We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
def add_two_number(a,b): return a+b parameters = ArkChatParameters(**request.__dict__) parameters.tools = [ add_two_number, ] llm = BaseChatLanguageModel( endpoint_id=endpoint_id, messages=["what is 7234234 + 12312"], parameters=parameters, ) resp = llm.arun()
参数类型可以支持基础数据类型,pydantic BaseModel, enum 等
The text was updated successfully, but these errors were encountered:
赞呀,还有一个事儿想讨论一下 BaseChatLanguageModel 和 ark.chat_completions.create 有可能整合一下嘛,比如类似 automatic tool execute 功能组合的方法附着上来
优势:
Sorry, something went wrong.
长期来看arkitect 和volcengine-python-sdk这两个库会慢慢合并吗?目前感觉这两个库有挺多重复的结构体定义,比如里面message,tool 定义等等都大差不差,但还又有点不同,用起来还是有点confusing。
不过就automatic tool execute 那个功能我觉得可能得带上human in the loop 的设计 再想一下怎么实现
长期来看arkitect 和volcengine-python-sdk这两个库会慢慢合并吗?目前感觉这两个库有挺多重复的结构体定义,
长期会,最可行的方案还是把 volcengine-python-sdk 当作 arkitect 的依赖,然后尽可能的复用结构体,如果有区别地方应该是可以尽可能合并的,比如 ToolOutput
senw512
wgzesg-bd
No branches or pull requests
参数类型可以支持基础数据类型,pydantic BaseModel, enum 等
The text was updated successfully, but these errors were encountered: