Vector databases (Qdrant, pgvector, Pinecone, Weaviate, Milvus) are the storage layer for RAG. You write embeddings in, you query by similarity to a new embedding. Most modern vector stores also support hybrid search (combining vector similarity with keyword search), filtering by metadata, and re-ranking. On Digitorn the rag module abstracts over Qdrant by default, with a per-app collection.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.