PinnedInLevel Up CodingbyMarco Bertelli·Sep 1, 2024Exploring Multimodal RAG with LlamaIndex and GPT-4 or the New Anthropic Sonnet ModelToday, we’ll explore how to build a Multimodal Retrieval-Augmented Generation (RAG) system using LlamaIndex in combination with GPT-4 or…A response icon4A response icon4
PinnedInLevel Up CodingbyMarco Bertelli·Feb 18, 2024Unveiling the Power of RAG: Building an Interactive Chatbot with React — A Comprehensive GuidePrevious Articles:
PinnedInLevel Up CodingbyMarco Bertelli·Jan 24, 2024Empowering Your Chatbot: Unveiling Dynamic Knowledge Sources with Advanced IntegrationExplore the next frontier in chatbot development adding how dynamic knowledge sources are harnessed.A response icon1A response icon1
PinnedInLevel Up CodingbyMarco Bertelli·Dec 28, 2023Build a complete OpenSource LLM RAG QA Chatbot — ChatEnginePrevious Articles:A response icon2A response icon2
PinnedInLevel Up CodingbyMarco Bertelli·Nov 16, 2023Build a complete OpenSource LLM RAG QA Chatbot — An In-depth Journey (Introduction)Embark on a comprehensive journey with me as we construct a fully-fledged QA RAG Chatbot, encompassing both the frontend and backend…A response icon3A response icon3
InLevel Up CodingbyMarco Bertelli·20h agoThe Questions You Should Ask Before Letting AI Build Your Next FeatureI built Filo, a Claude Code plugin that helps you work through a feature’s flow, one question at a time, before you implement it.A response icon2A response icon2
InLevel Up CodingbyMarco Bertelli·Sep 16The Architecture of a Multi-Agent System That Can Actually Take ActionOrchestrators and specialist agents are only the beginning. Here’s how tools, state, approvals, retries, and verification turn an AI…
InLevel Up CodingbyMarco Bertelli·Sep 9Why Does Hello World Cost $134/Month on AWS?A cost breakdown of private containers, redundant infrastructure, and controlled releases. And when they’re actually worth paying for.
InLevel Up CodingbyMarco Bertelli·Dec 16, 2025Stop Building Toy RAGs: A Guide to Self-Hosting LLMs on AWS SageMakerStop building toy apps. A deep dive into deploying Mistral-Nemo on AWS SageMaker, LlamaIndex and facing the $45k/year realityA response icon1A response icon1
InLevel Up CodingbyMarco Bertelli·Oct 4, 2025Scheduling chrone job’s for production application’s using Node JSWhy we forked Agenda and why you should care