An error "Invalid expr" occurred in Advanced Filtering on Array Fields in Milvus Lite

Question

I am using pymilvus version: 2.4.4

When trying to re-produce the code in documentations for advanced filtering on array fields https://milvus.io/docs/array_data_type.md#Advanced-filtering:

    collection_name="test_collection",
    filter="ARRAY_CONTAINS_ANY(color_coord, [7, 8, 9])",
    output_fields=["id", "color", "color_tag", "color_coord"],
    limit=3
)

It gives the following error:

MilvusException: <MilvusException: (code=1100, message=Invalid expr: ARRAY_CONTAINS_ANY(color_coord, [7, 8, 9]): invalid parameter)>

So, how to perform this operation correctly?

Answer 1

Did you have the full source code in there?

I just ran this successfully

import random, time
from pymilvus import MilvusClient, DataType

CLUSTER_ENDPOINT = "http://192.168.1.153:19530"

# 1. Set up a Milvus client
client = MilvusClient(
    uri=CLUSTER_ENDPOINT
)

# 2. Create a collection
schema = MilvusClient.create_schema(
    auto_id=False,
    enable_dynamic_field=False,
)

schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True)
schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=5)
schema.add_field(field_name="color", datatype=DataType.VARCHAR, max_length=512)
schema.add_field(field_name="color_tag", datatype=DataType.INT64)
schema.add_field(field_name="color_coord", datatype=DataType.ARRAY, element_type=DataType.INT64, max_capacity=5)

index_params = MilvusClient.prepare_index_params()

index_params.add_index(
    field_name="id",
    index_type="STL_SORT"
)

index_params.add_index(
    field_name="vector",
    index_type="IVF_FLAT",
    metric_type="L2",
    params={"nlist": 1024}
)

client.create_collection(
    collection_name="test_collection",
    schema=schema,
    index_params=index_params
)

res = client.get_load_state(
    collection_name="test_collection"
)

print(res)


res = client.query(
    collection_name="test_collection",
    filter="ARRAY_CONTAINS(color_coord, 10)",
    output_fields=["id", "color", "color_tag", "color_coord"],
    limit=3
)

print(res)

colors = ["green", "blue", "yellow", "red", "black", "white", "purple", "pink", "orange", "brown", "grey"]
data = []

for i in range(1000):
    current_color = random.choice(colors)
    current_tag = random.randint(1000, 9999)
    current_coord = [ random.randint(0, 40) for _ in range(random.randint(3, 5)) ]
    data.append({
        "id": i,
        "vector": [ random.uniform(-1, 1) for _ in range(5) ],
        "color": current_color,
        "color_tag": current_tag,
        "color_coord": current_coord,
    })

print(data[0])

# 3. Insert data
res = client.insert(
    collection_name="test_collection",
    data=data
)

print(res)

res = client.query( collection_name="test_collection",
    filter="ARRAY_CONTAINS_ANY(color_coord, [7, 8, 9])",
    output_fields=["id", "color", "color_tag", "color_coord"],
    limit=3
)

print(res)