[Bug]: Search with invalid sparse vector does not return an error

[ThreadDao]

Is there an existing issue for this?

• I have searched the existing issues

Environment

- Milvus version: master-20240415-fd971a43-amd64
- Deployment mode(standalone or cluster):standalone
- MQ type(rocksmq, pulsar or kafka):    
- SDK version(e.g. pymilvus v2.0.0rc2):
- OS(Ubuntu or CentOS): 
- CPU/Memory: 
- GPU: 
- Others:

Current Behavior

1. create collection with 2 vector fields: float32 and sparse
2. insert data -> index -> load
3. search with invalid sparse vector and no error is returned:

		positions := make([]uint32, 100)
		values := make([]float32, 100)
		for i := 0; i < 100; i++ {
			positions[i] = uint32(1)
			values[i] = rand.Float32()
		}
		vector, err := entity.NewSliceSparseEmbedding(positions, values)
		sp, _ := entity.NewIndexSparseInvertedSearchParam(0)
		searchRes, errSearch := mc.Search(ctx, collName, []string{}, "", []string{"*"}, []entity.Vector{vector}, common.DefaultSparseVecFieldName,
			entity.IP, common.DefaultTopK, sp)
		common.CheckErr(t, errSearch, false, "same index")

• go case:

func TestSearchInvalidSparseVector(t *testing.T) {
	t.Parallel()
	idxInverted := entity.NewGenericIndex(common.DefaultSparseVecFieldName, "SPARSE_INVERTED_INDEX", map[string]string{"drop_ratio_build": "0.2", "metric_type": "IP"})
	idxWand := entity.NewGenericIndex(common.DefaultSparseVecFieldName, "SPARSE_WAND", map[string]string{"drop_ratio_build": "0.3", "metric_type": "IP"})
	for _, idx := range []entity.Index{idxInverted, idxWand} {
		ctx := createContext(t, time.Second*common.DefaultTimeout*2)
		// connect
		mc := createMilvusClient(ctx, t)

		// create -> insert [0, 3000) -> flush -> index -> load
		cp := CollectionParams{CollectionFieldsType: Int64VarcharSparseVec, AutoID: false, EnableDynamicField: true,
			ShardsNum: common.DefaultShards, Dim: common.DefaultDim, MaxLength: common.TestMaxLen}

		dp := DataParams{DoInsert: true, CollectionFieldsType: Int64VarcharSparseVec, start: 0, nb: common.DefaultNb,
			dim: common.DefaultDim, EnableDynamicField: true}

		// index params
		idxHnsw, _ := entity.NewIndexHNSW(entity.L2, 8, 96)
		ips := []IndexParams{
			{BuildIndex: true, Index: idx, FieldName: common.DefaultSparseVecFieldName, async: false},
			{BuildIndex: true, Index: idxHnsw, FieldName: common.DefaultFloatVecFieldName, async: false},
		}
		collName := prepareCollection(ctx, t, mc, cp, WithDataParams(dp), WithIndexParams(ips), WithCreateOption(client.WithConsistencyLevel(entity.ClStrong)))

		positions := make([]uint32, 100)
		values := make([]float32, 100)
		for i := 0; i < 100; i++ {
			positions[i] = uint32(1)
			values[i] = rand.Float32()
		}
		vector, err := entity.NewSliceSparseEmbedding(positions, values)
		sp, _ := entity.NewIndexSparseInvertedSearchParam(0)
		searchRes, errSearch := mc.Search(ctx, collName, []string{}, "", []string{"*"}, []entity.Vector{vector}, common.DefaultSparseVecFieldName,
			entity.IP, common.DefaultTopK, sp)
		common.CheckErr(t, errSearch, false, "unsorted or same indices in sparse float vector")

		vector1, err := entity.NewSliceSparseEmbedding([]uint32{}, []float32{})
		common.CheckErr(t, err, true)
		searchRes, errSearch = mc.Search(ctx, collName, []string{}, "", []string{"*"}, []entity.Vector{vector1}, common.DefaultSparseVecFieldName,
			entity.IP, common.DefaultTopK, sp)
		common.CheckErr(t, errSearch, true)
		require.Len(t, searchRes, 0)
	}
}

Expected Behavior

No response

Steps To Reproduce

No response

Milvus Log

No response

Anything else?

No response

[yanliang567]

/unassign

[zhengbuqian]

should be fixed, can you verify? thanks!

[yanliang567]

/assign @ThreadDao
/unassign @zhengbuqian