Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

pgvector: vectors and nearest-neighbor search in PostgreSQL v1.0.0

Use this resource to store vectors in PostgreSQL and run nearest-neighbor searches

New

  • 322 downloads
  • 225 likes
  • 123 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install pgvector-postgres-vector-search

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent creates vector columns, picks the distance operator and the HNSW or IVFFlat index, then tunes filtering and performance. It relies on references per language and on the pitfalls to avoid.

Mostly picked by

Updated November 2, 2026

Card for the “pgvector: vectors and nearest-neighbor search in PostgreSQL” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: quick start, operators and index rules
  • references/indexing.md: HNSW and IVFFlat indexes
  • references/troubleshooting.md: troubleshooting

Good fit for

  • Your PostgreSQL database needs semantic search
  • A vector search is slow and its index needs tuning

Not for

    Tags

    • postgresql
    • vectors
    • search
    • hnsw
    • embeddings

    About

    You say

    “Add an embedding column to my documents table and create an HNSW index for similarity search.”

    Card for the “pgvector: vectors and nearest-neighbor search in PostgreSQL” skill

    Skill published by itechmeat under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to store vectors in PostgreSQL and run nearest-neighbor searches
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • references/core.md2.1 KB
    • references/go.md1.5 KB
    • references/indexing.md3.2 KB
    • references/installation.md1.6 KB
    • references/java.md1.3 KB
    • references/node.md1.2 KB
    • references/performance-and-filtering.md4.2 KB
    • references/python.md2.4 KB
    • references/swift.md1 KB
    • references/troubleshooting.md1.7 KB
    • references/types-and-functions.md3.3 KB
    • SKILL.md3.6 KB

    Origin and licence

    Listed unmodified

    Author
    itechmeat
    Source
    github.com/itechmeat/llm-code/tree/509c4e00400e83eced7a4313cd34de87698e63c2/skills/pgvector
    Licence
    MIT

    Notice

    « pgvector » (itechmeat, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.