Add IVF bench for PgVector extension

Signed-off-by: Artem Barger <artem@bargr.net>

ann_benchmarks/algorithms/pgvector/config.yml

@@ -5,7 +5,7 @@ float:
     disabled: false
     docker_tag: ann-benchmarks-pgvector
     module: ann_benchmarks.algorithms.pgvector
-    name: pgvector
+    name: pgvector_hnsw
     run_groups:
       M-16:
         arg_groups: [{M: 16, efConstruction: 200}]
@@ -15,3 +15,12 @@ float:
         arg_groups: [{M: 24, efConstruction: 200}]
         args: {}
         query_args: [[10, 20, 40, 80, 120, 200, 400, 800]]
+  - base_args: ['@metric']
+    constructor: PGVectorIVF
+    disabled: false
+    docker_tag: ann-benchmarks-pgvector
+    module: ann_benchmarks.algorithms.pgvector
+    name: pgvector_ivf
+    run_groups:
+      base:
+        args: [[32, 64, 128, 256, 512, 1024]]

ann_benchmarks/algorithms/pgvector/module.py

@@ -62,3 +62,55 @@ def get_memory_usage(self):
 
     def __str__(self):
         return f"PGVector(m={self._m}, ef_construction={self._ef_construction}, ef_search={self._ef_search})"
+
+
+class PGVectorIVF(BaseANN):
+    def __init__(self, metric, n_list):
+        self._metric = metric
+        self._n_list = n_list
+        self._cur = None
+
+        if metric == "angular":
+            self._query = "SELECT id FROM items ORDER BY embedding <=> %s LIMIT %s"
+        elif metric == "euclidean":
+            self._query = "SELECT id FROM items ORDER BY embedding <-> %s LIMIT %s"
+        else:
+            raise RuntimeError(f"unknown metric {metric}")
+
+    def fit(self, X):
+        subprocess.run("service postgresql start", shell=True, check=True, stdout=sys.stdout, stderr=sys.stderr)
+        conn = psycopg.connect(user="ann", password="ann", dbname="ann", autocommit=True)
+        pgvector.psycopg.register_vector(conn)
+        cur = conn.cursor()
+        cur.execute("DROP TABLE IF EXISTS items")
+        cur.execute("CREATE TABLE items (id int, embedding vector(%d))" % X.shape[1])
+        cur.execute("ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN")
+        print("copying data...")
+        with cur.copy("COPY items (id, embedding) FROM STDIN WITH (FORMAT BINARY)") as copy:
+            copy.set_types(["int4", "vector"])
+            for i, embedding in enumerate(X):
+                copy.write_row((i, embedding))
+        print("creating index...")
+        if self._metric == "angular":
+            cur.execute(
+                "CREATE INDEX ON items USING ivfflat (embedding vector_cosine_ops) WITH (lists = %d)" % (self._n_list)
+            )
+        elif self._metric == "euclidean":
+            cur.execute("CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = %d)" % (self._n_list))
+        else:
+            raise RuntimeError(f"unknown metric {self._metric}")
+        print("done!")
+        self._cur = cur
+
+    def query(self, v, n):
+        self._cur.execute(self._query, (v, n), binary=True, prepare=True)
+        return [id for id, in self._cur.fetchall()]
+
+    def get_memory_usage(self):
+        if self._cur is None:
+            return 0
+        self._cur.execute("SELECT pg_relation_size('items_embedding_idx')")
+        return self._cur.fetchone()[0] / 1024
+
+    def __str__(self):
+        return f"PGVectorIVF(n_list={self._n_list})"