usearch 0.9.0 → 0.9.2

package/.github/workflows/release.yml

@@ -166,6 +166,9 @@ jobs:
     name: Publish Docker Image
     needs: versioning
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
     steps:
     - uses: actions/checkout@v3
       with:
@@ -177,7 +180,7 @@ jobs:
         username: ${{ secrets.DOCKERHUB_USERNAME }}
         password: ${{ secrets.DOCKERHUB_TOKEN }}
     - name: Log in to GitHub Registry
-      uses: docker/login-action@2
+      uses: docker/login-action@v2
       with:
         registry: ghcr.io
         username: ${{ github.actor }}
@@ -186,7 +189,7 @@ jobs:
       uses: docker/setup-buildx-action@v2
     - name: Extract tags & labels for Docker
       id: meta
-      uses: docker/metadata-action@4
+      uses: docker/metadata-action@v4
       with:
         images: |
           unum/usearch

package/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "usearch"
-version = "0.9.0"
+version = "0.9.2"
 authors = ["Ashot Vardanian <1983160+ashvardanian@users.noreply.github.com>"]
 description = "Smaller & Faster Single-File Vector Search Engine from Unum"
 edition = "2021"

package/README.md

@@ -66,11 +66,11 @@ Both USearch and FAISS implement the same HNSW algorithm.
 But they differ in a lot of design decisions.
 USearch is designed to be compact and broadly compatible without sacrificing performance.
 
-|            | FAISS, `f32` | USearch, `f32` | USearch, `f16` | USearch, `f8` |
-| :--------- | -----------: | -------------: | -------------: | ------------: |
-| Insertions |       76 K/s |         89 K/s |         73 K/s |   **137 K/s** |
-| Queries    |      118 K/s |        167 K/s |        140 K/s |   **281 K/s** |
-| Recall @1  |          99% |          99.2% |            98% |     **99.2%** |
+|            | FAISS, `f32` | USearch, `f32` | USearch, `f16` | USearch, `f8` | USearch + Numba, `f32` |
+| :--------- | -----------: | -------------: | -------------: | ------------: | ---------------------: |
+| Insertions |       76 K/s |         89 K/s |         73 K/s |   **137 K/s** |                 99 K/s |
+| Queries    |      118 K/s |        167 K/s |        140 K/s |   **281 K/s** |                165 K/s |
+| Recall @1  |          99% |          99.2% |            98% |     **99.2%** |                  99.2% |
 
 > Dataset: 1M vectors sample of the Deep1B dataset.
 > Hardware: `c7g.metal` AWS instance with 64 cores and DDR5 memory.

package/VERSION

@@ -1 +1 @@
-0.9.0
+0.9.2

package/conanfile.py

@@ -4,7 +4,7 @@ from conans import ConanFile
 class USearchConan(ConanFile):
 
     name = 'USearch'
-    version = '0.9.0'
+    version = '0.9.2'
     license = 'Apache 2.0'
     url = 'https://github.com/unum-cloud/usearch'
     description = 'Smaller & Faster Single-File Vector Search Engine from Unum'

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "usearch",
-    "version": "0.9.0",
+    "version": "0.9.2",
     "description": "Smaller & Faster Single-File Vector Search Engine from Unum",
     "author": "Ashot Vardanian",
     "license": "Apache 2.0",

package/python/scripts/bench.py

@@ -106,10 +106,10 @@ def main(
 
         @cfunc(signature_f32)
         def inner_product_f32(a, b, n, m):
-            a_array = carray(a, n)
-            b_array = carray(b, n)
+            a_array = carray(a, dim)
+            b_array = carray(b, dim)
             c = types.float32(0)
-            for i in range(n):
+            for i in range(dim):
                 c += a_array[i] * b_array[i]
             return types.float32(1 - c)
 
@@ -120,12 +120,12 @@ def main(
 
         @cfunc(signature_f8)
         def cos_f8(a, b, n, m):
-            a_array = carray(a, n)
-            b_array = carray(b, n)
+            a_array = carray(a, dim)
+            b_array = carray(b, dim)
             c = types.int32(0)
             a_sq = types.int32(0)
             b_sq = types.int32(0)
-            for i in range(n):
+            for i in range(dim):
                 ai = types.int16(a_array[i])
                 bi = types.int16(b_array[i])
                 c += ai * bi