improve corpus UX and fix docs #498
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
pmeier
commented
Aug 21, 2024
There was a problem hiding this comment.
Changes in this file are mostly to properly support the corpus feature. Previously the corpus_name was ignored and everything was stored in the global corpus instead.
There was a problem hiding this comment.
Just minor cleanup in this file. Instead of hardcoding the corpus name in multiple places, I added a corpus_name variable and used that in the appropriate places.
|
This was "reviewed" already in #493. Thus, I'm going to self-merge when CI is green. |
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
corpus-devbranch break the documentation. This supersedes fix doc builds after recent changes #494.corpus_name=Nonesentinel and usecorpus_name="default"instead. See Support for metadata filter suggestions in the web UI #493 (comment)corpus_name="default"when creating a chat to avoid forcing users to pass something. The default handling is thus pushed to the author of the source storage.input=Nonewhen creating a chat. This way users with a corpus of documents can just ask away. I've added proper error handling in case we are unable to retrieve any sources.