@leonardo1903
Web & app dev enthusiast exploring blockchain and agentic AI. Building, breaking, learning—one project at a time.
Nothing here yet.
Nothing here yet.
Jun 7, 2025 · 19 min read · Here's a scenario that should feel familiar. Your RAG system retrieves beautifully on test queries. You've tuned chunk sizes, experimented with embedding models, added a reranker. The eval numbers loo
Join discussion
Jun 6, 2025 · 19 min read · You built a RAG chatbot. You chunked your documents, embedded them, shoved them into a vector store, and wired it to an LLM. It works — mostly. But it hallucinates on questions it should know, misses
Join discussion