Results 96 comments of zhjygit

> 只要兼容OpenAI接口且支持工具调用即可,但是不少大模型都错误生成工具调用,例如deepseek v3;kimi会产生一个很稳定的报错我还没找到原因,大意是str属性不存在name属性 意思是,国内模型,当前项目就无法测试的。

> Do you have any reference about supporting rerank model by Ollama? no, i don't know how to test that if the embedding or reranker model can be access. After...

https://ragflow.io/docs/dev/supported_models#Xinference In the doc file as above, ragFlow can use reranker model via Xinference, and not supported for ollama reranker.

解决了吗?我测试的ollama-function-call同样报错,提示“不支持”。 config_list = [ { "model": "llama3", "base_url": "http://127.0.0.1:11434/v1", "api_key": "ollama", } ] llm_config = {"config_list": config_list, "timeout": 120, "temperature": 0}

maybe, you can compile the code to exe.

> The dev tools do support decoding from images, and _could_ be compiled for windows. But there are probably some patches needed and I'd need some help to get (and...

Hi bro, you flash the code to t-deck? Whether we can integrate the IceNav code to the t-deck firmware?Because the T-deck has keyboard, If we flash the to t-deck, we...

> > 哪个环境? > > CVE-2019-17621那个环境 我刚搞定,你是啥具体问题。

> > > > 在docker里仿真固件的时候,不会返回地址,就是我上面那个图里的问题。 没看出来是啥问题。不过我用firmadyne也不行,最后使用firmAE仿真就比较正常。你可以试试。 firmAE仿真如果报错可私信我,[email protected]

> > > > > > > > > > > > > 在docker里仿真固件的时候,不会返回地址,就是我上面那个图里的问题。 > > > > > > 没看出来是啥问题。不过我用firmadyne也不行,最后使用firmAE仿真就比较正常。你可以试试。 firmAE仿真如果报错可私信我,[[email protected]](mailto:[email protected]) > > 谢谢你的帮助,我以一种匪夷所思的方式解决了,我把win11的内存隔离关掉了,重新开机之后再运行就成功返回地址了: ![image](https://user-images.githubusercontent.com/85167677/228238652-720e8aab-435d-4bf2-b9c2-80a516528810.png) 内存隔离是啥?vmware里面的东西吗