Skip to main content

LLM evaluations and synthetic data generation with the MAIHEM models

Project description

maihem

Introduction

The maihem python package allows you to simulate personas and generate synthetic text data for training and evaluating your LLMs. It also provides text data evaluations.

Getting Started

Installation

To install the API, run the following command:

pip install maihem

Obtaining your maihem API key

Request a free API key here: www.maihem.ai.

Setting API key

Before using the maihem package, you need to set your maihem API key as an environment variable. You can add it directly in your python code, or to your local bash script.

Alternative 1: In python code

In the beggining of your code add the following lines with your corresponding API key:

import os

os.environ['MAIHEM_API_KEY'] = '<your_maihem_api_key>'

Alternative 2: In local bash script

For Linux:

Open the .bashrc file in your home directory with a text editor

vim ~/.bashrc

add the following line to the file with your corresponding API key:

export MAIHEM_API_KEY = '<your_maihem_api_key>'

Run the following command in the terminal to apply the changes

source ~/.bashrc

For Mac:

Open the .bash_profile file in your home directory with a text editor

vim ~/.bash_profile

add the following line to the file with your corresponding API key:

export MAIHEM_API_KEY = '<your_maihem_api_key>'

Run the following command in the terminal to apply the changes

source ~/.bash_profile

Examples of how to use MAIHEM

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

maihem-1.5.0.tar.gz (29.9 kB view details)

Uploaded Source

Built Distribution

maihem-1.5.0-py3-none-any.whl (81.4 kB view details)

Uploaded Python 3

File details

Details for the file maihem-1.5.0.tar.gz.

File metadata

  • Download URL: maihem-1.5.0.tar.gz
  • Upload date:
  • Size: 29.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.18

File hashes

Hashes for maihem-1.5.0.tar.gz
Algorithm Hash digest
SHA256 6e118d4938d0059ada5026bc9bde1abcc284dd4a1f4b5dcf4b917a8cf2a527ef
MD5 4ca15f07c2608f5f1d34a31f895c9318
BLAKE2b-256 955bf98a0f3f5f5c3e8092f89fb930d1e5b446c49d5619ac62810af611db9952

See more details on using hashes here.

File details

Details for the file maihem-1.5.0-py3-none-any.whl.

File metadata

  • Download URL: maihem-1.5.0-py3-none-any.whl
  • Upload date:
  • Size: 81.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.18

File hashes

Hashes for maihem-1.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c617db8dbeb34487e6f54209b19bad8476c87463d02d64e7067b19a604f6939a
MD5 d17530d27312ebb89554b70996b5d09e
BLAKE2b-256 b1e824403a6fa1ebeadaf3111be66f28f514675e24e9fe04d0dbbf4c83813427

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