Skip to main content

Count the number of tokens in a text string or file, similar to the Unix 'wc' utility.

Project description

Token Count

Token Count is a command-line utility that counts the number of tokens in a text string, file, or directory, similar to the Unix wc utility. It uses the OpenAI tiktoken library for tokenization and is compatible with GPT-3.5-turbo token counts.

Installation

To install Token Count, run the following command in your terminal:

pip install token-count

Usage

Token Count has three main options:

Count tokens in a text string:

token-count --text "Your text here"

Count tokens in a file:

token-count --file path/to/your/file.txt

Count tokens in a directory (recursively):

token-count --directory path/to/your/directory

You can provide any combination of these options. Token Count will print the token count for each input type.

License

This project is licensed under the MIT License.

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

token-count-0.1.2.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

token_count-0.1.2-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file token-count-0.1.2.tar.gz.

File metadata

  • Download URL: token-count-0.1.2.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.4

File hashes

Hashes for token-count-0.1.2.tar.gz
Algorithm Hash digest
SHA256 5e4c7b5230b9fbcdb46165743b837b87bb34372e3fdb6b9fa93e4397dbb1c421
MD5 93c517eb6a72a6fc1dca6611a06bba3f
BLAKE2b-256 773741ec5a7c1ef8087f4017d74b5dff8022da08f1e942567deb508141c86dfc

See more details on using hashes here.

File details

Details for the file token_count-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: token_count-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 3.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.4

File hashes

Hashes for token_count-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 710f6e0e8e18dd405f38e33f5fbe7a8be6f31e432f627e09a3d1c93737c3533c
MD5 5383aeba2d9a0e039c1611a52aa30481
BLAKE2b-256 0adca9638900d0acb2550b23877aa839d866f1c702476012c7abe8b534d1eec2

See more details on using hashes here.

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