Piotr Mardziel

> The RAG successfully runs the query but the metrics do not get computed. Any suggestions on how to fix? Hi @JIAWENee , can you include the code that sets...

Note that the problem does not occur if the first line is just the triple quotes.

Hi; this is a tough one to debug. If you see it happen next time, can you collect information for us about open handles in the process trulens is running...

Hi; can you add abstract definitions of the new methods to db.py class DB ?

Thanks for the abstract definitions. A few smaller things: - Can you add docstrings to the abstract methods (you can reference the abstract ones form the non-abstract ones instead of...

> > * format.sh --eval" > > Formatting ./trulens_eval format.sh: line 14: isort: command not found format.sh: line 15: yapf: command not found You can install these with pip.

Thanks; can you also add this as a suggestion to proper names formatting in `/docs/trulens_eval/contributing/standards.md`. I presume this only applies to cases were markdown is used but you can make...

Hi @atulm-encora , the screeshot you shared shows that 6 feedbacks were computed. You can ignore the last line that says "Waiting for Runs" as that will show "0/32" if...

Hi @anotine10 , looks like this was fixed in some recent changes in how main app input is determined. I'm seeing the context work with chain3.invoke . Please let us...

Hi; what is the reasoning here? Does Huggingface have generative models for defining `LLMProvider._create_chat_completion` ?