Adjust default values for better performance #6844
Merged
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
timvisee
approved these changes
Jul 10, 2025
This comment was marked as resolved.
This comment was marked as resolved.
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/redoc/master/openapi.json(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (14)
- GitHub Check: test-shard-snapshot-api-s3-minio
- GitHub Check: test-snapshot-operations-s3-minio
- GitHub Check: Basic TLS/HTTPS tests
- GitHub Check: test-low-resources
- GitHub Check: test-consistency
- GitHub Check: test-consensus-compose
- GitHub Check: integration-tests
- GitHub Check: integration-tests-consensus
- GitHub Check: rust-tests (macos-latest)
- GitHub Check: rust-tests (windows-latest)
- GitHub Check: rust-tests-no-rocksdb (ubuntu-latest)
- GitHub Check: rust-tests (ubuntu-latest)
- GitHub Check: lint
- GitHub Check: storage-compat-test
Comment on lines
+7250
to
7252
| "description": "Maximum size (in kilobytes) of vectors allowed for plain index, exceeding this threshold will enable vector indexing\n\nDefault value is 10,000, based on experiments and observations.\n\nTo disable vector indexing, set to `0`.\n\nNote: 1kB = 1 vector of size 256.", | ||
| "default": null, | ||
| "type": "integer", |
There was a problem hiding this comment.
default field contradicts the new description
The description states “Default value is 10 000”, yet the "default" property is still null. Tools that generate clients or perform validation will treat null as the canonical default, not the textual explanation.
- "default": null,
+ "default": 10000,Align the JSON schema with the documented behavior to avoid silent misconfigurations.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "description": "Maximum size (in kilobytes) of vectors allowed for plain index, exceeding this threshold will enable vector indexing\n\nDefault value is 10,000, based on experiments and observations.\n\nTo disable vector indexing, set to `0`.\n\nNote: 1kB = 1 vector of size 256.", | |
| "default": null, | |
| "type": "integer", | |
| "description": "Maximum size (in kilobytes) of vectors allowed for plain index, exceeding this threshold will enable vector indexing\n\nDefault value is 10,000, based on experiments and observations.\n\nTo disable vector indexing, set to `0`.\n\nNote: 1kB = 1 vector of size 256.", | |
| "default": 10000, | |
| "type": "integer", |
🤖 Prompt for AI Agents
In docs/redoc/master/openapi.json around lines 7250 to 7252, the "default" field
is set to null, which contradicts the description stating the default value is
10,000. Update the "default" property to 10000 to match the documented default
value and ensure consistency between the schema and its description.
|
Are we expecting an improvement on the CI benchmark after this PR? |
No, CI benchmarks have explicitly configured values |
coszio
approved these changes
Jul 10, 2025
generall
added a commit
that referenced
this pull request
Jul 17, 2025
* adjsut default values for better performance * upd openapi
3 tasks
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.
indexing_threshold: 20k -> 10kmax_segment_size: 200mb -> 256mb per CPU core