promptolution

Name: promptolution
Author: gepromptet

151stars13forks

How to install promptolution?

gepromptet/promptolution

$git clone https://github.com/gepromptet/promptolution

Installs into the current project.

Summary

Promptolution is a unified, modular framework for prompt optimization built for researchers and advanced practitioners who want full control over their experimental setup. Unlike end-to-end application frameworks with high abstraction, promptolution focuses exclusively on the

Files · 1

View on GitHub

README.md

1	![Coverage](https://img.shields.io/badge/Coverage-96%25-brightgreen)
2	[![CI](https://github.com/automl/promptolution/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/automl/promptolution/actions/workflows/ci.yml)
3	[![Docs](https://github.com/automl/promptolution/actions/workflows/docs.yml/badge.svg?branch=main)](https://github.com/automl/promptolution/actions/workflows/docs.yml)
4	[![PyPI version](https://img.shields.io/pypi/v/promptolution.svg)](https://pypi.org/project/promptolution/)
5	![Code Style](https://img.shields.io/badge/Code%20Style-black-black)
6	![Python Versions](https://img.shields.io/badge/Python%20Versions-%E2%89%A53.10-blue)
7	[![Getting Started](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/automl/promptolution/blob/main/tutorials/getting_started.ipynb)
8
9	![promptolution](https://github.com/user-attachments/assets/84c050bd-61a1-4f2e-bc4e-874d9b4a69af)
10
11	<p align="center">
12	<img height="60" alt="lmu_logo" src="https://github.com/user-attachments/assets/5aecd0d6-fc2d-48b2-b395-d1877578a3c5" />
13	<img height="60" alt="mcml" src="https://github.com/user-attachments/assets/d9f3b18e-a5ec-4c3f-b449-e57cb977f483" />
14	<img height="60" alt="ellis_logo" src="https://github.com/user-attachments/assets/60654a27-0f8f-4624-a1d5-5122f2632bec" />
15	<img height="60" alt="uni_freiburg_color" src="https://github.com/user-attachments/assets/f5eabbd2-ae6a-497b-857b-71958ed77335" />
16	<img height="60" alt="tum_logo" src="https://github.com/user-attachments/assets/982ec2f0-ec14-4dc2-8d75-bfae09d4fa73" />
17	</p>
18
19	## 🚀 What is Promptolution?
20
21	Promptolution is a unified, modular framework for prompt optimization built for researchers and advanced practitioners who want full control over their experimental setup. Unlike end-to-end application frameworks with high abstraction, promptolution focuses exclusively on the optimization stage, providing a clean, transparent, and extensible API. It allows for simple prompt optimization for one task up to large-scale reproducible benchmark experiments.
22
23	<img width="808" height="356" alt="promptolution_framework" src="https://github.com/user-attachments/assets/e3d05493-30e3-4464-b0d6-1d3e3085f575" />
24
25	### Key Features
26
27	* Implementation of many current prompt optimizers out of the box.
28	* Unified LLM backend supporting API-based models, Local LLMs, and vLLM clusters.
29	* Built-in response caching to save costs and parallelized inference for speed.
30	* Detailed logging and token usage tracking for granular post-hoc analysis.
31
32	Have a look at our [Release Notes](https://automl.github.io/promptolution/release-notes/) for the latest updates to promptolution.
33
34	## 📚 Scientific Publications Powered by Promptolution
35
36	- CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution — Zehle, 2026. [arXiv](https://arxiv.org/abs/2605.13295)
37	- MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization — Büssing et al., 2026. [arXiv](https://arxiv.org/abs/2605.18869)
38	- promptolution: A Unified, Modular Framework for Prompt Optimization — Zehle et al., 2026. [EACL 2026](https://aclanthology.org/2026.eacl-demo.21/)
39	- Can Calibration of Positional Encodings Enhance Long Context Utilization? — Zehle & Aßenmacher, 2026. [EACL 2026](https://aclanthology.org/2026.findings-eacl.120/)
40	- Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky — Hathidara et al., 2025. [arXiv](https://arxiv.org/abs/2507.03336)
41	- CAPO: Cost-Aware Prompt Optimization — Zehle et al., 2025. [AutoML 2025](https://proceedings.mlr.press/v293/zehle25a.html)
42
43	## 🔧 Installation and Quickstart
44
45	```
46	pip install promptolution[api]
47	```
48
49	For local inference, add `[transformers]` (HuggingFace) or `[vllm]` (vLLM serving), or both.
50
51	```python
52	import pandas as pd
53	from promptolution.utils import ExperimentConfig
54	from promptolution.helpers import run_experiment
55
56	# DataFrame with columns "x" (input) and "y" (label)
57	df = pd.read_csv("yo

People who liked this also viewed

6 picks

Type

promptolution

151stars13forks

View on GitHub

How to install promptolution?

gepromptet/promptolution

$git clone https://github.com/gepromptet/promptolution

Installs into the current project.

Summary

Files · 1

View on GitHub

README.md

1	![Coverage](https://img.shields.io/badge/Coverage-96%25-brightgreen)
2	[![CI](https://github.com/automl/promptolution/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/automl/promptolution/actions/workflows/ci.yml)
3	[![Docs](https://github.com/automl/promptolution/actions/workflows/docs.yml/badge.svg?branch=main)](https://github.com/automl/promptolution/actions/workflows/docs.yml)
4	[![PyPI version](https://img.shields.io/pypi/v/promptolution.svg)](https://pypi.org/project/promptolution/)
5	![Code Style](https://img.shields.io/badge/Code%20Style-black-black)
6	![Python Versions](https://img.shields.io/badge/Python%20Versions-%E2%89%A53.10-blue)
7	[![Getting Started](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/automl/promptolution/blob/main/tutorials/getting_started.ipynb)
8
9	![promptolution](https://github.com/user-attachments/assets/84c050bd-61a1-4f2e-bc4e-874d9b4a69af)
10
11	<p align="center">
12	<img height="60" alt="lmu_logo" src="https://github.com/user-attachments/assets/5aecd0d6-fc2d-48b2-b395-d1877578a3c5" />
13	<img height="60" alt="mcml" src="https://github.com/user-attachments/assets/d9f3b18e-a5ec-4c3f-b449-e57cb977f483" />
14	<img height="60" alt="ellis_logo" src="https://github.com/user-attachments/assets/60654a27-0f8f-4624-a1d5-5122f2632bec" />
15	<img height="60" alt="uni_freiburg_color" src="https://github.com/user-attachments/assets/f5eabbd2-ae6a-497b-857b-71958ed77335" />
16	<img height="60" alt="tum_logo" src="https://github.com/user-attachments/assets/982ec2f0-ec14-4dc2-8d75-bfae09d4fa73" />
17	</p>
18
19	## 🚀 What is Promptolution?
20
21	Promptolution is a unified, modular framework for prompt optimization built for researchers and advanced practitioners who want full control over their experimental setup. Unlike end-to-end application frameworks with high abstraction, promptolution focuses exclusively on the optimization stage, providing a clean, transparent, and extensible API. It allows for simple prompt optimization for one task up to large-scale reproducible benchmark experiments.
22
23	<img width="808" height="356" alt="promptolution_framework" src="https://github.com/user-attachments/assets/e3d05493-30e3-4464-b0d6-1d3e3085f575" />
24
25	### Key Features
26
27	* Implementation of many current prompt optimizers out of the box.
28	* Unified LLM backend supporting API-based models, Local LLMs, and vLLM clusters.
29	* Built-in response caching to save costs and parallelized inference for speed.
30	* Detailed logging and token usage tracking for granular post-hoc analysis.
31
32	Have a look at our [Release Notes](https://automl.github.io/promptolution/release-notes/) for the latest updates to promptolution.
33
34	## 📚 Scientific Publications Powered by Promptolution
35
36	- CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution — Zehle, 2026. [arXiv](https://arxiv.org/abs/2605.13295)
37	- MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization — Büssing et al., 2026. [arXiv](https://arxiv.org/abs/2605.18869)
38	- promptolution: A Unified, Modular Framework for Prompt Optimization — Zehle et al., 2026. [EACL 2026](https://aclanthology.org/2026.eacl-demo.21/)
39	- Can Calibration of Positional Encodings Enhance Long Context Utilization? — Zehle & Aßenmacher, 2026. [EACL 2026](https://aclanthology.org/2026.findings-eacl.120/)
40	- Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky — Hathidara et al., 2025. [arXiv](https://arxiv.org/abs/2507.03336)
41	- CAPO: Cost-Aware Prompt Optimization — Zehle et al., 2025. [AutoML 2025](https://proceedings.mlr.press/v293/zehle25a.html)
42
43	## 🔧 Installation and Quickstart
44
45	```
46	pip install promptolution[api]
47	```
48
49	For local inference, add `[transformers]` (HuggingFace) or `[vllm]` (vLLM serving), or both.
50
51	```python
52	import pandas as pd
53	from promptolution.utils import ExperimentConfig
54	from promptolution.helpers import run_experiment
55
56	# DataFrame with columns "x" (input) and "y" (label)
57	df = pd.read_csv("yo

People who liked this also viewed

6 picks

Type