No description
| toolbench | ||
| .gitattributes | ||
| .gitignore | ||
| anytool.py | ||
| anytoolbench.json | ||
| api_database_function.py | ||
| arguments.py | ||
| check_solved.py | ||
| config_example.py | ||
| custom_query_data0129.json | ||
| data_for_retrieval.json | ||
| data_generation_by_gpt4.py | ||
| dfs_gt.py | ||
| extract_api_details.py | ||
| extract_category_tool_details.py | ||
| extract_tool_database.py | ||
| LICENSE | ||
| openai_utils.py | ||
| prompt_template.py | ||
| rapidapi.py | ||
| rapidapi_key_list_example.json | ||
| README.md | ||
| requirements.txt | ||
| run_main.sh | ||
| server.py | ||
| solved_dict.json | ||
| tool_details.json | ||
| unsolvable.json | ||
| verifier.py | ||
AnyTool
This is the implementation of the paper AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

🔧 Installation
✅ Dependencies
Require Python 3.9+
🚀 Quick install
pip install requirements.txt
🔆 Data
ToolBench
Refer to ToolBench.
AnyToolBench
Generation script
python data_generation_by_gpt4.py
We provide sample data in anytoolbench.json file.
🚗 Run AnyTool
Fill your OpenAI config and toolbench key into the config.py.
Run ToolBench
python anytool.py --output_dir result/test_instruction/G1_instruction --query_path data/test_instruction/G1_instruction.json --max_api_number 64
Run AnyToolBench
python anytool.py --output_dir result/anytoolbench --query_path anytoolbench.json -max_api_number 64
👨🏫 Acknowledgement
This repo is built on ToolBench.
📑Citation
If you find this project is helpful for your research, consider citing our paper
@article{du2024anytool,
title={AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls},
author={Du, Yu and Wei, Fangyun and Zhang, Hongyang},
journal={arXiv preprint arXiv:2402.04253},
year={2024}
}