consistent

Make sure AI model outputs are consistent

These details have not been verified by PyPI

Project links

Homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Project description

consisTent is a full blows testing framework for prompts. The goal of consisTent is to create reproducible tests for LLM based applications regardless of the FM used.

Installation

pip install consistent

Concepts

consisTent comes with 2 types of validators (testers)

Project details

These details have not been verified by PyPI

Project links

Homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

0.0.10

Jun 14, 2023

0.0.9

Apr 28, 2023

0.0.7

Apr 28, 2023

0.0.5

Apr 28, 2023

0.0.4

Apr 28, 2023

This version

0.0.3

Apr 28, 2023

0.0.2

Apr 22, 2023

0.0.1

Apr 22, 2023

Download files

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

Source Distribution

consistent-0.0.3.tar.gz (6.1 kB view hashes)

Uploaded Apr 28, 2023 Source

Built Distribution

consistent-0.0.3-py3-none-any.whl (7.5 kB view hashes)

Uploaded Apr 28, 2023 Python 3

Hashes for consistent-0.0.3.tar.gz

Hashes for consistent-0.0.3.tar.gz
Algorithm	Hash digest
SHA256	`40151825b5b835768b6a0d707b8cb727763a6cb12ff44e82a89da53776be6d84`
MD5	`74ff9e60344d468408d595d82abbc8d4`
BLAKE2b-256	`0d05f6c59324635a95075b3d727a9251d442a4e57c10d6b5ce126c17cdc1bd4d`

Hashes for consistent-0.0.3-py3-none-any.whl

Hashes for consistent-0.0.3-py3-none-any.whl
Algorithm	Hash digest
SHA256	`64e47dd96d650301b6e3d507a31d5d195988a9b6c9ecabcf8264671c55d18b5b`
MD5	`351e6436a086e274c55fb5e53141a71d`
BLAKE2b-256	`18bfc5c2a5dd85daec114c2b227a6196ca3cee8b146d2823dcc5183328b42f89`