# Vector Store A Vector Store (or Vector Database) is a specialized [[Database]] designed to store, index, and search high-dimensional vector [[Embeddings]]. Unlike traditional databases that store text and numbers in rows and columns, vector stores work with mathematical representations where similar items cluster together in multidimensional space. Vector stores are essential infrastructure for [[Retrieval-Augmented Generation (RAG)]] and modern AI applications. ## How Vector Embeddings Work ``` ┌─────────────────────────────────────────────────────┐ │ Embedding Process │ │ │ │ "The cat sat" ──► [0.23, -0.45, 0.12, ...] │ │ (384-1536 dimensions) │ │ │ │ Similar meanings = Nearby vectors │ │ Different meanings = Distant vectors │ └─────────────────────────────────────────────────────┘ ``` When ML models process text, images, or audio, they convert these into dense numerical vectors. Each dimension captures different features and attributes. ## Key Operations - **Indexing**: Store vectors with metadata - **Similarity search**: Find nearest neighbors (cosine, euclidean, dot product) - **Filtering**: Combine vector search with metadata filters - **Hybrid search**: Mix semantic and keyword search ## Popular Vector Databases | Database | Strength | |----------|----------| | Pinecone | Managed, easy RAG setup | | Milvus | Billion-scale, enterprise | | Weaviate | Model integrations, modules | | Chroma | Simple, developer-friendly | | Qdrant | Open source, high performance | | pgvector | [[PostgreSQL]] extension | | Redis | Sub-millisecond latency | ## Use Cases - [[Retrieval-Augmented Generation (RAG)]] for LLMs - Semantic search across documents - AI chatbots with contextual memory - Image/audio similarity search - Recommendation systems - Duplicate detection ## 2026 Trends - **Graph-enhanced retrieval**: Combining vector search with knowledge graphs - **Multimodal embeddings**: Text, image, audio in same vector space - **Hybrid architectures**: Vector + traditional database features ## References - https://www.pinecone.io/learn/vector-database/ - https://qdrant.tech/ ## Related - [[Retrieval-Augmented Generation (RAG)]] - [[RAG Pipelines]] - [[Database]] - [[PostgreSQL]] - [[Large Language Models (LLMs)]] - [[LangChain]] - [[Embeddings]] - [[Semantic Search]]