Knowledge Base
Organized notes, references, and insights across topics I'm exploring.
LLM & RAG
Retrieval-Augmented Generation, vector databases, and grounded AI systems
RAG Fundamentals
Retrieval-Augmented Generation combines document retrieval with LLM generation for grounded answers.
Vector Embeddings & Similarity Search
How text embeddings work, choosing embedding models, and similarity metrics (cosine, dot product, L2).
Document Chunking Strategies
Fixed-size, sentence-level, semantic, and recursive chunking. Trade-offs between context preservation and retrieval precision.
Model Fine-Tuning
Parameter-efficient training, LoRA, dataset preparation
LoRA & QLoRA
Parameter-efficient fine-tuning with Low-Rank Adaptation. QLoRA adds 4-bit quantization for memory efficiency.
Training Data Preparation
Data cleaning, instruction formatting (Alpaca, ShareGPT), and quality filtering techniques.
Practical LLM Skills
Prompt engineering, tool use, and agent patterns
Prompt Engineering Patterns
Chain-of-thought, few-shot, system prompts, and structured output techniques.
Function Calling & Tool Use
Integrating LLMs with external tools via function calling (OpenAI, Anthropic) and agent frameworks.
Dev Notes
Framework patterns, language tips, and engineering notes
Next.js App Router Patterns
Server components, streaming, parallel routes, and i18n with next-intl.
Rust Ownership & Lifetimes
Mental model for ownership, borrowing, lifetimes, and common patterns.