RECENT POSTS
Tokenization: BPE Algorithm
NLP models and LLMs do not process raw text directly, but instead operate on numerical representations. In this context, tokenization is the process of converting a sequence of characters (a string) into a sequence of tokens, smaller units of text. These tokens are then mapped to numerical identifiers (integers), which correspond to positions in a…
LangGraph: Human-in-the-Loop & Persistence
Human-in-the-loop (HITL) in LangGraph is a mechanism that allows pausing graph execution to request human intervention, enabling validation, approval, or adjustment of decisions before the flow continues. Persistence in LangGraph allows saving the graph state throughout execution using checkpoints stored in a persistent storage. This enables the workflow to be interrupted and later resumed from…
LangGraph: Getting Started
LangGraph is a framework designed for building complex graph-based workflows, enabling the explicit modeling of systems with multiple steps and decision points. Unlike traditional linear flows, it uses nodes (execution units) and edges (transitions between nodes) to define system behavior. This approach provides a high level of control, allowing for conditional branching, parallel node execution,…
Edvaldo Melo 