def get_weather(city: str) -> str:
"""
get weather information
@city: str, city name
@return: str, weather information
"""
return f"{city} weather: sunny"
# agent序列化位置，运行过程中会自动保存LLM的messages和python解析器的状态
workspace='./5_serialize'
role = 'You are a helpful agent.'
agent = Agent(workspace=workspace)
agent.user_input('My name is Shadow.')
agent = None
agent = Agent(role, workspace=workspace)
agent.user_input('What is my name?')
# 支持多模态: 图片输入
from GeneralAgent import Agent
agent = Agent('You are a helpful assistant.')
agent.user_input(['what is in the image?', {'image': '../docs/images/self_call.png'}])
总结
GeneralAgent 框架为构建智能代理提供了一个强大、灵活的平台，其丰富的功能和易用的 API 可以帮助开发者快速构建各种类型的智能代理应用。随着 LLM 技术的不断发展，GeneralAgent 框架将会在更多领域发挥重要作用。
Biderman, S. et al. (2023). Pythia: A suite for analyzing large language models across training and scaling. ✅arXiv preprint arXiv:2304.01355.
Chase, H. (2022). Langchain. ✅https://github.com/hwchase17/langchain.
Chiang, W. -L. et al. (2023). Stablelm-alpha 7b: Small and mighty for research. ✅https://github.com/Stability-AI/stablelm.
Clark, E. et al. (2023). Seahorse: A multilingual benchmark for factual correctness in summarization. ✅arXiv preprint arXiv:2306.05125.
Fabbri, A. R. et al. (2021). Summeval: Re-evaluating summarization evaluation. ✅Transactions of the Association for Computational Linguistics, 9, 408–430.
Fernandes, P. et al. (2023). AutoMQM: Automatic machine translation evaluation with large language models. In ✅Proceedings of the 17th Conference of the European Association for Machine Translation.
Freitag, M. et al. (2021). Results of the WMT21 Metrics Shared Task: Evaluating metrics with explanations. In ✅Proceedings of the Sixth Conference on Machine Translation.
Freitag, M. et al. (2022). Findings of the WMT22 Shared Task on Machine Translation Quality Estimation. In ✅Proceedings of the Seventh Conference on Machine Translation.
Freitag, M. et al. (2023). Findings of the WMT23 Shared Task on Machine Translation Quality Estimation. In ✅Proceedings of the Eighth Conference on Machine Translation.
Fu, Y. et al. (2023). From words to programs: Exploring the potential of large language models for abstract semantic parsing. ✅arXiv preprint arXiv:2305.17770.
Gao, L. et al. (2024a). A survey of large language model based automatic metrics for natural language generation. ✅arXiv preprint arXiv:2404.14012.
Gao, L. et al. (2024b). Retrieval augmentation for large language model based evaluation metrics. ✅arXiv preprint arXiv:2405.12504.
Iyer, S. et al. (2022). OPT: Open pre-trained transformer language models. ✅arXiv preprint arXiv:2205.01068.
Khattab, O. et al. (2023). DSPy: Towards general-purpose symbolic programming for composable program synthesis. ✅arXiv preprint arXiv:2305.15956.
Kocmi, T. and Federmann, C. (2023a). Large language models are not fair judges: Exploring the intrinsic bias of dataset average as a metric. ✅arXiv preprint arXiv:2305.13400.
Kocmi, T. and Federmann, C. (2023b). On the evaluation of machine translation systems trained with controlled simplification. In ✅Proceedings of the 17th Conference of the European Association for Machine Translation.
Kojima, T. et al. (2022). Large language models are zero-shot reasoners. ✅arXiv preprint arXiv:2205.11916.
Köpf, B. et al. (2023). OpenAssistant Conversations—democratizing large language model alignment. ✅arXiv preprint arXiv:2304.07327.
Lee, H. Y. et al. (2023a). PLATYPUS: Quick, cheap, and accurate fine-tuning of large language models. ✅arXiv preprint arXiv:2310.11307.
Leidinger, T. et al. (2023). Prompt surveillance: Tracking prompts that expose weaknesses in large language models. ✅arXiv preprint arXiv:2302.12177.
Leiter, C. et al. (2023). Findings of the WMT 2023 Shared Task on Evaluating the Evaluation of Machine Translation and Summarization. In ✅Proceedings of the Eighth Conference on Machine Translation.
Li, H. et al. (2023). Exploring the impact of emotion on large language models. ✅arXiv preprint arXiv:2305.14725.
Li, S. et al. (2024a). Unbabel’s submission to the WMT23 metrics shared task: Prompting large language models for machine translation quality estimation. In ✅Proceedings of the Eighth Conference on Machine Translation.
Li, Y. et al. (2024b). A survey of automatic metrics based on large language models for natural language generation. ✅arXiv preprint arXiv:2404.00774.
Liu, P. et al. (2023a). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ✅ACM Computing Surveys, 55(9), 1–35.
@misc{jin2024llm,
title={LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning},
author={Hongye Jin and Xiaotian Han and Jingfeng Yang and Zhimeng Jiang and Zirui Liu and Chia-Yuan Chang and Huiyuan Chen and Xia Hu},
year={2024},
eprint={2401.01325},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@misc{jin2024llm,
title={LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning},
author={Hongye Jin and Xiaotian Han and Jingfeng Yang and Zhimeng Jiang and Zirui Liu and Chia-Yuan Chang and Huiyuan Chen and Xia Hu},
year={2024},
eprint={2401.01325},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
