14｜工具和工具箱：LangChain中的Tool和Toolkits一览

老师好，那我们可以自定义工具吗？比如某个实际场景，我需要调用到某个内部系统的API，通过API返回的信息我再做提取，然后将提取到的信息重新给LLM推理

老师，文中“甚至尝试让大模型自动回答 Issues 中的问题——反正大模型解决代码问题的能力本来就更强。”是怎样实现让大模型理解项目系统代码的？例如：一个web项目，我给出一个接口，大模型能从给定的接口出发自顶向下，分析出每一层的调用关系和依赖关系。

怎么理解Tool和Toolkits 的异同呢？

老师，怎么进群啊？

(this Thought/Action/Action Input/Observation can repeat N times)\n——老师，这个可以让模型自主决定回溯多少次，如果稍微复杂的问题，是否有可能模型找不到最终答案？这种情况是如何跳出的？使用者是如何控制这个异常场景处理的？

I should search for the paper with the identifier "2005.14165" on arxiv to find out its innovative points. Action: arxiv Action Input: 2005.14165 Observation: Published: 2020-07-22 Title: Language Models are Few-Shot Learners Authors: Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, Dario Amodei Summary: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens 为何我执行了搜到的论文和文中的不一样，开始胡说八道了。