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.

Tuning a vector index: latency, recall, memory v1.0.0

Use this resource to tune a vector index for latency, recall and memory

New

  • 475 downloads
  • 156 likes
  • 213 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vector-index-performance-tuning

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 index type for your volume, tunes HNSW parameters and quantisation, then balances recall against speed. It suggests ways to scale vector search.

Mostly picked by

Updated November 2, 2026

Card for the “Tuning a vector index: latency, recall, memory” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: index types, HNSW parameters and quantisation
  • references/details.md: tuning templates and examples

Good fit for

  • Your semantic search is slow on a million vectors
  • Your index uses too much memory

Not for

    Tags

    • vector index
    • hnsw
    • quantization
    • search

    About

    You say

    “Tune the HNSW index of our two-million-vector store for low latency.”

    Card for the “Tuning a vector index: latency, recall, memory” skill

    Skill published by wshobson 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 tune a vector index for latency, recall and memory
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/details.md13.3 KB
    • SKILL.md2.3 KB

    Origin and licence

    Listed unmodified

    Author
    wshobson
    Source
    github.com/wshobson/agents/tree/0874a27b17a22e2b7c2e2bcd725768e0803cad06/plugins/llm-application-dev/skills/vector-index-tuning
    Licence
    MIT

    Notice

    « vector-index-tuning » (wshobson, 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.