• Stars
    star
    30
  • Rank 839,658 (Top 17 %)
  • Language
    Python
  • License
    MIT License
  • Created over 1 year ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Using embeddings compressed by Product Quantization, in Javascript

More Repositories

1

sqlite-vector-search

Jupyter Notebook
28
star
2

gcs

Compressed Bloom Filters (Golomb-compressed sequences, with indices)
Haskell
17
star
3

zgrab-the-web

Feed the hundreds of millions of domains in the Common Crawl to zgrab
Shell
9
star
4

save-bindings

Making printf-debugging obsolete.
Ruby
7
star
5

embeddingdb.js

An embedding database for the browser
JavaScript
6
star
6

text-entropy-api

Web service (via Sinatra) to pull stats for a list of words from the text-entropy statistical models
Ruby
6
star
7

text-entropy

Aggregate n-gram frequency counts from GBooks via Hadoop, dump statistical model out to flat files
Shell
6
star
8

text-entropy-visualization

The JS that renders the data from the API from text-entropy
JavaScript
4
star
9

ugc-contributors

Analyzing contributors to Wikipedia's user-generated content
Ruby
3
star
10

diffusion-local-time

Diffusion Local Time, in Art Hack Day DETHRONE 2024
Python
3
star
11

sister-cities-map

Map of sister cities, via lsb/city-correlation-mapping and deck.gl
JavaScript
2
star
12

jslzjb-faster

Trying out some speed improvements for jslzjb
JavaScript
2
star
13

liberstatim

This was the original incarnation of NoDictionaries, written in Ruby 1.6 [sic]. It is included for historical reference, and contains many antipatterns.
TeX
2
star
14

turk-rest-api

QC, fair wages, and question form generation for Mechanical Turk
Ruby
1
star
15

code-kata-bayhac2013

Code Kata BayHac 2013
Haskell
1
star
16

passphrase-safety-ui

UI for http://www.leebutterman.com/passphrase-safety/
JavaScript
1
star
17

n-gram-weaving

Visualizing the weave of n-grams in text
Haskell
1
star
18

generative-image-semantic-search

Image semantic search in <10 lines
1
star
19

city-correlation-mapping

City correlation mapping, via Wikipedia revisions
Jupyter Notebook
1
star
20

visualizing-light-pollution

Visualizing light pollution, as topography (and as haze)
1
star
21

slow-nested-svgs

Browser benchmark of speed differences between RECTs in nested SVGs versus non-nested RECTs.
1
star
22

enwiki-nlp

Obsolete: churn through wiki markup in various ways
Ruby
1
star
23

stable-diffusion-raspi-clock

A clock on a Raspberry Pi, telling time via Stable Diffusion images
Python
1
star
24

eight-ways-of-looking-at-a-fivegram

WIP. Markov-chain-generated text, US/UK, 1700s/1800s/early 1900s/late 1900s
Ruby
1
star
25

1984-dissociated-text

Markov-chain-generated text, based on Orwell's 1984, in the browser.
1
star
26

bashblog

A Bash script that handles blog posting
Shell
1
star
27

human-numbers

Lists of numbers in American English
Shell
1
star
28

wikipedia-protected-classes

Fine tuning a text classification model to identify potentially protected classes of new articles
Jupyter Notebook
1
star
29

ndclj

ND.clj
Clojure
1
star
30

stable-diffusion-clock

Timepiece, imagery via Stable Diffusion
Jupyter Notebook
1
star