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.

Building prefetch queries for hybrid search v1.0.0

Use this resource to build prefetch queries for hybrid search and choose the lexical method

New

  • 436 downloads
  • 208 likes
  • 108 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install qdrant-hybrid-prefetch-queries

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 works out whether your searches target the same vectors with different queries or different representations, then builds the prefetches. It helps you choose between BM25 on a full-text index and sparse vectors, or migrate sparse-vector BM25 to a full-text index.

Mostly picked by

Updated November 2, 2026

Card for the “Building prefetch queries for hybrid search” 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: building prefetches inside a Query API request
  • SKILL.md: choosing the lexical retriever and migrating BM25 to a full-text index

Good fit for

  • You combine dense and sparse retrieval in one search
  • You are choosing between BM25 and SPLADE

Not for

    Tags

    • qdrant
    • prefetch
    • bm25
    • sparse vectors
    • lexical search

    About

    You say

    “Should I use BM25 on a full-text index or sparse vectors for my product sheets?”

    Card for the “Building prefetch queries for hybrid search” skill

    Skill published by qdrant 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 build prefetch queries for hybrid search and choose the lexical method
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md13.2 KB

    Origin and licence

    Listed unmodified

    Author
    qdrant
    Source
    github.com/qdrant/skills/tree/15793b641b7bc85d2e7dc59be1b796381ce715ba/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types
    Licence
    Apache-2.0

    Notice

    « qdrant-hybrid-search-prefetches » (qdrant, 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.