clipsheep6 comments

Results 7 comments of


                                            clipsheep6

【功能建议】文字底部有水印也会被识别出来，能不能不识别水印

@hiroi-sora 是否考虑增加类似如下链接中的简单水印去除方法？对于字体相近的水印去除效果还不错 https://cloud.tencent.com/developer/article/1894330

OPENAI_BASE_URL 和 OPENAI_PROXY无法同时生效？

@voidking any solution to this issue got same issue , working behind a proxy while using a 3rd party openai API URL need use a system proxy to access internet...

runtime error show when install C lang server

@alexwebdevs issue still exist , run with Cursor-0.1.6.AppImage ``` 16:10:16.334 › Store does not have language downloaded c 16:10:16.334 › INSTALLING 16:10:17.097 › Error occurred in handler for 'installLS': Error:...

any plan to support a proxy setting?

Strongly agree

使用PDF提取工具变成了markdown

@drunkpig 其实除了训练数据，给人阅读版本的mark down也很有价值，最简单的应用就是文本扔到类似notebooklm 这样的应用里做学习使用

Is it possible to use the knowledge of the LLM instead of web search to write the report?

Support Mcp to add local knowledge /others mcp service as part of search looks good to enhance

Any idea how to set OPENAI_BASE_URL and system proxy？

it seems code in here only passing the OPENAI_API_KEY. https://github.com/yanniedog/Autocrew/blob/d885b22a0e7277d69090dfae30ddcd0f04dc8733/core.py#L184 a new config or env reading here is needed