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.

Run RAG and LLM systems in production v1.0.0

Use this resource to design a production LLM system with RAG, evals and cost control

New

  • 570 downloads
  • 223 likes
  • 194 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-production-operations

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 uses the skill to design RAG pipelines for indexing and querying, pick a vector database, structure prompts, cut costs and set up quality evals. You get production architecture guidance with the checkpoints to put in place.

Mostly picked by

Updated November 2, 2026

Card for the “Run RAG and LLM systems in production” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: full RAG architecture, indexing and query pipelines
  • SKILL.md: vector database choice, prompt structure and cost reduction

Good fit for

  • You want to add RAG to a product that already uses an LLM
  • You need to cut the cost of an AI service and measure its quality

Not for

    Tags

    • llm
    • rag
    • embeddings
    • production

    About

    You say

    “Design the RAG pipeline for our document base and suggest a vector database.”

    Card for the “Run RAG and LLM systems in production” skill

    Skill published by davila7 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 design a production LLM system with RAG, evals and cost control
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.1 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/llm-ops
    Licence
    MIT

    Notice

    « llm-ops » (davila7, 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.