gerallt

GUI Executor for RCEs Automated LLM Testing

https://github.com/dlr-sc/gerallt

Science Score: 62.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
    1 of 1 committers (100.0%) from academic institutions
  • Institutional organization owner
    Organization dlr-sc has institutional domain (www.dlr.de)
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

GUI Executor for RCEs Automated LLM Testing

Basic Info
  • Host: GitHub
  • Owner: DLR-SC
  • License: other
  • Language: Python
  • Default Branch: main
  • Size: 51.8 KB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

GERALLT - GUI Executor for RCEs Automated LLM Testing

Requirements

bash pip install -r requirements.txt

Setup

Download RCE from their website and set it up.

Edit config.cfg by adding following information: | Parameter | Description | |---|---| | rce_path | Path to RCE | | openai_api_key | OpenAI API Key (if you are using ChatGPT models) | | ollama_server_ip | IP to the Ollama server (if you are using local LLMs like Llama) |

Settings

Following Paramters can be changed in the config.cfg file:

| Parameter | Description | Example | |---|---|---| | controller_model | the LLM that performs actions on the GUI of RCE | gpt-4o-2024-08-06 | | evaluator_model | the LLM that evaluates the GUI for Problems | gpt-4o-2024-08-06 | | icon_description_model | LLM that gives a textual description of the icons on the GUI | gpt-4o-2024-08-06 | | max_saved_actions | maximum number of actions that are saved | 20 | | max_actions | maximum number of actions that are being performed | 200 | | step_by_step | if true, requires user input for performing any number of actions | true | | test_only_tool_integration | if true, only tests the Tool Integration Wizard of RCE (For testing all of RCE not all capabilities for the controler Agent are implemented) | true |

Results

After running automatedguitesting.py the results can be found in the ./temp/ folder.

Licenses

Please see the file LICENSE.md for further information about how the content is licensed.

Owner

  • Name: DLR Institute for Software Technology
  • Login: DLR-SC
  • Kind: organization
  • Email: opensource@dlr.de
  • Location: Cologne, Berlin, Braunschweig, Oberpfaffenhofen, Bremen

German Aerospace Center (DLR)

Citation (CITATION.cff)

# SPDX-FileCopyrightText: 2025 German Aerospace Center (DLR)
# SPDX-FileContributor: Tim Rosenbach <tim.rosenbach@dlr.de>
#
# SPDX-License-Identifier: CC-BY-NC-ND-4.0

cff-version: 1.2.0
title: >-
  Automated Testing of the GUI of RCE using Large Language
  Models
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Tim
    family-names: Rosenbach
    email: tim.rosenbach@dlr.de
    affiliation: German Aerospace Center (DLR)
    orcid: 'https://orcid.org/0009-0003-9748-6691'
identifiers:
  - type: doi
    value: 10.5281/zenodo.14646517
abstract: >-
  This software was developed to test the GUI of RCE using
  LLMs. At the moment it is possible to test the Tool
  Integration Wizard of RCE and partially test the rest of
  the GUI. It is possible to use OpenAI models or use local
  LLMs hosted by Ollama.
keywords:
  - Large Language Models
  - LLM
  - Automation
  - GUI Testing
  - Remote Component Environment
  - RCE
license: MIT
version: '1.0'
date-released: '2025-01-09'

GitHub Events

Total
  • Member event: 1
  • Push event: 1
  • Fork event: 1
  • Create event: 2
Last Year
  • Member event: 1
  • Push event: 1
  • Fork event: 1
  • Create event: 2

Committers

Last synced: 7 months ago

All Time
  • Total Commits: 2
  • Total Committers: 1
  • Avg Commits per committer: 2.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 2
  • Committers: 1
  • Avg Commits per committer: 2.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Tim-Rosenbach t****h@d****e 2
Committer Domains (Top 20 + Academic)
dlr.de: 1

Issues and Pull Requests

Last synced: 7 months ago


Dependencies

requirements.txt pypi