How to Add Guardrails to LLM Apps with NeMo Guardrails
Protect your LLM application from jailbreaks, off-topic use, and harmful outputs in under 50 lines
Posts
How to Build a RAG Pipeline with Hugging Face Transformers v5
Ground your LLM answers in real documents with a working RAG pipeline you can run locally
How to Build a Semantic Search Engine with Embeddings
Create a search engine that understands meaning, not just keywords, using OpenAI embeddings
How to Build a Tool-Using AI Agent with Python
Create a Python agent that can search the web, run calculations, and chain tool calls autonomously
How to Build Agents with LangGraph
Step-by-step guide to creating reliable AI agents with LangGraph’s graph-based architecture and built-in persistence.
How to Create Synthetic Training Data with LLMs
Use Claude or GPT-4 to create labeled training data when real data is scarce or expensive
How to Detect Objects in Images with YOLOv8
Set up YOLOv8 for image and video object detection with just a few lines of Python
How to Generate Images with FLUX.2 in Python
Run Black Forest Labs’ FLUX.2 models locally to create images from text prompts on your own hardware
How to Generate Images with Stable Diffusion in Python
Run Stable Diffusion on your own GPU to create images from text prompts with full control
How to Implement Content Filtering for LLM Applications
Add safety guardrails to your AI application with input validation and output filtering
How to Label Training Data with LLM-Assisted Annotation
Build an LLM-powered annotation pipeline that cuts labeling time and cost dramatically
How to Segment Images with SAM 2 in Python
Use SAM 2 to cut out objects from images with clicks or bounding boxes in a few lines of Python
How to Serve LLMs in Production with SGLang
Get an SGLang server running, send requests via the OpenAI SDK, and fix the errors you’ll actually hit
How to Serve LLMs in Production with vLLM
Set up vLLM to serve open-source LLMs with an OpenAI-compatible API endpoint
How to Set Up Multi-GPU Training with PyTorch
Go from single-GPU to multi-GPU training with PyTorch DDP in under 50 lines of code
How to Use Claude's Model Context Protocol (MCP)
Step-by-step guide to building your first MCP server in Python and wiring it into Claude Desktop
How to Use GPT-5.2 Structured Outputs for Reliable JSON
Stop wrestling with malformed JSON. Use GPT-5.2’s structured outputs to enforce schemas at the token level.
How to Use PyTorch FlexAttention for Fast LLM Inference
Replace hand-rolled attention kernels with FlexAttention and get up to 2x faster LLM decoding on long contexts.
How to Use the Anthropic Python SDK for Claude
Learn the Anthropic Python SDK basics: messages, streaming, system prompts, and error handling
How to Write Effective System Prompts for LLMs
Write better system prompts that get consistent, high-quality results from any large language model