mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-07 01:28:27 +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>
137 lines
2.9 KiB
Go
137 lines
2.9 KiB
Go
package indexparamcheck
|
|
|
|
import (
|
|
"strconv"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
|
|
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
|
"github.com/milvus-io/milvus/pkg/v2/common"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/metric"
|
|
)
|
|
|
|
func Test_baseChecker_CheckTrain(t *testing.T) {
|
|
validParams := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
}
|
|
paramsWithoutDim := map[string]string{
|
|
Metric: metric.L2,
|
|
}
|
|
sparseParamsWithoutDim := map[string]string{
|
|
Metric: metric.IP,
|
|
common.IsSparseKey: "True",
|
|
}
|
|
sparseParamsWrongMetric := map[string]string{
|
|
Metric: metric.L2,
|
|
common.IsSparseKey: "True",
|
|
}
|
|
badSparseParams := map[string]string{
|
|
Metric: metric.IP,
|
|
common.IsSparseKey: "ds",
|
|
}
|
|
cases := []struct {
|
|
params map[string]string
|
|
errIsNil bool
|
|
}{
|
|
{validParams, true},
|
|
{paramsWithoutDim, false},
|
|
{sparseParamsWithoutDim, true},
|
|
{sparseParamsWrongMetric, false},
|
|
{badSparseParams, false},
|
|
}
|
|
|
|
c, _ := GetIndexCheckerMgrInstance().GetChecker("HNSW")
|
|
for _, test := range cases {
|
|
test.params[common.IndexTypeKey] = "HNSW"
|
|
var err error
|
|
if test.params[common.IsSparseKey] == "True" {
|
|
err = c.CheckTrain(schemapb.DataType_SparseFloatVector, schemapb.DataType_None, test.params)
|
|
} else {
|
|
err = c.CheckTrain(schemapb.DataType_FloatVector, schemapb.DataType_None, test.params)
|
|
}
|
|
if test.errIsNil {
|
|
assert.NoError(t, err)
|
|
} else {
|
|
assert.Error(t, err)
|
|
}
|
|
}
|
|
}
|
|
|
|
func Test_baseChecker_CheckValidDataType(t *testing.T) {
|
|
cases := []struct {
|
|
dType schemapb.DataType
|
|
errIsNil bool
|
|
}{
|
|
{
|
|
dType: schemapb.DataType_Bool,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Int8,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Int16,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Int32,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Int64,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Float,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Double,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_String,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_VarChar,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_Array,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_JSON,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_FloatVector,
|
|
errIsNil: true,
|
|
},
|
|
{
|
|
dType: schemapb.DataType_BinaryVector,
|
|
errIsNil: true,
|
|
},
|
|
}
|
|
|
|
c := newBaseChecker()
|
|
for _, test := range cases {
|
|
fieldSchema := &schemapb.FieldSchema{DataType: test.dType}
|
|
err := c.CheckValidDataType("FLAT", fieldSchema)
|
|
if test.errIsNil {
|
|
assert.NoError(t, err)
|
|
} else {
|
|
assert.Error(t, err)
|
|
}
|
|
}
|
|
}
|
|
|
|
func Test_baseChecker_StaticCheck(t *testing.T) {
|
|
// TODO
|
|
assert.Error(t, newBaseChecker().StaticCheck(schemapb.DataType_FloatVector, schemapb.DataType_None, nil))
|
|
}
|