Skip to main content

prompt-autotune

A light weight library that takes in a task description and a prompt and tunes the prompt to perform better.

Accepting any and all PRs!

Installation

pip install prompt-autotune

Usage

Basic usage

  1. Import and initialize TunePrompt
from prompt_autotune import TunePrompt
tuner = TunePrompt(
    task = "your task here",
    prompt = "your prompt here",
    verbose = True # makes it log updates
)
  1. Call it as a function, the tuner will prompt you through the process through the command line
tuner()
  1. Once finished, access your tuned prompt
new_prompt = tuner.prompt

Command Line Tool

  1. Type the command and press enter.
tune
  1. Follow through the process.

  2. The final prompt will be printed on the console.

Enjoy!

Release files for prompt-autotune 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for prompt-autotune 0.4.0
File Size Uploaded
prompt_autotune-0.4.0.tar.gz 17.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for prompt-autotune 0.4.0
File Interpreter ABI Platform
prompt_autotune-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 36.3 kB

Release files / prompt_autotune-0.4.0.tar.gz

Download URL prompt_autotune-0.4.0.tar.gz
Size 17.2 kB
Tags Source
SHA-256 checksum
How to use checksums
1dcd764879d9f55a6bbc1f057b9bb665f6128b71861deb6ed780337fb676fa11
BLAKE2b-256 checksum
How to use checksums
25179b2e1f14839e21162ead020c744493b310e7458e0bd0345e86238d1706e7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.11.5

Release files / prompt_autotune-0.4.0-py3-none-any.whl

Download URL prompt_autotune-0.4.0-py3-none-any.whl
Size 19.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a7dac644dd75a96c6a42789379bf6a629f334cab45212b78c288d2d6b2f683ca
BLAKE2b-256 checksum
How to use checksums
cbc3b08876816da2ebd28bbc04c6ca8bf973b28248a4011695c7aae677a9fcab
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.11.5

Release history Release notifications | RSS feed

This release

0.4.0 This release

2 release files

0.3.0

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page