Mindket

GUIA

Newversion 1 · updated

Overview

Helps visitors plan a museum visit, find artworks by text search, save favorites and follow a walking route on an indoor map, as a static site.

GUIA is a kit in the Education category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python and pip, to fetch the files
  • A web browser
  • A backend Space address set as API_BASE in config.js, before you publish your own copy
Runs in
  • A browser, by visiting the Space on Hugging Face
  • Windows, macOS or Linux, for a copy you open in a web browser
  • A local web server on port 8000, for development with a backend on port 7860
Start with
pip install -U huggingface_hub
hf download feifanjasmineguan/guia-for-art --repo-type space --local-dir guia-for-art
cd guia-for-art

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

GUIA is a smart guide for the MET museum. It is a static website where a visitor searches artworks by text, hearts the ones they like, gets recommendations from storage, and sees a walking route on the museum's indoor map. A second view for curators ranks pieces in storage by how often visitors interact with them.

Who it suits

Museum visitors who want a plan for their visit, and curators who want to see which stored pieces visitors care about.

IndustryWho uses itHow they use itExample
MuseumsVisitorsSearch for art and follow a routeHeart a painting and walk to it on the map
MuseumsCuratorsSee which stored pieces draw interestOpen the leaderboard of in-storage pieces
EducationStudents and art loversLook at an artwork with similar works beside itOpen the single-artwork page
SoftwareWeb developersStudy a vanilla JavaScript site with a mapRead map.js and api.js

Anyone who needs a ready, hosted museum product can skip it, since the pages need a backend Space address to be set.

Where to use it

  • A browser, by visiting the Space on Hugging Face
  • Windows, macOS or Linux, for a copy you open in a web browser
  • A local web server on port 8000, for development with a backend on port 7860
Use caseWhoWhat they get back
Plan a visitVisitorsRanked artworks, in-storage recommendations and a route
View one artworkVisitorsLive museum details and a strip of similar works
Watch visitor interestCuratorsA live ranking of in-storage pieces

How to set it up

  • Python and pip, to fetch the files
  • A web browser
  • A backend Space address set as API_BASE in config.js, before you publish your own copy
  1. Install the Hugging Face hub package.
  2. Download the Space with the hf command.
  3. Move into the new folder.
  4. Open index.html in a web browser.
pip install -U huggingface_hub
hf download feifanjasmineguan/guia-for-art --repo-type space --local-dir guia-for-art
cd guia-for-art

For local development, the README starts a simple web server from the frontend folder and runs the backend with uvicorn in a second terminal.

cd guia-module3
python3 -m http.server 8000 --directory frontend

How to use it

Online, visit the Space on Hugging Face and pick a role on the landing page. In a local copy, open index.html and choose the same way.

ToolWhat it does
index.htmlLanding page where you pick a role
visitor.htmlText search, hearts, recommendations and a walking route
gallery.htmlOne artwork with live museum data and similar works
curator.htmlLive ranking of in-storage pieces by visitor interaction

Example

As a visitor you type a search for an artwork, heart a few results, and look at the recommendations from storage. The map then draws a walking route through the museum rooms.

For newcomers and experts

If you are new, visit the Space, pick the visitor role and type one search. Hearting a result is the first small thing to try, and it shows how the route and recommendations come from your choices.

If you know the field, the site is vanilla JavaScript with MapLibre for the indoor map and a baked routing graph of rooms, edges and floor information, about 4 MB, stored in met_route_graph.json. A query string can override the backend address for testing. The trade-off is that search and recommendations rely on a separate backend.

  1. You pick a role on the landing page
  2. You search and heart artworks
  3. The backend ranks and recommends
  4. The map draws a walking route

Good to know

  • Backend: the pages call a separate backend Space whose address you set in config.js
  • Data: a routing graph file ships with the frontend
  • License: mit
  • Cost to run: none named
  • Data it reaches: the backend you configure and live artwork details from the MET API, plus your searches and hearts
  • Not for: working fully offline, since it needs the backend

README and files

README

GUIA

Helps visitors plan a museum visit, find artworks by text search, save favorites and follow a walking route on an indoor map, as a static site.

Made by feifanjasmineguan on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: GUIA is a smart guide for the MET museum. It is a static website where a visitor searches artworks by text, hearts the ones they like, gets recommendations from storage, and sees a walking route on the museum's indoor map. A second view for curators ranks pieces in storage by how often visitors interact with them.

Who it suits: Museum visitors who want a plan for their visit, and curators who want to see which stored pieces visitors care about.

Industry | Who uses it | How they use it | Example
Museums | Visitors | Search for art and follow a route | Heart a painting and walk to it on the map
Museums | Curators | See which stored pieces draw interest | Open the leaderboard of in-storage pieces
Education | Students and art lovers | Look at an artwork with similar works beside it | Open the single-artwork page
Software | Web developers | Study a vanilla JavaScript site with a map | Read map.js and api.js

Anyone who needs a ready, hosted museum product can skip it, since the pages need a backend Space address to be set.

Where to use it:

  • A browser, by visiting the Space on Hugging Face
  • Windows, macOS or Linux, for a copy you open in a web browser
  • A local web server on port 8000, for development with a backend on port 7860
Use case | Who | What they get back
Plan a visit | Visitors | Ranked artworks, in-storage recommendations and a route
View one artwork | Visitors | Live museum details and a strip of similar works
Watch visitor interest | Curators | A live ranking of in-storage pieces

How to set it up:

  • Python and pip, to fetch the files
  • A web browser
  • A backend Space address set as API_BASE in config.js, before you publish your own copy
  1. Install the Hugging Face hub package.
  2. Download the Space with the hf command.
  3. Move into the new folder.
  4. Open index.html in a web browser.
pip install -U huggingface_hub
hf download feifanjasmineguan/guia-for-art --repo-type space --local-dir guia-for-art
cd guia-for-art

For local development, the README starts a simple web server from the frontend folder and runs the backend with uvicorn in a second terminal.

cd guia-module3
python3 -m http.server 8000 --directory frontend

How to use it: Online, visit the Space on Hugging Face and pick a role on the landing page. In a local copy, open index.html and choose the same way.

Tool | What it does
index.html | Landing page where you pick a role
visitor.html | Text search, hearts, recommendations and a walking route
gallery.html | One artwork with live museum data and similar works
curator.html | Live ranking of in-storage pieces by visitor interaction

Example: As a visitor you type a search for an artwork, heart a few results, and look at the recommendations from storage. The map then draws a walking route through the museum rooms.

For newcomers and experts: If you are new, visit the Space, pick the visitor role and type one search. Hearting a result is the first small thing to try, and it shows how the route and recommendations come from your choices.

If you know the field, the site is vanilla JavaScript with MapLibre for the indoor map and a baked routing graph of rooms, edges and floor information, about 4 MB, stored in met_route_graph.json. A query string can override the backend address for testing. The trade-off is that search and recommendations rely on a separate backend.

You pick a role on the landing page
You search and heart artworks
The backend ranks and recommends
The map draws a walking route

Good to know:

  • Backend: the pages call a separate backend Space whose address you set in config.js
  • Data: a routing graph file ships with the frontend
  • License: mit
  • Cost to run: none named
  • Data it reaches: the backend you configure and live artwork details from the MET API, plus your searches and hearts
  • Not for: working fully offline, since it needs the backend

On Hugging Face, 13 November 2026

  • Likes: 5
  • Built with: static
  • License: mit

Links

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.

Files
README.md  5 KB

1 file, 5 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

ProductLikesBuilt withLicenseLast change
GUIA This page5staticmit
The Ultra-Scale PlaybookShares static4,131staticapache-2.0
LLM训练终极指南 | The Ultra-Scale PlaybookShares static281staticapache-2.0
Attention VisualizationShares static200staticapache-2.0
Number Tokenization BlogShares static127staticmit
Train the agent slidesShares static20staticapache-2.0
Numbers as Mindket last read them, on 2026-11-12.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

upscaler

uwg · Kit

Holds a set of image upscaling models gathered from the OpenModelDB community, for people who want to enlarge low-resolution pictures with AI on their own comp…

New

Pixel Art XL

nerijs · Kit

A pixel art style add-on for Stable Diffusion XL that turns text prompts into pixel-style images, with an optional LCM LoRA for faster runs. For game makers, d…

New

VibeVoice-1.5B

microsoft · Kit

Turns written conversations into spoken audio with up to four speakers and about 90 minutes of speech, an open Microsoft text-to-speech model for research on p…

New

Similar in Education

See all in Education

Vāgdhenu by prathoshap

prathoshap · Kit

Reads classical Sanskrit verses aloud in a chant style, using one trained voice and a reference clip that sets the rhythm. For people who study, recite or need…

New

Limite 1B - Violetto

paradigma-inc · Kit

Solves hard math problems with a 1B-parameter model trained from scratch for fast, high-volume reasoning. It suits developers who run math workloads on an NVID…

New

Agaram 2.5B

murai-labs · Kit

Chats in Tamil script, romanized Tamil and English, and translates between Tamil and English. A 2.5B model built from scratch by Murai Labs, for Tamil speakers…

New