mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-07 01:28:27 +08:00
d6a428e880
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>
120 lines
2.7 KiB
Go
120 lines
2.7 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/log"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/metric"
|
|
)
|
|
|
|
func Test_cagraChecker_CheckTrain(t *testing.T) {
|
|
p1 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
}
|
|
p2 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.IP,
|
|
}
|
|
p3 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraInterDegree: strconv.Itoa(20),
|
|
}
|
|
|
|
p4 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraGraphDegree: strconv.Itoa(20),
|
|
}
|
|
p5 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraInterDegree: strconv.Itoa(60),
|
|
CagraGraphDegree: strconv.Itoa(20),
|
|
}
|
|
p6 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraInterDegree: strconv.Itoa(20),
|
|
CagraGraphDegree: strconv.Itoa(60),
|
|
}
|
|
p7 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.SUPERSTRUCTURE,
|
|
}
|
|
p8 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraInterDegree: "error",
|
|
CagraGraphDegree: strconv.Itoa(20),
|
|
}
|
|
p9 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraInterDegree: strconv.Itoa(20),
|
|
CagraGraphDegree: "error",
|
|
}
|
|
p10 := map[string]string{
|
|
DIM: strconv.Itoa(0),
|
|
Metric: metric.L2,
|
|
}
|
|
p11 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraBuildAlgo: "IVF_PQ",
|
|
}
|
|
p12 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
CagraBuildAlgo: "HNSW",
|
|
}
|
|
p13 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
RaftCacheDatasetOnDevice: "false",
|
|
}
|
|
p14 := map[string]string{
|
|
DIM: strconv.Itoa(128),
|
|
Metric: metric.L2,
|
|
RaftCacheDatasetOnDevice: "False",
|
|
}
|
|
cases := []struct {
|
|
params map[string]string
|
|
errIsNil bool
|
|
}{
|
|
{p1, true},
|
|
{p2, true},
|
|
{p3, true},
|
|
{p4, true},
|
|
{p5, true},
|
|
{p6, false},
|
|
{p7, false},
|
|
{p8, false},
|
|
{p9, false},
|
|
{p10, false},
|
|
{p11, true},
|
|
{p12, false},
|
|
{p13, true},
|
|
{p14, false},
|
|
}
|
|
|
|
c, _ := GetIndexCheckerMgrInstance().GetChecker("GPU_CAGRA")
|
|
if c == nil {
|
|
log.Error("can not get index checker instance, please enable GPU and rerun it")
|
|
return
|
|
}
|
|
for _, test := range cases {
|
|
err := c.CheckTrain(schemapb.DataType_FloatVector, schemapb.DataType_None, test.params)
|
|
if test.errIsNil {
|
|
assert.NoError(t, err)
|
|
} else {
|
|
assert.Error(t, err)
|
|
}
|
|
}
|
|
}
|