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.

Fast similarity search with FAISS v1.0.0

Use this resource to set up fast similarity search over vectors with FAISS

New

  • 552 downloads
  • 229 likes
  • 104 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install faiss-similarity-search

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 picks the right FAISS index type (exact, IVF or HNSW), builds the index from your embeddings and runs k-NN searches. It also says when a database with metadata, such as Chroma or Pinecone, is the better fit.

Mostly picked by

Updated November 2, 2026

Card for the “Fast similarity search with FAISS” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: CPU or GPU installation, index creation and search
  • references/index_types.md: Flat, IVF and HNSW index types

Good fit for

  • You search for similar vectors among millions of embeddings
  • Your search must be fast and needs no metadata filtering

Not for

    Tags

    • faiss
    • vectors
    • search
    • embeddings

    About

    You say

    “Create a FAISS index to find the ten closest products for each embedding.”

    Card for the “Fast similarity search with FAISS” 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 set up fast similarity search over vectors with FAISS
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/index_types.md6.3 KB
    • SKILL.md5.2 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « rag-faiss » (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.