Li Yang
Li Yang
maybe you confused `ai_classifier` with `ai_model`? ```python @ai_classifier class Sentiment(Enum): """ Score the sentiment of provided text. """ POSITIVE = 1 NEGATIVE = -1 Sentiment.as_prompt("") >> { 'messages': [ {...
As of [Jan 19](https://pandas.pydata.org/docs/dev/whatsnew/v2.2.0.html), `calamine` is now supported as an engine in `pandas` - I don't see any reason not to just have one processor for `.xls, .xlsx, .xlsm, .xlsb...
closed #1016
fwiw i don't think this image is "legacy". you can continue to use it as before: ``` template = ( Template() .from_image("e2bdev/code-interpreter:latest") .run_cmd("pip install {{ }}") .set_start_cmd( ".jupyter/start-up.sh", wait_for_url("http://localhost:49999/health") )...
> @hewliyang please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information. > > ``` > @microsoft-github-policy-service agree [company="{your company}"] >...
> @hewliyang please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information. > > ``` > @microsoft-github-policy-service agree [company="{your company}"] >...
> @hewliyang thanks for the PR. Our typical use case is including this data as context in an LLM. Do you think your suggested changes, NaN -> "", Unnamed:{I} ->...
> For empty values, "" is definitely better than NaN. Although I'm not sure if we want to remove empty columns, that would be transforming the structure of the data....
> Arguably, if the xlsx cell is empty, the conversion should be empty. > > If the excel value is "#N/A" then I believe it should be interpreted as NaN...