Concurrent batch vectorization requests #4827
Open
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
dirkkul
changed the title
aliszka
reviewed
May 6, 2024
aliszka
approved these changes
May 15, 2024
|
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Outdated suggestions cannot be applied.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.
What's being changed:
Send batch requests concurrently if the rate limit is high enough, otherwise keep sequential batching. For example Cohere allows 10k requests/min and we can basically send as many requests in parallel as we want.
With this the 100k sphere dataset with 2 named vectors was vectorized in ~2min using cohere and
collection.batch.fixed_size(concurrent_requests=20, batch_size=96).To test use this python client branch weaviate/weaviate-python-client#981 and the profiling/test_sphere.py script.
Review checklist