Articles tagged “rag”
16 articles
Agentic RAG: from dumb retrieval to self-correcting agents
Your RAG pipeline retrieves wrong documents and nobody catches it. Build a self-correcting agent that grades results, rewrites queries, and knows when to stop.
Graph memory for AI agents: when vector search isn't enough
Build graph memory for AI agents in TypeScript and Python. Extract entities, track relationships over time, and compare Mem0, Zep, and Letta in production.
Embeddings Turn Text Into Meaning. Here's the Math and the Code
What embeddings are, how similarity search works under the hood, and how to build a semantic search engine, from cosine similarity math to production vector databases.
The RAG You Built Last Year Is Already Outdated
RAG has branched into 5 distinct architectures: Self-RAG, Corrective RAG, Adaptive RAG, GraphRAG, and Agentic RAG. Here's when to use each and how to choose.
Your RAG Returns Wrong Answers. Upgrading the Model Won't Help
Most RAG quality problems are retrieval problems, not model problems. Bad chunking, wrong embeddings, and missing re-ranking cause more hallucinations than model capability gaps.
From Keyword Search to Shopping Memory
Build the intelligence layer for an AI shopping assistant: semantic product search with Commerce MCP, customer memory that persists across visits, and MCP tool registration for multi-channel deployment.
Your RAG Pipeline Is Answering the Wrong Question
Naive RAG scores 42% on multi-hop questions. Agentic RAG hits 94.5%. The difference: letting the agent decide what to retrieve, when, and whether the results are good enough. Build both in TypeScript and Python.
Your Agent Remembers Everything Except What Matters
ICLR 2026 MemAgents research reveals when AI agents need episodic memory (what happened) vs semantic memory (what's true). Covers MAGMA, Mem0, AdaMem papers, comparison of Mem0 vs Letta vs Zep, and architecture patterns with TypeScript examples.
Context Engineering Is What Your Agent Actually Needs
Prompt engineering hits a wall with production AI agents. Context engineering fixes it. Build a full context pipeline with memory, RAG, history compression, and tool resolution.
Your Voice Agent Forgets Everything. Here's How to Fix That
How to add persistent memory, tools, and knowledge to Pipecat and LiveKit voice agents using the Chanl Python SDK — one SDK instead of assembling five services.
Memoria de Agentes de IA: Del contexto de sesion al conocimiento a largo plazo
Construye sistemas de memoria para agentes de IA desde cero en TypeScript. Cubre tipos de memoria (sesion, episodica, semantica, procedural), arquitecturas (buffer, resumen, recuperacion vectorial), interseccion con RAG y diseno con privacidad.
Fine-tuning vs RAG: why most teams pick wrong and how to decide
When to fine-tune, when to use RAG, and when you need both — with hands-on LoRA fine-tuning and RAG implementation on the same task to show the difference.
RAG desde Cero: Construye un Pipeline de Generación Aumentada por Recuperación
Construye un pipeline RAG funcional desde cero en TypeScript y Python. Cubre embeddings, chunking, búsqueda vectorial y generación con código real y ejecutable.
The Knowledge Base Bottleneck: Why RAG Alone Isn't Enough for Production Agents
RAG works beautifully in demos. In production, stale data, chunking failures, and unscored retrieval quietly sink your AI agents. Here's what actually fixes it.
AI Agent Memory: Build Your Own or Buy Off the Shelf?
Comparing Mem0, Zep, Letta, and custom memory for AI agents. We break down architecture trade-offs, compliance risks, and when each approach makes sense.
Voice AI Hallucinations: The Hidden Cost of Unvalidated Agents
Discover how voice AI hallucinations can cost businesses thousands daily and learn proven strategies to detect and prevent them before they reach customers.
Aprende IA Agéntica
Una lección por semana: técnicas prácticas para construir, probar y lanzar agentes IA. Desde ingeniería de prompts hasta monitoreo en producción. Aprende haciendo.
