that tokenization—the seemingly simple act of breaking text into […]
Read more →Introduction: Function calling transforms LLMs from text generators into action-taking agents. Instead of just describing what to do, the model can actually do it—query databases, call APIs, execute code, and interact with external systems. OpenAI’s function calling (now called “tools”) and similar features from Anthropic and others let you define available functions, and the model […]
Read more →Introduction: LLM applications face unique security challenges—prompt injection, data leakage, jailbreaking, and harmful content generation. Traditional security measures don’t address these AI-specific threats. This guide covers defensive techniques for production LLM systems: input sanitization, prompt injection detection, output filtering, rate limiting, content moderation, and audit logging. These patterns help you build LLM applications that are […]
Read more →Introduction: Retrieval-Augmented Generation (RAG) has become the go-to architecture for building LLM applications that need access to private or current information. By retrieving relevant documents and including them in the prompt, RAG grounds LLM responses in factual content, reducing hallucinations and enabling knowledge that wasn’t in the training data. But naive RAG implementations often disappoint—the […]
Read more →
The first time I watched a generative model produce coherent text from a simple prompt, I knew we had crossed a threshold that would reshape how we build software. After two decades of working with various AI and ML systems, from rule-based expert systems to deep learning pipelines, I can say with confidence that generative […]
Read more →Introduction: Embeddings are the foundation of semantic search, RAG systems, and similarity-based applications. Choosing the right embedding model and strategy significantly impacts retrieval quality, latency, and cost. Different models excel at different tasks—some optimize for semantic similarity, others for retrieval, and some for specific domains. This guide covers practical embedding strategies: model selection based on […]
Read more →