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.

SPLADE: learned sparse retrieval in depth v1.0.0

Use this resource to set up learned sparse retrieval (SPLADE) and combine it with dense vectors

New

  • 462 downloads
  • 172 likes
  • 101 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install splade-learned-sparse-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 explains how SPLADE differs from BM25, encodes texts with Transformers, indexes sparse vectors in Qdrant or through rank_features in Elasticsearch, then combines SPLADE and dense results with RRF. It flags cost and speed trade-offs. You get an indexing and query pipeline.

Mostly picked by

Updated November 2, 2026

Card for the “SPLADE: learned sparse retrieval in depth” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: how SPLADE works and FLOPS regularization
  • SKILL.md: batch encoding with Hugging Face Transformers
  • SKILL.md: indexing in Qdrant or Elasticsearch and RRF hybrid fusion

Good fit for

  • Your lexical search misses synonyms or rephrased queries
  • You want a hybrid search that stays explainable

Not for

    Tags

    • splade
    • sparse retrieval
    • qdrant
    • hybrid

    About

    You say

    “Index my 200,000 product records with SPLADE in Qdrant and fuse the results with my dense embeddings using RRF.”

    Card for the “SPLADE: learned sparse retrieval in depth” 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 set up learned sparse retrieval (SPLADE) and combine it with dense vectors
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.3 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/retrieval/splade-deep
    Licence
    MIT

    Notice

    « splade-deep » (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.