Why it matters
Debugging semantic search means checking whether two embeddings really are close.
Paste vectors from your model's output and see every pair ranked.
How to use it
- Type or paste your input; the example shows the format.
- Press Compare. Results also update as you type.
- Read the summary line, then the table, notes or output below it.
- Copy or download what you need. Nothing leaves this page.
FAQ
Cosine or dot product?
For normalised vectors they rank identically; cosine is safer otherwise.
What's a good cosine score?
It depends on the model; compare against known related and unrelated pairs.
Is my input uploaded?
No. The tool runs in your browser and nothing you type, paste or open is sent anywhere.
Can I rely on the result?
It follows the public specification or formula named on this page and says where it simplifies. Check anything critical against the official tool or documentation before you ship it.