// LATEST
// RAG
How embeddings and vector stores actually work →
An embedding turns text into numbers and a vector store finds what is close in meaning. Here is what that actually does, and the one blind spot that shapes every RAG pipeline.
// MATE
The Mate Journey: how an idea became a tool →
The origin story of Symfony Mate, from a moment of quiet rivalry at a conference to a prototype built on a train with no internet connection.
// RAG
Indexing sets the ceiling for retrieval →
RAG quality starts at indexing, not at the query. Loading, chunking and enriching the source decide what your retriever can ever find. A field report from symfony/ai.
// RAG
RAG beyond hello world: retrieval is a pipeline →
Most RAG demos retrieve something. Real documentation needs the right passages, ranked for what the user meant. Why retrieval is a pipeline, not a lookup.
// BUILD
Symfony AI Spotlight: Mate, an Agent's Way into Your Runtime →
Mate gives a coding agent what source code can't: what a Symfony application actually just did. As of Symfony AI 0.13 it's a plain CLI with a discovery layer on top.