Cradle
1.0.0
[Situs web] [arxiv] [PDF]
The Cradle Framework memberdayakan model Yayasan Nascent untuk melakukan tugas komputer yang kompleks melalui antarmuka terpadu yang sama yang digunakan manusia, yaitu, tangkapan layar sebagai input dan operasi keyboard & mouse sebagai output.
Klik salah satu thumbnail video di atas untuk menontonnya di YouTube.
Kami saat ini menyediakan akses ke API Openai dan Claude. Harap buat file .env di root repositori untuk menyimpan tombol (salah satunya sudah cukup).
Contoh file .env yang berisi informasi pribadi:
OA_OPENAI_KEY = "abc123abc123abc123abc123abc123ab"
RF_CLAUDE_AK = "abc123abc123abc123abc123abc123ab" # Access Key for Claude
RF_CLAUDE_SK = "123abc123abc123abc123abc123abc12" # Secret Access Key for Claude
AZ_OPENAI_KEY = "123abc123abc123abc123abc123abc12"
AZ_BASE_URL = "https://abc123.openai.azure.com/"
RF_CLAUDE_AK = "abc123abc123abc123abc123abc123ab"
RF_CLAUDE_SK = "123abc123abc123abc123abc123abc12"
IDE_NAME = "Code"
OA_OPENAI_KEY adalah kunci API Openai. Anda bisa mendapatkannya dari openai.
AZ_OPENAI_KEY adalah kunci API Azure OpenAI. Anda bisa mendapatkannya dari portal Azure.
OA_CLAUDE_KEY adalah Kunci API Claude Antropik. Anda bisa mendapatkannya dari antropik.
Rf_claude_ak dan rf_claude_sk adalah AWS Restful API kunci dan kunci rahasia untuk Claude API.
IDE_NAME mengacu pada lingkungan IDE di mana kode repositori berjalan, seperti PyCharm atau Code (vScode). Ini terutama digunakan untuk memungkinkan pengalihan otomatis antara IDE dan lingkungan target.
Harap atur lingkungan Python Anda dan pasang dependensi yang diperlukan sebagai:
# Clone the repository
git clone https://github.com/BAAI-Agents/Cradle.git
cd Cradle
# Create a new conda environment
conda create --name cradle-dev python=3.10
conda activate cradle-dev
pip install -r requirements.txt 1. Option 1
# Download best-matching version of specific model for your spaCy installation
python -m spacy download en_core_web_lg
or
# pip install .tar.gz archive or .whl from path or URL
pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1.tar.gz
2. Option 2
# Copy this url https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1.tar.gz
# Paste it in the browser and download the file to res/spacy/data
cd res/spacy/data
pip install en_core_web_lg-3.7.1.tar.gz
Karena perbedaan besar antara setiap game dan perangkat lunak, kami telah memberikan pengaturan spesifik untuk masing -masing di bawah ini.
Karena beberapa pengguna mungkin ingin menerapkan kerangka kerja kami pada game baru, bagian ini terutama menampilkan direktori inti dan struktur organisasi cradle. Kami akan menyoroti dalam "" modul yang terkait dengan migrasi ke game baru, dan memberikan penjelasan terperinci nanti.
Cradle
├── cache # Cache the GroundingDino model and the bert-base-uncased model
├── conf # The configuration files for the environment and the llm model
│ ├── env_config_dealers.json
│ ├── env_config_rdr2_main_storyline.json
│ ├── env_config_rdr2_open_ended_mission.json
│ ├── env_config_skylines.json
│ ├── env_config_stardew_cultivation.json
│ ├── env_config_stardew_farm_clearup.json
│ ├── env_config_stardew_shopping.json
│ ├── openai_config.json
│ ├── claude_config.json
│ ├── restful_claude_config.json
│ └── ...
├── deps # The dependencies for the Cradle framework, ignore this folder
├── docs # The documentation for the Cradle framework, ignore this folder
├── res # The resources for the Cradle framework
│ ├── models # Ignore this folder
│ ├── tool # Subfinder for RDR2
│ ├── [game or software] # The resources for game, exmpale: rdr2, dealers, skylines, stardew, outlook, chrome, capcut, meitu, feishu
│ │ ├── prompts # The prompts for the game
│ │ │ └── templates
│ │ │ ├── action_planning.prompt
│ │ │ ├── information_gathering.prompt
│ │ │ ├── self_reflection.prompt
│ │ │ └── task_inference.prompt
│ │ ├── skills # The skills json for the game, it will be generated automatically
│ │ ├── icons # The icons difficult for GPT-4 to recognize in the game can be replaced with text for better recognition using an icon replacer
│ │ └── saves # Save files in the game
│ └── ...
├── requirements.txt # The requirements for the Cradle framework
├── runner.py # The main entry for the Cradle framework
├── cradle # Cradle's core modules
│ ├── config # The configuration for the Cradle framework
│ ├── environment # The environment for the Cradle framework
│ │ ├── [game or software] # The environment for the game, exmpale: rdr2, dealers, skylines, stardew, outlook, chrome, capcut, meitu, feishu
│ │ │ ├── __init__.py # The initialization file for the environment
│ │ │ ├── atomic_skills # Atomic skills in the game. Users should customise them to suit the needs of the game or software, e.g. character movement
│ │ │ ├── composite_skills # Combination skills for atomic skills in games or software
│ │ │ ├── skill_registry.py # The skill registry for the game. Will register all atomic skills and composite skills into the registry.
│ │ │ └── ui_control.py # The UI control for the game. Define functions to pause the game and switch to the game window
│ │ └── ...
│ ├── gameio # Interfaces that directly wrap the skill registry and ui control in the environment
│ ├── log # The log for the Cradle framework
│ ├── memory # The memory for the Cradle framework
│ ├── module # Currently there is only the skill execution module. Later will migrate action planning, self-reflection and other modules from planner and provider
│ ├── planner # The planner for the Cradle framework. Unified interface for action planning, self-reflection and other modules. This module will be deleted later and will be moved to the module module.
│ ├── runner # The logical flow of execution for each game and software. All game and software processes will then be unified into a single runner
│ ├── utils # Defines some helper functions such as save json and load json
│ └── provider # The provider for the Cradle framework. We have semantically decomposed most of the execution flow in the runner into providers
│ ├── augment # Methods for image augmentation
│ ├── llm # Call for the LLM model, e.g. OpenAI's GPT-4o, Claude, etc.
│ ├── module # The module for the Cradle framework. e.g., action planning, self-reflection and other modules. It will be migrated to the cradle/module later.
│ ├── object_detect # Methods for object detection
│ ├── process # Methods for pre-processing and post-processing for action planning, self-reflection and other modules
│ ├── video # Methods for video processing
│ ├── others # Methods for other operations, e.g., save and load coordinates for skylines
│ ├── circle_detector.py # The circle detector for the rdr2
│ ├── icon_replacer.py # Methods for replacing icons with text
│ ├── sam_provider.py # Segment anything for software
│ └── ...
└── ...
Karena setiap pengaturan game dan sistem operasi yang kompatibel dengan mereka berbeda, Cradle tidak bisa begitu saja mengganti satu nama game untuk bermigrasi ke game baru. Kami sarankan mempertimbangkan setiap game secara khusus. Misalnya, RDR2, game AAA yang independen, membutuhkan pertempuran waktu nyata, jadi kita perlu menjeda game untuk menunggu respons GPT-4O dan kemudian melepaskan permainan untuk menjalankan tindakan. Stardew memiliki masalah yang sama. Game lain seperti Dealer's Life 2 and Cities: Skylines tidak memiliki persyaratan real-time, sehingga mereka tidak perlu berhenti. Jika game baru mirip dengan yang terakhir, kami merekomendasikan untuk menyalin kota: implementasi Skylines dan mengikuti jalur implementasinya untuk membuat modul yang sesuai. Meskipun setiap permainan mungkin berbeda secara signifikan, kerangka kerja cradle kami masih dapat mencapai adaptasi terpadu untuk sebuah game. Dengan asumsi nama game baru adalah Newgame , pipa migrasi spesifik dapat ditemukan bermigrasi ke panduan game baru.
Jika Anda menganggap pekerjaan kami bermanfaat, silakan pertimbangkan mengutip kami!
@article{tan2024cradle,
title={Cradle: Empowering Foundation Agents towards General Computer Control},
author={Weihao Tan and Wentao Zhang and Xinrun Xu and Haochong Xia and Ziluo Ding and Boyu Li and Bohan Zhou and Junpeng Yue and Jiechuan Jiang and Yewen Li and Ruyi An and Molei Qin and Chuqiao Zong and Longtao Zheng and Yujie Wu and Xiaoqiang Chai and Yifei Bi and Tianbao Xie and Pengjie Gu and Xiyun Li and Ceyao Zhang and Long Tian and Chaojie Wang and Xinrun Wang and Börje F. Karlsson and Bo An and Shuicheng Yan and Zongqing Lu},
journal={arXiv preprint arXiv:2403.03186},
year={2024}
}
