Menjalankan Milvus menggunkan Python

Topik ini menjelaskan bagaimana cara menjalankan Milvus menggunkan Python.

1. Instal PyMilvus

pip3 install pymilvus==2.1.x

2. Unduh kode sampel

$ wget https://raw.githubusercontent.com/milvus-io/pymilvus/v2.1.x/examples/hello_milvus.py

3. Pindai sampel

Langkah-langkah yang dilakukan untuk membuat kode sampel.

• Impor paket PyMilvus :

from pymilvus import connections, FieldSchema, CollectionSchema, DataType, Collection

• Koneksikan ke server:

connections.connect(host='localhost', port='19530')

• Buat koleksi:

dim = 128
default_fields = [
    FieldSchema(name="count", dtype=DataType.INT64, is_primary=True),
    FieldSchema(name="random_value", dtype=DataType.DOUBLE),
    FieldSchema(name="float_vector", dtype=DataType.FLOAT_VECTOR, dim=dim)
]
default_schema = CollectionSchema(fields=default_fields, description="test collection")

print(f"\nCreate collection...")
collection = Collection(name="hello_milvus", schema=default_schema)

• Tambahkan vector ke dalam koleksi:

import random
nb = 3000
vectors = [[random.random() for _ in range(dim)] for _ in range(nb)]
collection.insert(
    [
        [i for i in range(nb)],
        [float(random.randrange(-20,-10)) for _ in range(nb)],
        vectors
    ]
)

• Bangun indeks dan muat koleksi:

default_index = {"index_type": "IVF_FLAT", "params": {"nlist": 128}, "metric_type": "L2"}
collection.create_index(field_name="float_vector", index_params=default_index)
collection.load()

• Lakukan pencarian persamaan vektor::

topK = 5
search_params = {"metric_type": "L2", "params": {"nprobe": 10}}
# define output_fields of search result
res = collection.search(
    vectors[-2:], "float_vector", search_params, topK,
    "count > 100", output_fields=["count", "random_value"]
)

Untuk mencetak hasil pencarian berdasarkan ID dan jarak, jalankan perintah berikut.

for raw_result in res:
    for result in raw_result:
        id = result.id  # result id
        distance = result.distance
        print(id, distance)

Baca Referensi API untuk informasi lebih lanjut.

• Lakukan pencarian hibrid：

from pymilvus import connections, Collection, FieldSchema, CollectionSchema, DataType
import random
connections.connect()
schema = CollectionSchema([
    FieldSchema("film_id", DataType.INT64, is_primary=True),
    FieldSchema("films", dtype=DataType.FLOAT_VECTOR, dim=2)
])
collection = Collection("test_collection_search", schema)
# insert
data = [
    [i for i in range(10)],
    [[random.random() for _ in range(2)] for _ in range(10)],
]
collection.insert(data)
collection.num_entities
10
collection.load()
# search
search_param = {
    "data": [[1.0, 1.0]],
    "anns_field": "films",
    "param": {"metric_type": "L2"},
    "limit": 2,
    "expr": "film_id in [2,4,6,8]",
}
res = collection.search(**search_param)
assert len(res) == 1
hits = res[0]
assert len(hits) == 2
print(f"- Total hits: {len(hits)}, hits ids: {hits.ids} ")
- Total hits: 2, hits ids: [2, 4]
print(f"- Top1 hit id: {hits[0].id}, distance: {hits[0].distance}, score: {hits[0].score} ")
- Top1 hit id: 2, distance: 0.10143111646175385, score: 0.101431116461

4. Jalankan sampel

$ python3 hello_milvus.py

Hasil yang dikembalikan dan latensi kueri ditampilkan sebagai berikut:

Selamat! Kamu baru saja memulai Milvus mandiri dan melakukan pencarian persamaan vector pertama.