Skip to main content

Genetic algorithms for LLMs

Project description

prompt-genetics

Genetic algorithms for optimizing LLM prompts.

Installation

pip install prompt-genetics

Usage

from prompt_genetics import PromptOptimizer

# Example usage will be provided here

Features

  • Genetic algorithm-based optimization for LLM prompts
  • Support for various fitness functions
  • Configurable mutation and crossover operations
  • Easy integration with popular LLM APIs

Development

Setup

git clone https://github.com/OlegSokolov/prompt-genetics.git
cd prompt-genetics
pip install -e ".[dev]"

Running Tests

pytest

License

This project is licensed under the MIT License - see the LICENSE file for details.

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

prompt_genetics-0.0.1.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

prompt_genetics-0.0.1-py2.py3-none-any.whl (3.2 kB view details)

Uploaded Python 2Python 3

File details

Details for the file prompt_genetics-0.0.1.tar.gz.

File metadata

  • Download URL: prompt_genetics-0.0.1.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.7

File hashes

Hashes for prompt_genetics-0.0.1.tar.gz
Algorithm Hash digest
SHA256 57f3bdfcfa4c9d61075aac0aa2ad8b96e02e44bf6dee819580c1c3e8ab392f14
MD5 e2b8e28e032d8ea405871947e4c907b2
BLAKE2b-256 1b3185484d4f45a5c6ad4f58973cfed57d8bc68abe5e1b3c8acf08cb28218934

See more details on using hashes here.

File details

Details for the file prompt_genetics-0.0.1-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for prompt_genetics-0.0.1-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 5dfc1c0b7952f4253cd90aebb8924f523c982bfd667991d68c99eb65d545cf4b
MD5 cc80767cacdec82b62af0b8c54042288
BLAKE2b-256 cbc88ae52ad67b82d2789e57fb1512f17092a9e527cfe68e127e82251a144709

See more details on using hashes here.

Supported by

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