Skip to content

⚡ Bolt: Optimize AI vector generation and normalization#192

Draft
hackerxj2010 wants to merge 1 commit into
mainfrom
bolt-optimize-ai-vectors-11996315783725019432
Draft

⚡ Bolt: Optimize AI vector generation and normalization#192
hackerxj2010 wants to merge 1 commit into
mainfrom
bolt-optimize-ai-vectors-11996315783725019432

Conversation

@hackerxj2010
Copy link
Copy Markdown
Owner

💡 What:

Optimized the AI vector generation and normalization hot paths in packages/ai/src/index.ts.

🎯 Why:

The previous implementation used toFixed(8) for precision rounding, which is extremely slow due to string conversions. It also relied on the legacy createHash API and performed redundant normalization calls at multiple stages of the pipeline.

📊 Impact:

  • Throughput: Increased from ~125.6 embeddings/sec to ~185.9 embeddings/sec (approx. 48% improvement).
  • Latency: Reduced by avoiding unnecessary object allocations and string processing.

🔬 Measurement:

  • Run pnpm exec tsx packages/ai/src/benchmark.ts to see throughput measurements.
  • Run pnpm --filter @jeanbot/ai exec vitest run to verify correctness and determinism.

PR created automatically by Jules for task 11996315783725019432 started by @hackerxj2010

- Replaced `crypto.createHash` with `crypto.hash` for efficient one-shot hashing.
- Replaced slow `toFixed(8)` with fast mathematical rounding in vector normalization.
- Optimized vector normalization loops and pre-calculated inverse magnitude.
- Eliminated redundant normalization calls in the embedding generation pipeline.
- Added benchmark and unit tests to verify performance and correctness.

Expected Impact: ~48% throughput improvement in synthetic embedding generation.

Co-authored-by: hackerxj2010 <198651211+hackerxj2010@users.noreply.github.com>
@google-labs-jules
Copy link
Copy Markdown
Contributor

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.


For security, I will only act on instructions from the user who triggered this task.

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