Start here in Generative AI
The most useful guides in this topic, not just the most recent.
Generative AI Guides & Tutorials
Practical guides to LLMs, RAG, agents, prompt engineering and the modern Gen AI stack used in production today.
Generative AI articles
Hugging Face Transformers: A Practical Getting-Started Guide
Hugging Face Transformers is the standard Python library for using open models. This guide explains the Hub and the library, runs a sentiment pipeline and a text generator on a laptop, then repeats the classification by hand so you can see the tokens, scores and probabilities that a pipeline hides.
LlamaIndex vs LangChain: Which Framework to Pick
LlamaIndex and LangChain overlap more than their marketing suggests. This comparison builds the same retrieval step in both, over the same documents with the same embedding model, and finds the framework made no difference to the results while the chunking settings changed the text sent to the model fivefold.
Open-Source LLMs vs Closed Models: A 2026 Comparison
The choice between an open-weight model and a closed one is now less about raw quality and more about control, licence terms and cost structure. This comparison explains what open actually means for a language model, reads the licences that matter, and sets out when each kind of model is the better fit.
Chunking Strategies for RAG: Getting Retrieval Right
How you cut documents into chunks decides what a RAG system can find. This guide tests five chunking strategies on the same 40 questions and finds no single winner: splitting rescued facts buried in long sections, lost others that needed their surroundings, and section titles mattered more than size or overlap.
Prompt Templates and Versioning: Managing Prompts at Scale
Once an application has more than a few prompts, editing them in place stops being safe. This guide shows how to keep prompts as versioned code: templates that keep user text out, versions that include the model and settings, fingerprints that catch silent edits, and checks that run before a prompt ships.
vLLM and Model Serving: Scaling LLM Inference
Running a model for one user is easy. Serving it to hundreds at once is a scheduling and memory problem. This guide explains decode steps, batching and the key-value cache, simulates why continuous batching keeps a GPU busy, and shows how vLLM is started and called through an OpenAI-compatible API.