From ee5519a6bbd63636647ea95162ee16415bc15c7a Mon Sep 17 00:00:00 2001
From: David Rubinstein <drubinstein@spotify.com>
Date: Mon, 23 Oct 2023 12:32:41 -0400
Subject: [PATCH] Add voyager to algorithms

---
 .github/workflows/benchmarks.yml             |  1 +
 ann_benchmarks/algorithms/voyager/Dockerfile |  7 +++
 ann_benchmarks/algorithms/voyager/config.yml | 45 ++++++++++++++++++++
 ann_benchmarks/algorithms/voyager/module.py  | 31 ++++++++++++++
 4 files changed, 84 insertions(+)
 create mode 100644 ann_benchmarks/algorithms/voyager/Dockerfile
 create mode 100644 ann_benchmarks/algorithms/voyager/config.yml
 create mode 100644 ann_benchmarks/algorithms/voyager/module.py

diff --git a/.github/workflows/benchmarks.yml b/.github/workflows/benchmarks.yml
index 364d704ac..2ac15ed1c 100644
--- a/.github/workflows/benchmarks.yml
+++ b/.github/workflows/benchmarks.yml
@@ -64,6 +64,7 @@ jobs:
           - vald
           - vearch
           - vespa
+          - voyager
           - weaviate
         include:
           - library: pynndescent
diff --git a/ann_benchmarks/algorithms/voyager/Dockerfile b/ann_benchmarks/algorithms/voyager/Dockerfile
new file mode 100644
index 000000000..f4361d741
--- /dev/null
+++ b/ann_benchmarks/algorithms/voyager/Dockerfile
@@ -0,0 +1,7 @@
+FROM ann-benchmarks
+
+RUN apt-get install -y python-setuptools python-pip
+RUN pip3 install voyager
+
+RUN python3 -c 'import voyager'
+
diff --git a/ann_benchmarks/algorithms/voyager/config.yml b/ann_benchmarks/algorithms/voyager/config.yml
new file mode 100644
index 000000000..f8c964108
--- /dev/null
+++ b/ann_benchmarks/algorithms/voyager/config.yml
@@ -0,0 +1,45 @@
+float:
+  any:
+  - base_args: ['@metric']
+    constructor: Voyager
+    disabled: false
+    docker_tag: ann-benchmarks-voyager
+    module: ann_benchmarks.algorithms.voyager
+    name: voyager 
+    run_groups:
+      M-12:
+        arg_groups: [{M: 12, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-16:
+        arg_groups: [{M: 16, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-24:
+        arg_groups: [{M: 24, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-36:
+        arg_groups: [{M: 36, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-4:
+        arg_groups: [{M: 4, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-48:
+        arg_groups: [{M: 48, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-64:
+        arg_groups: [{M: 64, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-8:
+        arg_groups: [{M: 8, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
+      M-96:
+        arg_groups: [{M: 96, efConstruction: 500}]
+        args: {}
+        query_args: [[10, 20, 40, 80, 120, 200, 400, 600, 800]]
diff --git a/ann_benchmarks/algorithms/voyager/module.py b/ann_benchmarks/algorithms/voyager/module.py
new file mode 100644
index 000000000..f7bd88d97
--- /dev/null
+++ b/ann_benchmarks/algorithms/voyager/module.py
@@ -0,0 +1,31 @@
+import numpy as np
+import voyager
+
+from ..base.module import BaseANN
+
+
+class Voyager(BaseANN):
+    def __init__(self, metric, method_param):
+        self.metric = {"angular": 2, "euclidean": 0}[metric]
+        self.method_param = method_param
+        self.name = "voyager (%s)" % (self.method_param)
+
+    def fit(self, X):
+        self.p = voyager.Index(
+            space=voyager.Space(self.metric),
+            num_dimensions=len(X[0]),
+            max_elements=len(X),
+            ef_construction=self.method_param["efConstruction"],
+            M=self.method_param["M"],
+        )
+        data_labels = np.arange(len(X))
+        self.p.add_items(np.asarray(X), data_labels)
+
+    def set_query_arguments(self, ef):
+        self.ef = ef
+
+    def query(self, v, n):
+        return self.p.query(np.expand_dims(v, axis=0), k=n, query_ef=self.ef)[0][0]
+
+    def freeIndex(self):
+        del self.p