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.

Nemotron retrieval recipes: embed and rerank v1.0.0

Use this resource to plan, debug and deploy the Nemotron embedding and reranking recipes

New

  • 384 downloads
  • 192 likes
  • 214 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install nemotron-embed-rerank-recipes

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 reads the checkout first, routes the retrieval failure to the right recipe, then guides configuration, evaluation and export. It treats a recipe as available only once its directory and CLI files are present.

Mostly picked by

Updated November 2, 2026

Card for the “Nemotron retrieval recipes: embed and rerank” 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: priorities, safe workflow and routing
  • references/embed.md: embedding recipes
  • references/rerank.md: reranking recipes

Good fit for

  • Your semantic search returns the wrong documents and you want to improve reranking
  • You must export a Nemotron embedding model

Not for

    Tags

    • nemotron
    • embedding
    • reranking
    • retrieval

    About

    You say

    “My Nemotron reranking ranks documents poorly: which recipe should I try?”

    Card for the “Nemotron retrieval recipes: embed and rerank” skill

    Skill published by NVIDIA Nemotron Team <noreply@nvidia.com> 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 plan, debug and deploy the Nemotron embedding and reranking recipes
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md3.1 KB
    • evals/.gitignore0 KB
    • evals/EVAL.md4.4 KB
    • evals/evals.json19.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/embed.md11.5 KB
    • references/evaluation.md3.5 KB
    • references/remote.md2 KB
    • references/rerank.md9.5 KB
    • skill-card.md4 KB
    • SKILL.md10.4 KB
    • skill.oms.sig5.8 KB

    Origin and licence

    Listed unmodified

    Author
    NVIDIA Nemotron Team <noreply@nvidia.com>
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/nemotron-retrieval-recipes
    Licence
    Apache-2.0

    Notice

    « nemotron-retrieval-recipes » (NVIDIA Nemotron Team <noreply@nvidia.com>, 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.