针对ChatGLM3模型实现了接口统一化运行脚本(opeai接口规范).

[Haoke98]

由于ChatGLM3模型采用了全新设计的 Prompt 格式，除正常的多轮对话外。同时原生支持工具调用（Function Call）、代码执行（Code Interpreter）和 Agent 任务等复杂场景。原来的ChatGLM模型的运行脚本不适用.

[cla-assistant[bot]]

All committers have signed the CLA.

[cla-assistant[bot]]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[sweep-ai[bot]]

Apply Sweep Rules to your PR?

• [ ] Apply: All new business logic should have corresponding unit tests.
• [ ] Apply: Refactor large functions to be more modular.
• [ ] Apply: Add docstrings to all functions and file headers.

[Haoke98]

由于我用原来的 openai_api.py 文件加载 chatglm3-6b 模型时, 其 tokenization_chatglm.py 文件处理History时总时报字典的KeyError (如下图所示) 所以我一气之下修改了一下源代码, 也顺手就推送到了这里, 希望给其他开发者提供便利, 少做重复工作. 还希望原作者能够采纳.

[c121914yu]

非常感谢。 您可以增加一个 readme 来更好的描述相关运行和部署流程么？

[c121914yu]

hello，请问还在么？希望能提供一份README,便于其他人理解如何运行和部署。