add mmr

benchmarker/cmd/ann_benchmark.go

@@ -962,6 +962,12 @@ var annBenchmarkCommand = &cobra.Command{
 
 		importTime := 0 * time.Second
 
+		if cfg.CreateOnly {
+			createSchema(&cfg, client)
+			log.Printf("Created empty collection %s, exiting", cfg.ClassName)
+			return
+		}
+
 		if !cfg.QueryOnly {
 
 			if !cfg.ExistingSchema {
@@ -994,6 +1000,16 @@ var annBenchmarkCommand = &cobra.Command{
 		}
 
 		neighbors := dataset.Neighbors()
+		if cfg.Diversity && cfg.DiversityBalance != 1 {
+			if hdf5ds, ok := dataset.(*Hdf5Dataset); ok {
+				sparseNeighbors := hdf5ds.SparseNeighbors()
+				if sparseNeighbors == nil {
+					log.Warn("--diversity flag is set but sparse_neighbors dataset not found in the HDF5 file, falling back to neighbors")
+				} else {
+					neighbors = sparseNeighbors
+				}
+			}
+		}
 		testData := dataset.TestVectors()
 		testFilters := dataset.TestFilters()
 
@@ -1113,6 +1129,8 @@ func initAnnBenchmark() {
 		"parallel", "p", numCPU, "Set the number of parallel threads which send queries")
 	annBenchmarkCommand.PersistentFlags().BoolVar(&globalConfig.ExistingSchema,
 		"existingSchema", false, "Leave the schema as-is (default false)")
+	annBenchmarkCommand.PersistentFlags().BoolVar(&globalConfig.CreateOnly,
+		"createOnly", false, "Only create the collection schema without importing any data (default false)")
 	annBenchmarkCommand.PersistentFlags().IntVar(&globalConfig.NumTenants,
 		"numTenants", 0, "Number of tenants to use (default 0)")
 	annBenchmarkCommand.PersistentFlags().IntVar(&globalConfig.StartTenantNum,
@@ -1173,6 +1191,12 @@ func initAnnBenchmark() {
 		"replicas", 4, "Number of replicas for HFresh index (default 4)")
 	annBenchmarkCommand.PersistentFlags().Float64Var(&globalConfig.RngFactor,
 		"rngFactor", 10.0, "RNG factor for HFresh index (default 10.0)")
+	annBenchmarkCommand.PersistentFlags().BoolVar(&globalConfig.Diversity,
+		"diversity", false, "Enable MMR diversity selection (default false)")
+	annBenchmarkCommand.PersistentFlags().Float32Var(&globalConfig.DiversityBalance,
+		"diversityBalance", 0.5, "MMR balance parameter: 0=pure diversity, 1=pure relevance (default 0.5)")
+	annBenchmarkCommand.PersistentFlags().Float32Var(&globalConfig.DiversityLimit,
+		"diversityLimit", 10, "MMR candidate limit passed to the selector (default 10)")
 }
 
 func benchmarkANN(cfg Config, queries Queries, neighbors Neighbors, filters []int) Results {

benchmarker/cmd/config.go

@@ -82,6 +82,10 @@ type Config struct {
 	MaxPostingSizeKB         int
 	Replicas                 int
 	RngFactor                float64
+	CreateOnly               bool
+	Diversity                bool
+	DiversityBalance         float32
+	DiversityLimit           float32
 }
 
 func (c *Config) Validate() error {
@@ -172,12 +176,14 @@ func (c *Config) parseLabels() {
 }
 
 func (c Config) validateANN() error {
-	if c.BenchmarkFile == "" && c.DatasetRepo == "" {
-		return errors.Errorf("a vector benchmark file or a dataset repository and dataset must be provided")
-	}
+	if !c.CreateOnly {
+		if c.BenchmarkFile == "" && c.DatasetRepo == "" {
+			return errors.Errorf("a vector benchmark file or a dataset repository and dataset must be provided")
+		}
 
-	if c.BenchmarkFile == "" && !(c.DatasetRepo != "" && c.Dataset != "") {
-		return errors.Errorf("if a vector benchmark file is not provided both a dataset repo and a dataset must be provided")
+		if c.BenchmarkFile == "" && !(c.DatasetRepo != "" && c.Dataset != "") {
+			return errors.Errorf("if a vector benchmark file is not provided both a dataset repo and a dataset must be provided")
+		}
 	}
 
 	if c.API != "grpc" {

benchmarker/cmd/hdf5_dataset.go

@@ -65,6 +65,15 @@ func (ds *Hdf5Dataset) Neighbors() [][]int {
 	return loadHdf5Neighbors(ds.file, "neighbors")
 }
 
+func (ds *Hdf5Dataset) SparseNeighbors() [][]int {
+	dataset, err := ds.file.OpenDataset("sparse_neighbors")
+	if err != nil {
+		return nil
+	}
+	dataset.Close()
+	return loadHdf5Neighbors(ds.file, "sparse_neighbors")
+}
+
 func (ds *Hdf5Dataset) TestVectors() [][]float32 {
 	if ds.multiVectorDimension > 0 {
 		return loadHdf5Colbert(ds.file, "test", ds.multiVectorDimension)

benchmarker/cmd/random_vectors.go

@@ -204,7 +204,19 @@ func nearVectorQueryGrpc(cfg *Config, vec []float32, tenant string, filter int)
 			On:       []string{"category"},
 			Operator: weaviategrpc.Filters_OPERATOR_EQUAL,
 		}
+	}
 
+	if cfg.Diversity {
+		diversityLimit := cfg.DiversityLimit
+		diversityBalance := cfg.DiversityBalance
+		searchRequest.NearVector.Selection = &weaviategrpc.Selection{
+			Selection: &weaviategrpc.Selection_Mmr{
+				Mmr: &weaviategrpc.Selection_MMR{
+					Limit:   &diversityLimit,
+					Balance: &diversityBalance,
+				},
+			},
+		}
 	}
 
 	data, err := proto.Marshal(searchRequest)

benchmarker/go.mod

@@ -1,60 +1,70 @@
 module github.com/semi-technologies/weaviate-benchmarking/benchmarker
 
-go 1.24
-
-toolchain go1.24.0
+go 1.26
 
 require (
 	github.com/google/uuid v1.6.0
 	github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.0.1
 	github.com/hashicorp/go-retryablehttp v0.7.7
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus/common v0.65.0
-	github.com/sirupsen/logrus v1.9.3
+	github.com/sirupsen/logrus v1.9.4
 	github.com/spf13/cobra v1.8.1
-	github.com/stretchr/testify v1.10.0
+	github.com/stretchr/testify v1.11.1
 	github.com/weaviate/hdf5 v0.0.0-20230911114900-3cd888ffadcd
 	github.com/weaviate/weaviate v1.34.0-rc.0.0.20251022050050-d6dd7edf23f3
 	github.com/weaviate/weaviate-go-client/v4 v4.16.2-0.20250127073049-5b267cd41195
-	golang.org/x/exp v0.0.0-20250210185358-939b2ce775ac
-	google.golang.org/grpc v1.74.2
-	google.golang.org/protobuf v1.36.6
+	golang.org/x/exp v0.0.0-20251113190631-e25ba8c21ef6
+	google.golang.org/grpc v1.79.3
+	google.golang.org/protobuf v1.36.11
 )
 
 require (
-	github.com/andybalholm/brotli v1.1.0 // indirect
-	github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2 // indirect
+	github.com/andybalholm/brotli v1.1.1 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
-	github.com/go-openapi/analysis v0.23.0 // indirect
-	github.com/go-openapi/errors v0.22.0 // indirect
-	github.com/go-openapi/jsonpointer v0.21.0 // indirect
-	github.com/go-openapi/jsonreference v0.21.0 // indirect
-	github.com/go-openapi/loads v0.22.0 // indirect
-	github.com/go-openapi/spec v0.21.0 // indirect
-	github.com/go-openapi/strfmt v0.23.0 // indirect
+	github.com/go-openapi/analysis v0.24.1 // indirect
+	github.com/go-openapi/errors v0.22.4 // indirect
+	github.com/go-openapi/jsonpointer v0.22.4 // indirect
+	github.com/go-openapi/jsonreference v0.21.4 // indirect
+	github.com/go-openapi/loads v0.23.2 // indirect
+	github.com/go-openapi/spec v0.22.3 // indirect
+	github.com/go-openapi/strfmt v0.25.0 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
-	github.com/go-openapi/validate v0.24.0 // indirect
-	github.com/gofrs/flock v0.12.1 // indirect
-	github.com/gomlx/go-huggingface v0.2.2 // indirect
+	github.com/go-openapi/swag/conv v0.25.4 // indirect
+	github.com/go-openapi/swag/fileutils v0.25.1 // indirect
+	github.com/go-openapi/swag/jsonname v0.25.4 // indirect
+	github.com/go-openapi/swag/jsonutils v0.25.4 // indirect
+	github.com/go-openapi/swag/loading v0.25.4 // indirect
+	github.com/go-openapi/swag/mangling v0.25.1 // indirect
+	github.com/go-openapi/swag/stringutils v0.25.4 // indirect
+	github.com/go-openapi/swag/typeutils v0.25.4 // indirect
+	github.com/go-openapi/swag/yamlutils v0.25.4 // indirect
+	github.com/go-openapi/validate v0.25.1 // indirect
+	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
+	github.com/gofrs/flock v0.13.0 // indirect
+	github.com/gomlx/go-huggingface v0.3.1 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/klauspost/compress v1.18.0 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
-	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/oklog/ulid v1.3.1 // indirect
-	github.com/parquet-go/parquet-go v0.25.1 // indirect
+	github.com/parquet-go/bitpack v1.0.0 // indirect
+	github.com/parquet-go/jsonlite v1.0.0 // indirect
+	github.com/parquet-go/parquet-go v0.27.0 // indirect
 	github.com/pierrec/lz4/v4 v4.1.21 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
 	github.com/spf13/pflag v1.0.6 // indirect
-	go.mongodb.org/mongo-driver v1.14.0 // indirect
-	golang.org/x/net v0.42.0 // indirect
-	golang.org/x/oauth2 v0.30.0 // indirect
-	golang.org/x/sys v0.34.0 // indirect
-	golang.org/x/text v0.27.0 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20250728155136-f173205681a0 // indirect
+	github.com/twpayne/go-geom v1.6.1 // indirect
+	go.mongodb.org/mongo-driver v1.17.6 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/net v0.49.0 // indirect
+	golang.org/x/oauth2 v0.35.0 // indirect
+	golang.org/x/sys v0.40.0 // indirect
+	golang.org/x/text v0.33.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )