Luolin Zhang
Luolin Zhang
> The issue with LaTeX formulas not rendering on your Dify conversation page might be related to the dependencies responsible for LaTeX rendering. Dify uses the following libraries for this...
My server's /use/local/bin folder does not contain the pm2 file, so I can't restart the node service using this command. Additionally, I noticed that these three libraries are also listed...
说到引用,能不能实现引用对话的内容?类似豆包的这个功能,选中对话中的一段文字,作为上下文: 
> 补充一下，目前lobechat上传文件后还需要等待向量化才送给大模型。有些PPT或PDF文件本身有比较复杂的图表时会报错向量化失败。但是其他类似的平台例如cherry studio似乎是将整个文件发送给大模型，速度快而且读的内容更精准。 我也用过cherry,只有少数服务商的api支持直接接收文件,按作者说的没有单独适配的api其实都是本地解析出文件内容再发送
> > 说到引用,能不能实现引用对话的内容?类似豆包的这个功能,选中对话中的一段文字,作为上下文: > >  > > 这个功能有什么场景？现在发送消息时应该是会把 chat history 作为上下文一起发送？ 更方便的定位在上下文中需要详细解释或者提问的内容
These features are very useful, especially the content vector embedding based on the embedding model and relevance retrieval, which are highly effective for finding semantically related but keyword-ambiguous content