perf: small fix for the insert-method of pgvector #1004
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Outdated suggestions cannot be applied.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.
Please describe the purpose of this pull request.
Thankfully @sarahwooders provided a fix for #988 , but assumed a fixed chunk size of 1,000 for
pg8000
which slows down the ingestion-process significantly and is not future-proof.So I added a small method to get the optimal chunk size based on the number of columns in the database.
How to test
memgpt load directory --name <some_name> --input-files=<very_large_input_files>
Have you tested this PR?
I tested it with several very large PDFs and TXTs (around 1.000 pages of scientific content).
Related issues or PRs
#988
Is your PR over 500 lines of code?
No.