Skip to content

perf: reduce multi-namespace retrieval latency - #155

Merged
suguanYang merged 1 commit into
stagingfrom
perf/wangbinqi/concurrent-namespace-retrieval
Aug 24, 2026
Merged

perf: reduce multi-namespace retrieval latency#155
suguanYang merged 1 commit into
stagingfrom
perf/wangbinqi/concurrent-namespace-retrieval

Conversation

@suguanYang

Copy link
Copy Markdown
Contributor

Summary

  • query up to four retrieval namespaces concurrently
  • retry only rate-limited namespace failures sequentially
  • add regression coverage for concurrency limits and fallback behavior

Test plan

  • pnpm exec vitest run src/domains/chat
  • pnpm run typecheck
  • pnpm exec eslint src/domains/chat/index.ts src/domains/chat/index.test.ts

Made with Cursor

Run independent namespace searches concurrently while retrying only rate-limited failures sequentially.

Co-authored-by: Cursor <cursoragent@cursor.com>
@vercel

vercel Bot commented Aug 24, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
knowhere-notebook-staging Ready Ready Preview Aug 24, 2026 3:09am
1 Skipped Deployment
Project Deployment Actions Updated (UTC)
knowhere-notebook Ignored Ignored Aug 24, 2026 3:09am

Request Review

@suguanYang
suguanYang merged commit 1b8afdd into staging Aug 24, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant