hackiey
hackiey
I'm confused about the _run_controller, if I use the lstm as controller, the dimension of controller_input should be 3, so the controller_input = controller_input[:, None, :] because the lstm call...
### 💻 系统环境 | Operating System Other ### 🌐 浏览器 | Browser Edge ### 🐛 问题描述 | Bug Description dalle3的systemRole里,工具名称是Dall.E 3,prompt里是dalle,但function name是dalle3____text2image____builtin。 因为这段system prompt是OpenAI训练Dalle3作为内置工具的prompt,所以会有偶发的function call中name为"dalle“的情况,导致后续失败。建议内置工具(尤其是OpenAI的内置工具)可以直接用原名,其他类型的tool可以拼上前后缀做独特identifier ### 🚦 期望结果 | Expected...
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答? | Is there an...
### 🥰 需求描述 目前的tool_calls机制仅在调用工具的时候使用了tools参数,拿到工具返回后仍使用role=function继续调用。看代码似乎没有实现当tool_calls数组有多个时分别调用多个function。 ### 🧐 解决方案 应参考OpenAI的官方案例,在遇到tool_calls的assistant消息时,将该消息插入在历史messages中,并将tool_calls数组中的每个tool进行调用,得到结果后同样插入历史messages中。 原工具调用链 调用时: ```json [ {"role": "user", "content": "北京和上海天气怎么样"}, {"role": "assistant", "content": "请稍等,我将为您查询天气", "tool_calls": [ {"id": "xxx", "type": "function", "function": {"name": "get_weather", "arguments":...
### 🥰 需求描述 因为需求配置key、网络和性能等原因,我在部署时删除了一些plugin,导致有些从市场添加的Agent无法正常运行 ### 🧐 解决方案 1. 在Agent市场展示该Agent需要的plugin(并展示plugin商店中是否有该plugin) 2. 添加Agent时提醒所需plugin是否安装成功 ### 📝 补充信息 _No response_