milvus/internal/util/vecindexmgr/vector_index_mgr_test.go
Spade A d6a428e880
feat: impl StructArray -- support create index for vector array (embedding list) and search on it (#43726)
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>
2025-08-20 10:27:46 +08:00

233 lines
4.8 KiB
Go

package vecindexmgr
import (
"testing"
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
)
func Test_VecIndex_DataType_Support(t *testing.T) {
type testCase struct {
indexType IndexType
dataTypes []schemapb.DataType
wants []bool
}
tests := []testCase{
{
indexType: "FLAT",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{true, false, true, true, false},
},
{
indexType: "BIN_FLAT",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{false, true, false, false, false},
},
{
indexType: "IVF_FLAT",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{true, false, true, true, false},
},
{
indexType: "IVF_PQ",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{true, false, true, true, false},
},
{
indexType: "HNSW",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{true, false, true, true, false},
},
{
indexType: "DISKANN",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{true, false, true, true, false},
},
{
indexType: "UNKNOWN",
dataTypes: []schemapb.DataType{
schemapb.DataType_FloatVector,
schemapb.DataType_BinaryVector,
schemapb.DataType_BFloat16Vector,
schemapb.DataType_Float16Vector,
schemapb.DataType_SparseFloatVector,
},
wants: []bool{false, false, false, false, false},
},
}
mgr := GetVecIndexMgrInstance()
for _, tt := range tests {
t.Run(string(tt.indexType), func(t *testing.T) {
for i, dataType := range tt.dataTypes {
got := mgr.IsDataTypeSupport(tt.indexType, dataType, schemapb.DataType_None)
if got != tt.wants[i] {
t.Errorf("IsDataTypeSupport(%v, %v) = %v, want %v", tt.indexType, dataType, got, tt.wants[i])
}
}
})
}
}
func Test_VecIndex_IsNoTrainIndex(t *testing.T) {
mgr := GetVecIndexMgrInstance()
tests := []struct {
indexType IndexType
want bool
}{
{
indexType: "FLAT",
want: true,
},
{
indexType: "BIN_FLAT",
want: true,
},
{
indexType: "IVF_FLAT",
want: false,
},
{
indexType: "IVF_SQ8",
want: false,
},
{
indexType: "IVF_PQ",
want: false,
},
{
indexType: "HNSW",
want: false,
},
{
indexType: "DISKANN",
want: false,
},
{
indexType: "UNKNOWN",
want: false,
},
}
for _, test := range tests {
got := mgr.IsNoTrainIndex(test.indexType)
if got != test.want {
t.Errorf("IsNoTrainIndex(%v) = %v, 期望 %v", test.indexType, got, test.want)
}
}
}
func Test_VecIndex_IsDiskVecIndex(t *testing.T) {
mgr := GetVecIndexMgrInstance()
tests := []struct {
indexType IndexType
want bool
}{
{
indexType: "FLAT",
want: false,
},
{
indexType: "BIN_FLAT",
want: false,
},
{
indexType: "IVF_FLAT",
want: false,
},
{
indexType: "DISKANN",
want: true,
},
{
indexType: "HNSW",
want: false,
},
{
indexType: "UNKNOWN",
want: false,
},
}
for _, test := range tests {
got := mgr.IsDiskVecIndex(test.indexType)
if got != test.want {
t.Errorf("IsDiskVecIndex(%v) = %v, want %v", test.indexType, got, test.want)
}
}
}
func Test_VecIndex_IsMvSupported(t *testing.T) {
mgr := GetVecIndexMgrInstance()
tests := []struct {
indexType IndexType
want bool
}{
{
indexType: "FLAT",
want: false,
},
{
indexType: "IVF_FLAT",
want: false,
},
{
indexType: "DISKANN",
want: false,
},
{
indexType: "HNSW",
want: true,
},
{
indexType: "UNKNOWN",
want: false,
},
}
for _, test := range tests {
got := mgr.IsMvSupported(test.indexType)
if got != test.want {
t.Errorf("IsMvSupported(%v) = %v, want %v", test.indexType, got, test.want)
}
}
}