Skip to content

Command Palette

Search for a command to run...

RAG

Vector Databases

Store and search embeddings at scale for semantic retrieval.

Vector databases store high-dimensional embeddings and enable fast approximate nearest neighbour (ANN) search. This hub covers pgvector, Pinecone, Qdrant, Weaviate, HNSW indexing, hybrid search and when to use a dedicated vector DB vs Postgres.

Start Here

Begin with the fundamentals

The recommended first lesson for this topic.

Start
Fundamentals
Retrieval And Reranking
Tutorials
Embeddings And Vector Search
Architecture Patterns
Hybrid Search
Challenges
Embedding Model Drift
Projects
Rag Assistant
Key Concepts
vector-databaseembeddingshybrid-searchreranker
Technologies
pgvectorredis

Related Topics

RAG — Retrieval Augmented Generation

Ground LLMs in your private data with retrieval, reranking and citations.

Embeddings

Vector representations of meaning for semantic search and RAG.