nemotron-retrieval-recipes

Coordinate planning and safety checks for Nemotron embed and rerank retrieval recipes.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill nemotron-retrieval-recipes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nemotron-retrieval-recipes
Source: https://github.com/sayalinvidia/sayali-skills-test/tree/main/skills/nemotron-retrieval-recipes
Command: npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill nemotron-retrieval-recipes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill coordinates planning, debugging, tuning, evaluation, export, and deployment of Nemotron embedding and rerank retrieval recipes, ensuring teams work from the current checkout and follow safe, auditable steps.

Core Features & Use Cases

  • Guides end-to-end recipe planning for embed and rerank flows, including safety checks and dry-run recommendations.
  • Helps diagnose failures, compare base vs fine-tuned models, and reconcile public recipe docs with the current repository.
  • Assists with export/deploy handoffs and remote execution planning, while preserving secrets and minimizing risk.

Quick Start

Use the Nemotron retrieval recipes skill to plan and validate the current checkout before running any heavy experiments.

Frequently Asked Questions about nemotron-retrieval-recipes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan and validate Nemotron retrieval recipes before running GPU experiments?

Plan Nemotron retrieval recipes by applying safety checks and dry-run recommendations within your repository checkout before executing long-running GPU work. The skill enforces prerequisites, references current SKILL.md guidance, and selects the correct recipe family to validate embed and rerank flows.

What is the best way to debug Nemotron embed and rerank retrieval failures?

Debug Nemotron retrieval failures by diagnosing embed and rerank flow errors, comparing base versus fine-tuned model metrics, and reconciling public recipe documentation with your current repository checkout to identify configuration mismatches or outdated guidance.

Can I tune hyperparameters for Nemotron embed and rerank flows using this workflow?

You can tune hyperparameters for Nemotron embed and rerank flows. The workflow assists with interpreting evaluation metrics, selecting the correct recipe family, and adjusting parameters safely within the current repository checkout before deploying results.

Does the Nemotron retrieval workflow handle export and deployment handoffs?

The Nemotron retrieval workflow handles export and deployment handoffs. It assists with remote execution planning while preserving secrets, minimizing risk, and ensuring configurations are safely transitioned from tuning to deployment across embed and rerank flows.

Why should I run dry-runs before executing Nemotron retrieval tuning tasks?

Run dry-runs before Nemotron retrieval tuning to enforce prerequisites and prevent costly errors during long-running GPU work. The workflow recommends dry-runs to validate the current checkout and ensure safe, auditable steps before heavy experimentation.