近来,字节跳动的青训营再次扬帆起航,作为第二次参与其中的小北,深感荣幸能借此时机为那些尚未了解青训营的友友们带来一些具体先容。青训营不但是一个技术学习与成长的摇篮,更是一个连接未来与梦想的桥梁~
小北的青训营 X MarsCode 技术训练营——AI 加码,字节跳动青训营入营考核解答(连续更新中~~~)-CSDN博客https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118编辑https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143384787?sharetype=blogdetail&sharerId=143384787&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118
小北的字节跳动青训营与 LangChain 实战课:探索 AI 技术的新边界(连续更新中~~~)-CSDN博客编辑https://blog.csdn.net/Zhiyilang/article/details/143454165https://blog.csdn.net/Zhiyilang/article/details/143454165https://blog.csdn.net/Zhiyilang/article/details/143454165https://blog.csdn.net/Zhiyilang/article/details/143454165https://blog.csdn.net/Zhiyilang/article/details/143454165https://blog.csdn.net/Zhiyilang/article/details/143454165
小北的字节跳动青训营与LangChain系统安装和快速入门学习(连续更新中~~~)。-CSDN博客编辑https://blog.csdn.net/Zhiyilang/article/details/143455380https://blog.csdn.net/Zhiyilang/article/details/143455380https://blog.csdn.net/Zhiyilang/article/details/143455380https://blog.csdn.net/Zhiyilang/article/details/143455380https://blog.csdn.net/Zhiyilang/article/details/143455380https://blog.csdn.net/Zhiyilang/article/details/143455380 小北的字节跳动青训营用LangChain打造“易速鲜花”内部员工知识库问答系统(连续更新中~~~)-CSDN博客编辑https://blog.csdn.net/Zhiyilang/article/details/143456544https://blog.csdn.net/Zhiyilang/article/details/143456544https://blog.csdn.net/Zhiyilang/article/details/143456544https://blog.csdn.net/Zhiyilang/article/details/143456544https://blog.csdn.net/Zhiyilang/article/details/143456544https://blog.csdn.net/Zhiyilang/article/details/143456544小北的字节跳动青训营与提示工程(上):用少样本FewShotTemplate和ExampleSelector创建应景文案(连续更新中~~~)-CSDN博客https://blog.csdn.net/Zhiyilang/article/details/143468624?sharetype=blogdetail&sharerId=143468624&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143468624?sharetype=blogdetail&sharerId=143468624&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118https://blog.csdn.net/Zhiyilang/article/details/143468624?sharetype=blogdetail&sharerId=143468624&sharerefer=PC&sharesource=Zhiyilang&spm=1011.2480.3001.8118小北的字节跳动青训营与提示工程(下):用思维链和思维树提升模型思索质量(连续更新中~~~)-CSDN博客https://blog.csdn.net/Zhiyilang/article/details/143494432https://blog.csdn.net/Zhiyilang/article/details/143494432小北的字节跳动青训营与调用模型:调用模型:OpenAI API vs 微调开源Llama2/ChatGLM(连续更新中~~~)-CSDN博客https://blog.csdn.net/Zhiyilang/article/details/143495077哈喽哈喽,这里是是zyll~,北浊.接待来到小北的 LangChain 实战课学习条记!
输出格式: The output should be formatted as a JSON instance that conforms to the JSON schema below.
As an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}}
the object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.
具体来说,输出的一个提示是如许的: 提示: 您是一位专业的鲜花店文案撰写员。 对于售价为 20 元的 康乃馨 ,您能提供一个吸引人的简短中文描述吗?
The output should be formatted as a JSON instance that conforms to the JSON schema below.
As an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}}
the object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.
Here is the output schema:
langchain.schema.output_parser.OutputParserException: Failed to parse Flower from completion {'name': '康乃馨', 'colors': ['粉红色','白色']}. Got: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)
我们通过一个示例来演示如何利用重试剖析器。假设我们有一个输出不完备的响应,利用OutputFixingParser无法完全修复。此时,我们可以利用RetryWithErrorOutputParser来尝试重新生成完备的输出。这个剖析器没有让我们失望,乐成地还原了格式,甚至也根据传入的原始提示,还原了action_input字段的内容。RetryWithErrorOutputParser的parse结果:action='search' action_input='colors of Orchid'
总结