Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: handle 'null' value in chunking 'chunk_column' #340

Merged
merged 1 commit into from
Jan 7, 2025

Conversation

JamesGuthrie
Copy link
Member

@JamesGuthrie JamesGuthrie commented Jan 6, 2025

The chunking configuration takes a 'chunk_column' parameter, which determines which column of the source row is chunked.

This commit treats a null entry as being equivalent to the empty string, and no embeddings are generated.

Fixes #334

@JamesGuthrie JamesGuthrie requested a review from a team as a code owner January 6, 2025 15:31
Copy link
Contributor

@Askir Askir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me, tests seem to fail because of incorrect API keys? Bit confused, did someone upload new ones or did ours time out?

@JamesGuthrie JamesGuthrie force-pushed the jg/handle-null-contents-column branch from 8a7f1d0 to 030bca0 Compare January 7, 2025 08:31
The chunking configuration takes a 'chunk_column' parameter, which
determines which column of the source row is chunked.

This commit treats a null entry as being equivalent to the empty string,
and no embeddings are generated.
@JamesGuthrie JamesGuthrie force-pushed the jg/handle-null-contents-column branch from 030bca0 to ac8f340 Compare January 7, 2025 08:39
@JamesGuthrie
Copy link
Member Author

Looks good to me, tests seem to fail because of incorrect API keys? Bit confused, did someone upload new ones or did ours time out?

Honestly I don't remember. I've replaced the broken ones.

@JamesGuthrie JamesGuthrie merged commit f283b6c into main Jan 7, 2025
5 checks passed
@JamesGuthrie JamesGuthrie deleted the jg/handle-null-contents-column branch January 7, 2025 08:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Bug]: Null items in source table cause problems
3 participants