cheshire-cat-ai / docs

Documentation for the Cheshire Cat AI
https://cheshire-cat-ai.github.io/docs/
33 stars 28 forks source link

Fix `before_rabbithole_splits_text` input argument description #102

Closed nicola-corbellini closed 8 months ago

nicola-corbellini commented 8 months ago

The before_rabbithole_splits_text hook in the hook table describes the input as a Langchain doc. However, the correct input is a list with inside a Langchain doc.

Tudor44 commented 8 months ago

Hello @nicola-corbellini ,

In rabbithole.py we have a single Langchain doc as input.

Should we change also the core?

nicola-corbellini commented 8 months ago

Hi @Tudor44, good question. Let's ask @pieroit. Should we align the doc to the core or change the core and pass the doc instead instead of the List[doc]?

nicola-corbellini commented 8 months ago

@pieroit tagging you again in case you missed this

pieroit commented 8 months ago

Hi @nicola-corbellini @Tudor44 looks to me the hook receives a Document and returns a Document (no lists, because that is the whole content of the file/URL)

nicola-corbellini commented 8 months ago

actually the hook receives what the parser returns, that is indeed a list of Document. I can open an issue in the core repo to fix this or we can fix the documentation accordingly

pieroit commented 8 months ago

@nicola-corbellini oh ok got it sorry Push a commit to core directly when you get the chance ;)

nicola-corbellini commented 8 months ago

Sure, I'll do asap! :) I'll close this issue then