🏐Lab 4

ANNOY vs. FAISS vs. HNSW

Percobaan kali ini kita akan melihat perbedaan ketiga model yang telah kita bahas dan bandingkan hasilnya.

import numpy as np
import time
from annoy import AnnoyIndex
import faiss
import hnswlib

# ===============================
# Build 1mio rows with 5D
# ===============================
n_data = 1_000_000   # try 100_000 if you have limited memory
dim = 5
X = np.random.random((n_data, dim)).astype(np.float32)

# Query point
query = np.random.random((1, dim)).astype(np.float32)
k = 10

# ===============================
# 2. Annoy
# ===============================
print("=== Annoy ===")
ann_index = AnnoyIndex(dim, 'euclidean')

start = time.time()
for i in range(n_data):
    ann_index.add_item(i, X[i])
ann_index.build(10)  # 10 trees
build_time = time.time() - start

start = time.time()
neighbors = ann_index.get_nns_by_vector(query[0], k, include_distances=True)
query_time = time.time() - start

print("Build time:", build_time, "detik")
print("Query time:", query_time, "detik")
print("Neighbors:", neighbors[0][:5], "...")

# ===============================
# 3. FAISS (Flat Index)
# ===============================
print("\n=== FAISS (IndexFlatL2) ===")
faiss_index = faiss.IndexFlatL2(dim)

start = time.time()
faiss_index.add(X)
build_time = time.time() - start

start = time.time()
distances, indices = faiss_index.search(query, k)
query_time = time.time() - start

print("Build time:", build_time, "detik")
print("Query time:", query_time, "detik")
print("Neighbors:", indices[0][:5], "...")

# ===============================
# 4. HNSW (hnswlib)
# ===============================
print("\n=== HNSW (hnswlib) ===")
hnsw_index = hnswlib.Index(space='l2', dim=dim)

start = time.time()
hnsw_index.init_index(max_elements=n_data, ef_construction=200, M=16)
hnsw_index.add_items(X)
build_time = time.time() - start

hnsw_index.set_ef(50)

start = time.time()
labels, distances = hnsw_index.knn_query(query, k=k)
query_time = time.time() - start

print("Build time:", build_time, "detik")
print("Query time:", query_time, "detik")
print("Neighbors:", labels[0][:5], "...")

Hasilnya (bisa jadi berbeda),

=== Annoy ===
Build time: 20.291711807250977 detik
Query time: 0.00025844573974609375 detik
Neighbors: [652544, 105406, 139716, 722254, 898386] ...

=== FAISS (IndexFlatL2) ===
Build time: 0.017807483673095703 detik
Query time: 0.012749195098876953 detik
Neighbors: [652544 105406 139716 722254 898386] ...

=== HNSW (hnswlib) ===
Build time: 156.97257900238037 detik
Query time: 0.00021314620971679688 detik
Neighbors: [652544 105406 139716 722254 898386] ...