Avoid copy by using VectorView and update benchmark.py for sqlite-vec #21
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Outdated suggestions cannot be applied.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.
This PR does 3 things:
vector_distance
,vector_to_json
,vector_from_json
asSQLITE_INNOCUOUS
andSQLITE_DETERMINISTIC
see https://sqlite.org/forum/forumpost/4a8b1f9d3b . So that brute force with vectorlite can be simply done byselect rowid from my_table order by vector_distance(some_vector, embedding, 'l2') asc limit 10
The benchmark data will be updated when I get access to my PC.