Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Similarity from query is greater than 1 and does not match too #104

Open
sairash opened this issue Jan 7, 2025 · 0 comments
Open

Similarity from query is greater than 1 and does not match too #104

sairash opened this issue Jan 7, 2025 · 0 comments

Comments

@sairash
Copy link

sairash commented Jan 7, 2025

When having embedding like this ->

[-0.07083614 0.12190464 0.025770642 -0.039472707 -0.12028625 0.056348786 -0.15252885 0.0042825416 -0.00023576897 0.0263003 0.2609792 -0.066559464 -0.24802631 -0.007337872 0.000101908576 0.1345756 -0.15539747 -0.052619018 -0.2015995 -0.124964945 -0.07976487 0.057311438 0.043585703 0.06952152 -0.0772083 -0.34031448 -0.078466505 -0.10305231 0.109324776 -0.14144775 -0.056200445 -0.03891104 -0.13330732 -0.07326787 0.10166346 0.024927747 -0.10640622 -0.13536835 0.23431908 0.004784152 -0.1210499 0.100829296 0.10013285 0.32314882 0.22357354 0.0438594 0.036317103 -0.010869566 0.077771656 -0.20320293 0.09037393 0.2337631 0.18030888 0.101348296 0.06855987 -0.1219093 0.013430927 0.21057314 -0.15934649 0.08435744 0.004779402 -0.006034756 -0.06905728 -0.1231056 0.18838042 0.12991679 -0.18514541 -0.23120442 0.07723315 -0.11382575 -0.07632307 0.10347416 -0.14789738 -0.1977503 -0.24588855 0.06917821 0.3577754 0.14115238 -0.3053733 0.004435137 -0.023189519 -0.1141416 -0.013000004 0.1225572 -0.096868664 -0.059129596 -0.049395315 -0.019225594 0.1567679 -0.017110191 -0.04435732 0.2090028 0.032425143 -0.046653178 0.075279124 0.12553018 -0.15518479 -0.08281295 -0.10542522 -0.067100465 0.056343548 -0.14048672 -0.056614153 0.045450583 -0.18762243 0.24965154 0.0020598024 0.0044965744 0.0034101792 0.010916386 -0.058495305 -0.00034603477 0.25038373 -0.31473136 0.1770426 0.22536507 0.063099675 0.11881032 0.13684323 0.07832798 0.01532745 0.044129185 -0.14497943 -0.1754754 -0.027552057 -0.048475202 0.016123436 0.029926114]

I am getting similarity more than 1.
For example:
When I query the same embedding as above I get the similarity value as 1.5220202 and if I query a completely random embedding that has no correlational or similarity with other documents in the collection I get 1.3222984.

Can you please help me fix this problem? Thanks.

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

No branches or pull requests

1 participant