Rangehow
Rangehow
> 我也遇到了一样的问题，你解决了吗？ 没有。而且问题和offline环境变量也没关系，换日志记录吧，wandb似乎不止要拷走工作目录下的log，还要拷走一个artifacts文件才能正常sync。
> Is it reproducible? This problem occurs from time to time, and I don't know the reason.
@tonysy 请问这个问题还有在跟进吗？例如opencompass/ai2_arc-dev这个dataset id，似乎已经在huggingface仓库中删除了？在modelscope中也不存在，请问该如何对齐呢？
Hi @Hua-Wu-Que-Code, this is a very good use case contribution. As an example submitted to a public repository, you could refer to: [https://github.com/gusye1234/nano-graphrag/blob/main/examples/using_ollama_as_llm.py](https://www.google.com/url?sa=E&q=https%3A%2F%2Fgithub.com%2Fgusye1234%2Fnano-graphrag%2Fblob%2Fmain%2Fexamples%2Fusing_ollama_as_llm.py) Firstly, for model paths, it's best to...
It should be added that the length of a chunk is sensitive to both the embedding model and the LLM (API), so it’s hard to say there’s a necessity to...
From my personal perspective, the scope of this PR is much broader than the custom length mentioned in #111. This PR moves most of the logic from the user-invisible `get_chunks`...
Hello, could you elaborate on the necessity of switching from JSON to JSON5? It would be helpful to provide some practical examples. Since this requires installing an additional external library,...
Not sure which version you are using, but I tested the json you provided here without any problem. From your trace back, it seems that you are using the deprecated...
Which file are you running?
Yes, openai api requires payment. You may need to set API_KEY before requesting it. Or you can try local llm following instruction in /example