npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@nodellmcache/pgvector

v1.0.0

Published

Postgres + pgvector store adapter for NodeLLMCache

Downloads

232

Readme

@nodellmcache/pgvector

Postgres + pgvector store adapter for NodeLLMCache. Implements VectorStoreAdapter, so it plugs into @nodellmcache/semantic-cache — "you already have Postgres" is reason enough to use it.

Install

npm install @nodellmcache/pgvector @nodellmcache/core pg

Requires the vector extension (the adapter runs CREATE EXTENSION IF NOT EXISTS vector):

docker run -e POSTGRES_PASSWORD=pw -p 5432:5432 pgvector/pgvector:pg16

Quick start

import { PgVectorAdapter } from '@nodellmcache/pgvector'

const store = new PgVectorAdapter<{ source: string }>({
  connectionString: 'postgres://postgres:pw@localhost:5432/postgres',
  table: 'embeddings', // created on first use
})

await store.upsert('doc-1', embedding, { source: 'wiki' })
const matches = await store.query(queryEmbedding, 5, { source: 'wiki' })
// → [{ id: 'doc-1', score: 0.94, metadata: { source: 'wiki' } }]
await store.delete('doc-1')
await store.disconnect()

Schema & queries

The adapter manages a table (id text primary key, embedding vector(dim), metadata jsonb):

  • upsertINSERT ... ON CONFLICT (id) DO UPDATE.
  • query → ordered by cosine distance embedding <=> $1, returning score = 1 - distance (cosine similarity). Metadata filters use jsonb containment (metadata @> $filter).
  • Dimension is taken from vectorSize or inferred from the first upserted vector.

Options

| Option | Default | Description | |--------|---------|-------------| | connectionString / host+port+user+password+database | localhost:5432 | Connection (or pass client) | | table | nodellmcache_vectors | Table name (validated as a safe identifier) | | vectorSize | inferred | Dimensionality | | ssl / max | — | Passed to the pg pool | | maxRetries | 3 | Attempts per op on transient failure | | client | constructed | Inject an existing pg pool/client (or compatible) |

Testing

Unit tests use an in-memory fake. Integration tests are guarded:

docker run -e POSTGRES_PASSWORD=pw -p 5432:5432 pgvector/pgvector:pg16
PGVECTOR_URL=postgres://postgres:pw@localhost:5432/postgres pnpm --filter @nodellmcache/pgvector test

License

MIT