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-1.4.2.tar.gz (5.3 kB view details)

Uploaded Source

Built Distribution

maihem-1.4.2-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file maihem-1.4.2.tar.gz.

File metadata

  • Download URL: maihem-1.4.2.tar.gz
  • Upload date:
  • Size: 5.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for maihem-1.4.2.tar.gz
Algorithm Hash digest
SHA256 1a60a82743b10dc21b3c6cb9e0ddcab3c92c7f2040a5bbfdbfc2b5ca9ca60eb3
MD5 552324a33f36b22b4d25d6816e5d5ff8
BLAKE2b-256 370e8d3608902a45ff74718db3c5e902b87515067587ca4df0ddc2bb4742f75b

See more details on using hashes here.

File details

Details for the file maihem-1.4.2-py3-none-any.whl.

File metadata

  • Download URL: maihem-1.4.2-py3-none-any.whl
  • Upload date:
  • Size: 6.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for maihem-1.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 b82cd7253f0c88c7ce204089c00a2a6aa02564621104fa9fcf7f47ea4a72a827
MD5 f7cd57ac9cef41f6dc6f3de7a98f6d47
BLAKE2b-256 01f5b7ea7475aa63f20486c8efdafc8b6e8bbed452e1f1b1245b6ee65059627a

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