fix: cosine distance (#231)

* fix: cosine distance Signed-off-by: Keming <kemingyang@tensorchord.ai> * fix sq and pq Signed-off-by: Keming <kemingyang@tensorchord.ai> * fix doc Signed-off-by: Keming <kemingyang@tensorchord.ai> --------- Signed-off-by: Keming <kemingyang@tensorchord.ai>
tensorchord · Jan 6, 2024 · 4aafd8c · 4aafd8c
1 parent f30a10c
commit 4aafd8c
Show file tree

Hide file tree

Showing 4 changed files with 15 additions and 15 deletions.
diff --git a/README.md b/README.md
@@ -106,7 +106,7 @@ We support three operators to calculate the distance between two vectors.
 
 - `<->`: squared Euclidean distance, defined as $\Sigma (x_i - y_i) ^ 2$.
 - `<#>`: negative dot product, defined as $- \Sigma x_iy_i$.
-- `<=>`: negative cosine similarity, defined as $- \frac{\Sigma x_iy_i}{\sqrt{\Sigma x_i^2 \Sigma y_i^2}}$.
+- `<=>`: cosine distance, defined as $1 - \frac{\Sigma x_iy_i}{\sqrt{\Sigma x_i^2 \Sigma y_i^2}}$.
 
 ```sql
 -- call the distance function through operators
@@ -115,7 +115,7 @@ We support three operators to calculate the distance between two vectors.
 SELECT '[1, 2, 3]'::vector <-> '[3, 2, 1]'::vector;
 -- negative dot product
 SELECT '[1, 2, 3]'::vector <#> '[3, 2, 1]'::vector;
--- negative cosine similarity
+-- cosine distance
 SELECT '[1, 2, 3]'::vector <=> '[3, 2, 1]'::vector;
 ```
 

diff --git a/crates/service/src/instance/metadata.rs b/crates/service/src/instance/metadata.rs
@@ -18,7 +18,7 @@ pub struct Metadata {
 }
 
 impl Metadata {
-    const VERSION: u64 = 2;
+    const VERSION: u64 = 3;
     const SOFT_VERSION: u64 = 1;
 }
 

diff --git a/crates/service/src/prelude/global/f16_cos.rs b/crates/service/src/prelude/global/f16_cos.rs
@@ -13,7 +13,7 @@ impl G for F16Cos {
     type L2 = F16L2;
 
     fn distance(lhs: &[F16], rhs: &[F16]) -> F32 {
-        super::f16::cosine(lhs, rhs) * (-1.0)
+        F32(1.0) - super::f16::cosine(lhs, rhs)
     }
 
     fn elkan_k_means_normalize(vector: &mut [F16]) {
@@ -47,7 +47,7 @@ impl G for F16Cos {
             x2 += _x * _x;
             y2 += _y * _y;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -73,7 +73,7 @@ impl G for F16Cos {
             x2 += _x * _x;
             y2 += _y * _y;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -103,7 +103,7 @@ impl G for F16Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -134,7 +134,7 @@ impl G for F16Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -166,7 +166,7 @@ impl G for F16Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 }
 

diff --git a/crates/service/src/prelude/global/f32_cos.rs b/crates/service/src/prelude/global/f32_cos.rs
@@ -13,7 +13,7 @@ impl G for F32Cos {
     type L2 = F32L2;
 
     fn distance(lhs: &[F32], rhs: &[F32]) -> F32 {
-        cosine(lhs, rhs) * (-1.0)
+        F32(1.0) - cosine(lhs, rhs)
     }
 
     fn elkan_k_means_normalize(vector: &mut [F32]) {
@@ -47,7 +47,7 @@ impl G for F32Cos {
             x2 += _x * _x;
             y2 += _y * _y;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -73,7 +73,7 @@ impl G for F32Cos {
             x2 += _x * _x;
             y2 += _y * _y;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -103,7 +103,7 @@ impl G for F32Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -134,7 +134,7 @@ impl G for F32Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 
     #[multiversion::multiversion(targets(
@@ -166,7 +166,7 @@ impl G for F32Cos {
             x2 += _x2;
             y2 += _y2;
         }
-        xy / (x2 * y2).sqrt() * (-1.0)
+        F32(1.0) - xy / (x2 * y2).sqrt()
     }
 }