Vector DB

Concept

RAG Explained

Retrieval-Augmented Generation is how you give LLMs access to your own data without retraining them. Here's how it actually works.

Concept

Vector Databases Explained

What vector databases actually do, when you need one, and what the real tradeoffs between Pinecone, Weaviate, Qdrant, and pgvector look like.

Directory

Chroma

Open-source embedding database for LLM apps with a simple Python and JavaScript API plus managed Chroma Cloud.

Directory

Milvus

Open-source vector database built for billion-scale similarity search, maintained by Zilliz with a managed cloud option.

Directory

pgvector

Open-source Postgres extension adding vector types and similarity search, enabling embeddings in an existing database.

Directory

Pinecone

Managed vector database. Serverless tier, sub-100ms queries at scale.

Directory

Qdrant

Open-source vector DB written in Rust. Fast, with great filtering.

Directory

turbopuffer

Serverless vector and full-text search engine built on object storage, priced for large-scale workloads.

Directory

Weaviate

Open-source vector database with hybrid search, modular model integrations, and a managed cloud offering.