mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-06 17:18:35 +08:00
Ref https://github.com/milvus-io/milvus/issues/42148 This PR supports create index for vector array (now, only for `DataType.FLOAT_VECTOR`) and search on it. The index type supported in this PR is `EMB_LIST_HNSW` and the metric type is `MAX_SIM` only. The way to use it: ```python milvus_client = MilvusClient("xxx:19530") schema = milvus_client.create_schema(enable_dynamic_field=True, auto_id=True) ... struct_schema = milvus_client.create_struct_array_field_schema("struct_array_field") ... struct_schema.add_field("struct_float_vec", DataType.ARRAY_OF_VECTOR, element_type=DataType.FLOAT_VECTOR, dim=128, max_capacity=1000) ... schema.add_struct_array_field(struct_schema) index_params = milvus_client.prepare_index_params() index_params.add_index(field_name="struct_float_vec", index_type="EMB_LIST_HNSW", metric_type="MAX_SIM", index_params={"nlist": 128}) ... milvus_client.create_index(COLLECTION_NAME, schema=schema, index_params=index_params) ``` Note: This PR uses `Lims` to convey offsets of the vector array to knowhere where vectors of multiple vector arrays are concatenated and we need offsets to specify which vectors belong to which vector array. --------- Signed-off-by: SpadeA <tangchenjie1210@gmail.com> Signed-off-by: SpadeA-Tang <tangchenjie1210@gmail.com>
139 lines
3.0 KiB
Go
139 lines
3.0 KiB
Go
package indexparamcheck
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
|
|
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
|
)
|
|
|
|
func TestVecIndexChecker_StaticCheck(t *testing.T) {
|
|
checker := newVecIndexChecker()
|
|
|
|
tests := []struct {
|
|
name string
|
|
dataType schemapb.DataType
|
|
params map[string]string
|
|
wantErr bool
|
|
}{
|
|
{
|
|
name: "Valid IVF_FLAT index",
|
|
dataType: schemapb.DataType_FloatVector,
|
|
params: map[string]string{
|
|
"index_type": "IVF_FLAT",
|
|
"metric_type": "L2",
|
|
"nlist": "1024",
|
|
},
|
|
wantErr: false,
|
|
},
|
|
{
|
|
name: "Invalid index type",
|
|
dataType: schemapb.DataType_FloatVector,
|
|
params: map[string]string{
|
|
"index_type": "INVALID_INDEX",
|
|
},
|
|
wantErr: true,
|
|
},
|
|
{
|
|
name: "Missing index type",
|
|
dataType: schemapb.DataType_FloatVector,
|
|
params: map[string]string{},
|
|
wantErr: true,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
err := checker.StaticCheck(tt.dataType, schemapb.DataType_None, tt.params)
|
|
if tt.wantErr {
|
|
assert.Error(t, err)
|
|
} else {
|
|
assert.NoError(t, err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestVecIndexChecker_CheckValidDataType(t *testing.T) {
|
|
checker := newVecIndexChecker()
|
|
|
|
tests := []struct {
|
|
name string
|
|
indexType IndexType
|
|
field *schemapb.FieldSchema
|
|
wantErr bool
|
|
}{
|
|
{
|
|
name: "Valid float vector",
|
|
indexType: "IVF_FLAT",
|
|
field: &schemapb.FieldSchema{
|
|
DataType: schemapb.DataType_FloatVector,
|
|
},
|
|
wantErr: false,
|
|
},
|
|
{
|
|
name: "Invalid data type",
|
|
indexType: "IVF_FLAT",
|
|
field: &schemapb.FieldSchema{
|
|
DataType: schemapb.DataType_Int64,
|
|
},
|
|
wantErr: true,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
err := checker.CheckValidDataType(tt.indexType, tt.field)
|
|
if tt.wantErr {
|
|
assert.Error(t, err)
|
|
} else {
|
|
assert.NoError(t, err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestVecIndexChecker_SetDefaultMetricTypeIfNotExist(t *testing.T) {
|
|
checker := newVecIndexChecker()
|
|
|
|
tests := []struct {
|
|
name string
|
|
dataType schemapb.DataType
|
|
params map[string]string
|
|
expectedType string
|
|
}{
|
|
{
|
|
name: "Float vector",
|
|
dataType: schemapb.DataType_FloatVector,
|
|
params: map[string]string{},
|
|
expectedType: FloatVectorDefaultMetricType,
|
|
},
|
|
{
|
|
name: "Binary vector",
|
|
dataType: schemapb.DataType_BinaryVector,
|
|
params: map[string]string{},
|
|
expectedType: BinaryVectorDefaultMetricType,
|
|
},
|
|
{
|
|
name: "int vector",
|
|
dataType: schemapb.DataType_Int8Vector,
|
|
params: map[string]string{},
|
|
expectedType: IntVectorDefaultMetricType,
|
|
},
|
|
{
|
|
name: "Existing metric type",
|
|
dataType: schemapb.DataType_FloatVector,
|
|
params: map[string]string{"metric_type": "IP"},
|
|
expectedType: "IP",
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
checker.SetDefaultMetricTypeIfNotExist(tt.dataType, tt.params)
|
|
assert.Equal(t, tt.expectedType, tt.params["metric_type"])
|
|
})
|
|
}
|
|
}
|