Giorgio Robino

@logan-markewich yes, thanks. As a documentation improvement, maybe the page https://langchain.readthedocs.io/en/latest/modules/llms/examples/custom_llm.html could be improved with an example following what suggested @i-am-neo (an LLM already loaded from transformers)

yes, thanks. The documentation has been just improved about it: https://github.com/hwchase17/langchain/issues/936#issuecomment-1422283398 It could be useful to have a notebook that merge your code above here: https://langchain.readthedocs.io/en/latest/ecosystem/huggingface.html#llm

Hi Hector! In facts I agree with the point Eugenio explained. In my case I'd use the serial port (windows/linux) to print on a thermal printer. To see if the...

BTW, I solved, see: http://stackoverflow.com/questions/23489812/ruby-serialport-timeout-exception/23521862#23521862

Another proposal: The spam verification yes/no question is tedious. If I (as annotator) believe that the content is spam, I probably don't want to elaborate. Right? So my best option...

Hi, for me that's a TRUE BUG of Azure OpenAI’s content management policy. When testing a chatbot (made with Azure OpenAI completions, e.g. a deployment using a GPT3.5-Turbo policy) in...

Hi Alex @rattrayalex I agree with you regarding the Azure filter management component responsibility and I just submitted a formal issue to Azure. Nevertheless, reading documentation here: https://help.openai.com/en/articles/6897213-openai-library-error-types-guidance, I'm still...

Thanks Alex, I open a separate issue as you are suggesting.

Well, chatting in Italian I have answers in Italian, but with low quality. See: https://github.com/LAION-AI/Open-Assistant/issues/2659 > I think it caused by chinese messages treees is much lower than English or...

Hi Roberto, I didn't experienced a full "stop working" of the page, but, at times (1 year ago when I developed the code), I experienced a lot of minor issues...