Upgrade protobuf from v4 to v5: 5x Upsert throughput #393
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
Upgrade the protobuf dependancy from v4 (4.25) to v5 (5.28). This
appears to have significantly faster protobuf encoding - I see a 5x
inprovement in Upsert throughput on a given EC2 machine (i3.xlarge)
for large batches (~300) of high dimensionality vectors (1536):
Before:
Performing Populate phase 1675770/138364198 ╸━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1% 0:35:34 44:17:17
Records/sec: 785.2
After:
Performing Populate phase 1531830/138364198 ╸━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1% 0:07:07 10:35:48
Records/sec: 3584.4
I haven't dug into the exact details, but the profile is quite
different - the python frames performing type checking are no longer
present, so I assume they have been optimised, perhaps pushed to
native code?
Collaborator
|
Looks good, thanks! Changing dependencies is a breaking change, but it should go out soon when we release new SDKs for the Oct 15 API version. |
daverigby
added a commit
to pinecone-io/VSB
that referenced
this pull request
Apr 11, 2025
Upgrade pinecone SDK from 5.0 to 6.0. This makes use of protobuf v5.x (pinecone-io/pinecone-python-client#393) which significantly improves upsert throughput (by up to 5x for large batches / high dimentionality)
7 tasks
daverigby
added a commit
to pinecone-io/VSB
that referenced
this pull request
Apr 11, 2025
Upgrade pinecone SDK from 5.0 to 6.0. This makes use of protobuf v5.x (pinecone-io/pinecone-python-client#393) which significantly improves upsert throughput (by up to 5x for large batches / high dimentionality)
daverigby
added a commit
to pinecone-io/VSB
that referenced
this pull request
Apr 11, 2025
Upgrade pinecone SDK from 5.0 to 6.0. This makes use of protobuf v5.x (pinecone-io/pinecone-python-client#393) which significantly improves upsert throughput (by up to 5x for large batches / high dimentionality)
daverigby
added a commit
to pinecone-io/VSB
that referenced
this pull request
Apr 11, 2025
Upgrade pinecone SDK from 5.0 to 6.0. This makes use of protobuf v5.x (pinecone-io/pinecone-python-client#393) which significantly improves upsert throughput (by up to 5x for large batches / high dimentionality) ## Problem Describe the purpose of this change. What problem is being solved and why? ## Solution Describe the approach you took. Link to any relevant bugs, issues, docs, or other resources. ## Type of Change - [ ] Bug fix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected) - [ ] This change requires a documentation update - [ ] Infrastructure change (CI configs, etc) - [ ] Non-code change (docs, etc) - [ ] None of the above: (explain here) ## Test Plan Describe specific steps for validating this change.
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.
Upgrade the protobuf dependancy from v4 (4.25) to v5 (5.28). This
appears to have significantly faster protobuf encoding - I see a 4.5x - 5x
inprovement in Upsert throughput on a given EC2 machine (i3.xlarge)
for large batches (~300) of high dimensionality vectors (1536):
Before:
After:
I haven't dug into the exact details, but the profile is quite
different - the python frames performing type checking are no longer
present, so I assume they have been optimised, perhaps pushed to
native code?
Before profile:
After profile:
Type of Change
Test Plan
Describe specific steps for validating this change.