← Glossary

Vector Database

Tool

Definition

A database optimized for storing and querying high-dimensional embedding vectors via approximate nearest neighbor (ANN) search. Core infrastructure for RAG systems. Examples: Pinecone, Weaviate, Qdrant, pgvector (PostgreSQL extension).

Related Terms

Embedding

A dense numerical vector that represents text, images, or other data in a high-dimensional space where semantic similarity maps to geometric closeness. Foundation of semantic search, RAG systems, and recommendation engines.

RAG (Retrieval-Augmented Generation)

An architecture that enhances LLM outputs by first retrieving relevant documents from a knowledge base (via vector search) and injecting them into the prompt. Grounds the model in external, up-to-date facts without requiring retraining.

Inference

The process of running a trained model to generate predictions or outputs — as opposed to training (updating weights). Inference efficiency (speed, cost, latency) is the primary concern for production deployments.

Articles about Vector Database

8 RAG patterns that turn demos into prod

Open Source RAG Stack Turns Chaos Into a Build Plan

49 stars for GitHub’s RAG production list

SPIRE brings evidence-grounded AI to humanities research

Qdrant’s filter-first RAG design, decoded

All Terms

AgentAttention MechanismChain-of-ThoughtContext WindowDiffusion ModelDistillationDPO (Direct Preference Optimization)EmbeddingFew-shot PromptingFine-tuningFunction CallingGAN (Generative Adversarial Network)GRPO (Group Relative Policy Optimization)HallucinationInferenceLLM (Large Language Model)LoRA (Low-Rank Adaptation)MCP (Model Context Protocol)MultimodalPrompt EngineeringQLoRA (Quantized LoRA)QuantizationRAG (Retrieval-Augmented Generation)RLHF (Reinforcement Learning from Human Feedback)TemperatureTokenizerTool UseTop-p (Nucleus Sampling)TransformerVector DatabaseZero-shot Prompting