RAG & knowledge

Vector database

A database optimised for storing and querying high-dimensional vectors, typically for similarity search.

also known as: vector store, vector DB

In depth

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.

Related concepts

EmbeddingA fixed-size numeric vector that represents the semantic meaning of a piece of text.RAGA pattern where relevant documents are fetched from a knowledge base and pasted into context before the LLM answers.Hybrid searchCombining vector similarity with keyword matching to get the best of both.

Newsletter

Get the next post in your inbox.

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.

More in RAG & knowledge

Chunking/glossary/chunking Embedding/glossary/embedding Hybrid search/glossary/hybrid-search Knowledge base/glossary/knowledge-base RAG/glossary/rag Re-ranking/glossary/rerank