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.

Matryoshka embeddings: truncating dimensions v1.0.0

Use this resource to reduce embedding dimensions while keeping good retrieval quality

New

  • 531 downloads
  • 227 likes
  • 164 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install matryoshka-embedding-truncation

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 checks that the model was trained with MRL, truncates vectors to the chosen dimension and renormalizes them. You get a dimension choice and the storage versus quality trade-off.

Mostly picked by

Updated November 2, 2026

Card for the “Matryoshka embeddings: truncating dimensions” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: MRL principle and compatible models
  • SKILL.md: manual truncation, MatryoshkaLoss and the dimension versus quality trade-off

Good fit for

  • Your vector store is expensive because of 1536 dimensions
  • You want an embedding model usable as both a short and a full vector

Not for

    Tags

    • matryoshka
    • mrl
    • embeddings
    • dimension
    • storage

    About

    You say

    “Truncate my OpenAI embeddings to 512 dimensions and measure the recall drop on my test set.”

    Card for the “Matryoshka embeddings: truncating dimensions” skill

    Skill published by claude-dev-suite 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 reduce embedding dimensions while keeping good retrieval quality
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.1 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/embeddings/matryoshka-embeddings
    Licence
    MIT

    Notice

    « matryoshka-embeddings » (claude-dev-suite, 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.