Skip to main content

tpu_index is a package for fast similarity search over large collections of high dimension vectors on TPUs

Project description

TPU Index

TPU Index is a package for fast similarity search over large collections of high dimension vectors on TPUs. This package was built to support our project that we developed for https://tfworld.devpost.com/.

Link to our project: https://devpost.com/software/naturallanguagerecommendations

Installation

!pip install tpu-index

Basic usage

from tpu_index import TPUIndex

index = TPUIndex(num_tpu_cores=8)
index.create_index(vectors)  # vectors = numpy array, shape == [None, None]

...
D, I = index.search(xq, distance_metric='cosine', top_k=5)

ToDo:

  • Add more distance metrics
  • Optional GPU support

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tpu_index-0.0.3.tar.gz (2.5 kB view hashes)

Uploaded Source

Built Distribution

tpu_index-0.0.3-py3-none-any.whl (3.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page