pgvector

pgvector adds vector similarity search directly inside PostgreSQL: store embeddings in a vector column next to the rest of your relational data and query with exact or approximate nearest-neighbor search. It supports single/half-precision, binary, and sparse vectors; L2, inner product, cosine, L1, Hamming, and Jaccard distances; and inherits Postgres superpowers — ACID transactions, point-in-time recovery, and JOINs between vectors and business data. Install from source, Docker, Homebrew, APT, or use any major hosted Postgres (it ships preinstalled on many).

```bash

cd /tmp && git clone --branch v0.8.7 https://github.com/pgvector/pgvector.git

cd pgvector && make && sudo make install

```

```sql

CREATE EXTENSION vector;

CREATE TABLE docs (id bigserial PRIMARY KEY, embedding vector(1536));

SELECT * FROM docs ORDER BY embedding <-> '[0.1,0.2,...]' LIMIT 5;

```

Or skip compiling: Docker image, Homebrew (brew install pgvector), or hosted Postgres with the extension preinstalled.