refactor: convert chunk embedding to one API call #24
Conversation
This file contains hidden or 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
Member
|
LFG - will review. Thank you! |
Member
|
@jwaltz can you run |
Contributor
Author
|
@timothycarambat no problem, linted and committed. |
Contributor
|
is there a reason this isn't merges (other than merge conflicts)? Anything that could enhance speed would be helpful. |
Member
|
Moved to #153 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
I was having really long embed times for a couple large .docx documents ingested through the
/hotdir. One had 256 chunks and took many minutes to fully embed, sometimes never finishing at all.I converted the
embedChunk()method to accept a list of chunks instead of just one chunk, and make a single call to OpenAI's embedding API endpoint, which seems to have sped up the embed process dramatically. The refactoredembedChunks()required some changes to its usage inaddDocumentToNamespace()as well. I included these changes for the 3 vector db options at/server/utils/vectorDbProviders/[vectorDb]/index.jsLet me know what you think and if this is helpful. Again, apologies for my editor's lsp changing some of the method signatures and line-length formatting, hope it is ok.