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.

Choosing an embedding model and chunking strategy v1.0.0

Use this resource to choose an embedding model and chunking strategy for search

New

  • 304 downloads
  • 163 likes
  • 218 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install embedding-model-chunking-choice

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 compares embedding models by domain and language, sets the document chunking strategy and the processing chain, then suggests dimension reduction. The goal is precise semantic search for RAG.

Mostly picked by

Updated November 2, 2026

Card for the “Choosing an embedding model and chunking strategy” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: model comparison and embedding pipeline
  • references/details.md: chunking strategies and examples

Good fit for

  • Your RAG returns weakly relevant passages
  • You index multilingual documents

Not for

    Tags

    • embeddings
    • rag
    • chunking
    • semantic search

    About

    You say

    “Choose an embedding model and a chunking scheme for our technical docs in French and English.”

    Card for the “Choosing an embedding model and chunking strategy” 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 choose an embedding model and chunking strategy for search
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/details.md17 KB
    • SKILL.md2.8 KB

    Origin and licence

    Listed unmodified

    Author
    wshobson
    Source
    github.com/wshobson/agents/tree/0874a27b17a22e2b7c2e2bcd725768e0803cad06/plugins/llm-application-dev/skills/embedding-strategies
    Licence
    MIT

    Notice

    « embedding-strategies » (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.