From e1dcf84381373c4d5327fcc7a0f25ecda4fd6df7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Hei=C3=9F?=
 <87521684+timo282@users.noreply.github.com>
Date: Sun, 29 Sep 2024 21:27:07 +0200
Subject: [PATCH] Update README.md

---
 README.md | 46 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 39 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 28b5cc2..a842ae3 100644
--- a/README.md
+++ b/README.md
@@ -1,18 +1,30 @@
 # Promptolution
 
-Project for seminar "AutoML in the age of large pre-trained language models" at LMU Munich , developed by [Timo Heiß](https://www.linkedin.com/in/timo-heiss/), [Moritz Schlager](https://www.linkedin.com/in/moritz-schlager/) and [Tom Zehle](https://www.linkedin.com/in/tom-zehle/).
+Promptolution is a library that provides a modular and extensible framework for implementing prompt tuning experiments. It offers a user-friendly interface to assemble the core components for various prompt optimization tasks.
 
-## Set Up
+In addition, this repository contains our experiments for the paper "Towards Cost-Effective Prompt Tuning: Evaluating the Effects of Model Size, Model Family and Task Descriptions in EvoPrompt".
 
-After having cloned the repository, run
+This project was developed by [Timo Heiß](https://www.linkedin.com/in/timo-heiss/), [Moritz Schlager](https://www.linkedin.com/in/moritz-schlager/) and [Tom Zehle](https://www.linkedin.com/in/tom-zehle/).
+
+## Installation
+
+Use pip to install our library:
+
+```
+pip install promptolution
+```
+
+Alternatively, clone the repository, run
 
 ```
 poetry install
 ```
 
-to install the necessary dependencies.
+to install the necessary dependencies. You might need to install [pipx](https://pipx.pypa.io/stable/installation/) and [poetry](https://python-poetry.org/docs/) first.
+
+## Documentation
 
-You might need to install [pipx](https://pipx.pypa.io/stable/installation/) and [poetry](https://python-poetry.org/docs/) first.
+A comprehensive documentation with API reference is availabe at https://finitearth.github.io/promptolution/.
 
 ## Usage
 
@@ -21,9 +33,29 @@ Create API Keys for the models you want to use:
 - Anthropic: store token in anthropictoken.txt
 - DeepInfra (for Llama): store token in deepinfratoken.txt
 
-Run experiments based on config via:
+## Core Components
+
+- Task: Encapsulates initial prompts, dataset features, targets, and evaluation methods.
+- Predictor: Implements the prediction logic, interfacing between the Task and LLM components.
+- LLM: Unifies the process of obtaining responses from language models, whether locally hosted or accessed via API.
+- Optimizer: Implements prompt optimization algorithms, utilizing the other components during the optimization process.
+
+## Key Features
+
+- Modular and object-oriented design
+- Extensible architecture
+- Easy-to-use interface for assembling experiments
+- Parallelized LLM requests for improved efficiency
+- Integration with langchain for standardized LLM API calls
+- Detailed logging and callback system for optimization analysis
+
+## Reproduce our Experiments
+
+We provide scripts and configs for all our experiments. Run experiments based on config via:
 
 ```
 poetry run python scripts/experiment_runs.py --experiment "configs/<my_experiment>.ini"
 ```
-where `<my_experiment>.ini` is a config based on our templates.
\ No newline at end of file
+where `<my_experiment>.ini` is a config based on our templates.
+
+This project was developed for seminar "AutoML in the age of large pre-trained models" at LMU Munich.