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.

Vector search and embeddings v1.0.0

Use this resource to set up semantic search with embeddings

New

  • 534 downloads
  • 129 likes
  • 239 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vector-search-retrieval

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 picks the embedding model, the vector store and how to combine it with keyword search, then adds reranking. You get more relevant search and the metrics to watch to keep quality high.

Mostly picked by

Updated November 2, 2026

Card for the “Vector search and embeddings” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: the vector search expert's role and method
  • references/patterns.md: hybrid retrieval and reranking architectures
  • references/sharp_edges.md: embedding drift, recall loss and off-topic results

Good fit for

  • Your search engine misses products described with different words
  • You must choose between pgvector and a dedicated vector database

Not for

    Tags

    • embeddings
    • vector search
    • pgvector
    • qdrant
    • reranking

    About

    You say

    “Add semantic search to our catalogue with pgvector and reranking of the top fifty results.”

    Card for the “Vector search and embeddings” skill

    Skill published by omer-metin under the Apache-2.0 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 set up semantic search with embeddings
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md5.3 KB
    • references/sharp_edges.md17.9 KB
    • references/validations.md5 KB
    • SKILL.md2.3 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/vector-specialist
    Licence
    Apache-2.0

    Notice

    « vector-specialist » (omer-metin, Apache-2.0) 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.