Skip to main content
ModelTerms

Agents & Tools · intermediate

Vector Database (vector store)

A vector database stores high-dimensional embeddings and answers "find the K nearest vectors to this query" extremely fast. The retrieval engine behind most RAG systems.

Explanation

Vector DBs index millions to billions of embeddings using algorithms like HNSW or IVF so nearest-neighbor search runs in milliseconds instead of seconds. They typically also store metadata so you can filter ("nearest among documents from last week") alongside vector similarity.

Popular options include Pinecone, Weaviate, Qdrant, Milvus, pgvector (Postgres extension), and Chroma. For small workloads, in-memory indexes via FAISS or LanceDB are often enough.

Examples

  • Pinecone hosting embeddings for a customer-support RAG.
  • pgvector inside a Postgres app for semantic search.

Frequently asked

What is Vector Database?

A vector database stores high-dimensional embeddings and answers "find the K nearest vectors to this query" extremely fast. The retrieval engine behind most RAG systems.

What is an example of vector database?

Pinecone hosting embeddings for a customer-support RAG.

How is Vector Database related to Embedding?

Vector Database and Embedding are both agents & tools concepts. An embedding is a list of numbers (a vector) that represents a piece of input — a word, a sentence, an image — in a space where similar things end up close together.

Is Vector Database considered intermediate?

Vector Database is generally considered intermediate-level material in the AI and LLM space.

EmbeddingArchitecture

An embedding is a list of numbers (a vector) that represents a piece of input — a word, a sentence, an image — in a space where similar things end up close together.

Retrieval-Augmented GenerationAgents & Tools

RAG retrieves relevant documents from a corpus at query time and includes them in the prompt, letting an LLM answer with up-to-date, source-cited, private information without retraining.

Semantic SearchAgents & Tools

Semantic search ranks documents by meaning rather than keyword match, using embedding similarity. "Affordable laptops" can match "cheap notebooks" even with no overlapping words.

Hybrid SearchAgents & Tools

Hybrid search combines vector (semantic) and keyword (BM25) retrieval and fuses their results — usually via Reciprocal Rank Fusion — to get the best of both: semantic recall and exact-match precision.

BM25Agents & Tools

BM25 is the classical keyword-based ranking algorithm: a refined TF-IDF that scores documents by query-term frequency, document length, and corpus-wide rarity. The keyword side of hybrid search.

RerankerAgents & Tools

A reranker is a second-pass scoring model that takes the top-K retrieved candidates and reorders them by joint relevance to the query. Typically a cross-encoder; dramatically improves retrieval precision at low cost.

Side-by-side comparisons

Sources