Skip to main content
NetApp Solutions

Appendix B: prepare_data_netapp_new.py

Contributors kevin-hoke nkarthik

This section provides a sample Python script used to prepare data for the vector database.

Appendix B: prepare_data_netapp_new.py

root@node2:~# cat prepare_data_netapp_new.py
# hello_milvus.py demonstrates the basic operations of PyMilvus, a Python SDK of Milvus.
# 1. connect to Milvus
# 2. create collection
# 3. insert data
# 4. create index
# 5. search, query, and hybrid search on entities
# 6. delete entities by PK
# 7. drop collection
import time
import os
import numpy as np
from pymilvus import (
    connections,
    utility,
    FieldSchema, CollectionSchema, DataType,
    Collection,
)

fmt = "\n=== {:30} ===\n"
search_latency_fmt = "search latency = {:.4f}s"
#num_entities, dim = 3000, 8
num_entities, dim = 3000, 16

#################################################################################
# 1. connect to Milvus
# Add a new connection alias `default` for Milvus server in `localhost:19530`
# Actually the "default" alias is a buildin in PyMilvus.
# If the address of Milvus is the same as `localhost:19530`, you can omit all
# parameters and call the method as: `connections.connect()`.
#
# Note: the `using` parameter of the following methods is default to "default".
print(fmt.format("start connecting to Milvus"))

host = os.environ.get('MILVUS_HOST')
if host == None:
    host = "localhost"
print(fmt.format(f"Milvus host: {host}"))
#connections.connect("default", host=host, port="19530")
connections.connect("default", host=host, port="27017")

has = utility.has_collection("hello_milvus_ntapnew_update2_sc")
print(f"Does collection hello_milvus_ntapnew_update2_sc exist in Milvus: {has}")

#drop the collection
print(fmt.format(f"Drop collection - hello_milvus_ntapnew_update2_sc"))
utility.drop_collection("hello_milvus_ntapnew_update2_sc")
#drop the collection
print(fmt.format(f"Drop collection - hello_milvus_ntapnew_update2_sc2"))
utility.drop_collection("hello_milvus_ntapnew_update2_sc2")

#################################################################################
# 2. create collection
# We're going to create a collection with 3 fields.
# +-+------------+------------+------------------+------------------------------+
# | | field name | field type | other attributes |       field description      |
# +-+------------+------------+------------------+------------------------------+
# |1|    "pk"    |    Int64   |  is_primary=True |      "primary field"         |
# | |            |            |   auto_id=False  |                              |
# +-+------------+------------+------------------+------------------------------+
# |2|  "random"  |    Double  |                  |      "a double field"        |
# +-+------------+------------+------------------+------------------------------+
# |3|"embeddings"| FloatVector|     dim=8        |  "float vector with dim 8"   |
# +-+------------+------------+------------------+------------------------------+
fields = [
    FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=False),
    FieldSchema(name="random", dtype=DataType.DOUBLE),
    FieldSchema(name="var", dtype=DataType.VARCHAR, max_length=65535),
    FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=dim)
]

schema = CollectionSchema(fields, "hello_milvus_ntapnew_update2_sc")

print(fmt.format("Create collection `hello_milvus_ntapnew_update2_sc`"))
hello_milvus_ntapnew_update2_sc = Collection("hello_milvus_ntapnew_update2_sc", schema, consistency_level="Strong")

################################################################################
# 3. insert data
# We are going to insert 3000 rows of data into `hello_milvus_ntapnew_update2_sc`
# Data to be inserted must be organized in fields.
#
# The insert() method returns:
# - either automatically generated primary keys by Milvus if auto_id=True in the schema;
# - or the existing primary key field from the entities if auto_id=False in the schema.

print(fmt.format("Start inserting entities"))
rng = np.random.default_rng(seed=19530)
entities = [
    # provide the pk field because `auto_id` is set to False
    [i for i in range(num_entities)],
    rng.random(num_entities).tolist(),  # field random, only supports list
    [str(i) for i in range(num_entities)],
    rng.random((num_entities, dim)),    # field embeddings, supports numpy.ndarray and list
]

insert_result = hello_milvus_ntapnew_update2_sc.insert(entities)
hello_milvus_ntapnew_update2_sc.flush()
print(f"Number of entities in hello_milvus_ntapnew_update2_sc: {hello_milvus_ntapnew_update2_sc.num_entities}")  # check the num_entites

# create another collection
fields2 = [
    FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=True),
    FieldSchema(name="random", dtype=DataType.DOUBLE),
    FieldSchema(name="var", dtype=DataType.VARCHAR, max_length=65535),
    FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=dim)
]


schema2 = CollectionSchema(fields2, "hello_milvus_ntapnew_update2_sc2")

print(fmt.format("Create collection `hello_milvus_ntapnew_update2_sc2`"))
hello_milvus_ntapnew_update2_sc2 = Collection("hello_milvus_ntapnew_update2_sc2", schema2, consistency_level="Strong")

entities2 = [
    rng.random(num_entities).tolist(),  # field random, only supports list
    [str(i) for i in range(num_entities)],
    rng.random((num_entities, dim)),    # field embeddings, supports numpy.ndarray and list
]

insert_result2 = hello_milvus_ntapnew_update2_sc2.insert(entities2)
hello_milvus_ntapnew_update2_sc2.flush()
insert_result2 = hello_milvus_ntapnew_update2_sc2.insert(entities2)
hello_milvus_ntapnew_update2_sc2.flush()

# index_params = {"index_type": "IVF_FLAT", "params": {"nlist": 128}, "metric_type": "L2"}
# hello_milvus_ntapnew_update2_sc.create_index("embeddings", index_params)
# hello_milvus_ntapnew_update2_sc2.create_index(field_name="var",index_name="scalar_index")

# index_params2 = {"index_type": "Trie"}
# hello_milvus_ntapnew_update2_sc2.create_index("var", index_params2)

print(f"Number of entities in hello_milvus_ntapnew_update2_sc2: {hello_milvus_ntapnew_update2_sc2.num_entities}")  # check the num_entites

root@node2:~#