dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

fix(stores): Stores fixes and testing (#4663)

Browse source 
* fix(stores): Actually check a vector is a unit vector/normalized

Instead of just summing the components to see if they equal 1.0, take
the actual magnitude/p-norm of the vector and check that is
approximately 1.0.

Note that this shouldn't change the order of results except in edge
cases if I am too lax with the precision of the equality
comparison. However it should improve performance for normalized
vectors which were being misclassified.

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(stores): Add tests for known results and triangle inequality

This adds some more tests to check the cosine similarity function has
some expected mathematical properties.

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
This commit is contained in:
Richard Palethorpe 2025-01-22 18:35:05 +00:00 • committed by GitHub
parent e15d29aba2
commit e8eb0b2c50
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 141 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

14
backend/go/stores/store.go
View file

@ -311,12 +311,16 @@ func (s *Store) StoresGet(opts *pb.StoresGetOptions) (pb.StoresGetResult, error)
}
func isNormalized(k []float32) bool {
var sum float32
var sum float64
for _, v := range k {
sum += v
v64 := float64(v)
sum += v64*v64
}
return sum == 1.0
s := math.Sqrt(sum)
return s >= 0.99 && s <= 1.01
}
// TODO: This we could replace with handwritten SIMD code
@ -328,7 +332,7 @@ func normalizedCosineSimilarity(k1, k2 []float32) float32 {
dot += k1[i] * k2[i]
}
assert(dot >= -1 && dot <= 1, fmt.Sprintf("dot = %f", dot))
assert(dot >= -1.01 && dot <= 1.01, fmt.Sprintf("dot = %f", dot))
// 2.0 * (1.0 - dot) would be the Euclidean distance
return dot
@ -418,7 +422,7 @@ func cosineSimilarity(k1, k2 []float32, mag1 float64) float32 {
sim := float32(dot / (mag1 * math.Sqrt(mag2)))
assert(sim >= -1 && sim <= 1, fmt.Sprintf("sim = %f", sim))
assert(sim >= -1.01 && sim <= 1.01, fmt.Sprintf("sim = %f", sim))
return sim
}