Definition
Vector databases are specialized systems for efficient similarity search over embedding vectors.
Core Operations: - Store vectors with metadata - Find k-nearest neighbors - Filter by metadata - Update/delete vectors
Search Algorithms: - HNSW (Hierarchical Navigable Small World) - IVF (Inverted File Index) - PQ (Product Quantization) - Exact nearest neighbor (small scale)
Popular Solutions: - Pinecone (managed) - Weaviate (open source) - Milvus (open source) - Qdrant (open source) - Chroma (lightweight) - pgvector (PostgreSQL extension)
Use Cases: - RAG systems - Semantic search - Recommendation engines - Image similarity
Examples
Pinecone storing document embeddings for a customer support chatbot.
Related Terms
Want more AI knowledge?
Get bite-sized AI concepts delivered to your inbox.
Free daily digest. No spam, unsubscribe anytime.