chenk-gd
chenk-gd
What is the recommended practice if one wishes to use the output of the previous ActionNode as part of the prompt of the next ActionNode's fill method? The current MetaGPT...
Looked at ActionNode and was quite confused. Can't see what role ActionNode mainly plays and what it does. There is an example of generating a Fibonacci series online. On this...
传过去的stop参数：['✿RESULT✿', '✿RESULT✿:', '✿RESULT✿:\n', 'Observation:', 'Observation:\n']，超过了OpenAI的限制
见https://qwenlm.github.io/zh/blog/qwen-agent-2405/的内容
有这样一个场景：公司前端团队开发了一套组件和页面模板。目前开发流程通常是找一个相近的页面模板，拷贝过来在上面修改。考虑用大模型提供一些帮助。 目前尝试用ReACT Agent去做。做了2个工具。一个是根据名称查找页面模板，返回模板代码；另外一个是根据返回的代码，加上用户修改的需求，让大模型生成页面。但有几个问题： 1. ReACT第一步的Thought可以正确判断使用的工具，调用工具返回页面模板代码。但如果页面模板比较大，第二步的Thought就有问题，它会忘记它是需要根据第一步返回模板生成新的代码，而是变成去解释返回的模板代码，提出改进意见。如下： Thought: The provided code snippet is a Vue component that manages a table for listing and operating on hosts, with functionalities such as pagination, selection...
分块阅读后将相关回答合并作为summary的knowledge，感觉效果没有太大差别。 ``` # 修改parallel_doc_qa.py的第226和227行 # retrieve_content = self._retrieve_according_to_member_responses(messages=messages, lang=lang, query=query) # return self.summary_agent.run(messages=messages, lang=lang, knowledge=retrieve_content) return self.summary_agent.run(messages=messages, lang=lang, knowledge=member_res) ```
There are multiple actions in a role and these actions are excuted in by-order mode. But sometimes the action may fail and need to be retried. Check the result of...
Suppose there is a multi-turn dialog: USER: What is the name of the hero of the novel The Count of Monte Cristo? ASSISTANT：The hero of the novel "The Count of...
### Describe your problem Planning to use infinity on k8s, not going to use server version of infinity for some reason. However, since there are more than 1 pod copy,...