Vector set embeddings

Index and query embeddings with Redis vector sets

Vector set is a new data type that is currently in preview and may be subject to change.

A Redis vector set lets you store a set of unique keys, each with its own associated vector. You can then retrieve keys from the set according to the similarity between their stored vectors and a query vector that you specify.

You can use vector sets to store any type of numeric vector but they are particularly optimized to work with text embedding vectors (see Redis for AI to learn more about text embeddings). The example below shows how to use the Hugot library to generate vector embeddings and then store and retrieve them using a vector set with go-redis.

Initialize

Start by installing go-redis if you haven't already done so. Note that you need go-redis v9.10.0 or later to use vector sets.

Also, install hugot:

go get github.com/knights-analytics/hugot

In a new Go file, add the required imports:

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

These include the Hugot library to generate an embedding from a section of text. This example uses an instance of the SentenceTransformer model all-MiniLM-L6-v2 for the embeddings. This model generates vectors with 384 dimensions, regardless of the length of the input text, but note that the input is truncated to 256 tokens (see Word piece tokenization at the Hugging Face docs to learn more about the way tokens are related to the original text).

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

Create the data

The example data is contained in a map with some brief descriptions of famous people:

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

Add the data to a vector set

The next step is to connect to Redis and add the data to a new vector set.

The code below iterates through the peopleData map and adds corresponding elements to a vector set called famousPeople.

Use the RunPipeline() method of embeddingPipeline to generate the embedding as an array of float32 values, then use a loop like the one shown below to convert the float32 array to a float64 array. You can then pass this array to the VAdd() command to set the embedding.

The call to VAdd() also adds the born and died values from the original map as attribute data. You can access this during a query or by using the VGetAttr() method.

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

Query the vector set

You can now query the data in the set. The basic approach is to use the RunPipeline() method to generate another embedding vector for the query text. (This is the same method used to add the elements to the set.) Then, pass the query vector to VSim() to return elements of the set, ranked in order of similarity to the query.

Start with a simple query for "actors":

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

This returns the following list of elements (formatted slightly for clarity):

'actors': Masako Natsume, Chaim Topol, Linus Pauling, Marie Fredriksson,
    Maryam Mirzakhani, Marie Curie, Freddie Mercury, Paul Erdos

The first two people in the list are the two actors, as expected, but none of the people from Linus Pauling onward was especially well-known for acting (and there certainly isn't any information about that in the short description text). As it stands, the search attempts to rank all the elements in the set, based on the information contained in the embedding model. You can use the Count parameter of VSimWithArgs() to limit the list of elements to just the most relevant few items:

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

The reason for using text embeddings rather than simple text search is that the embeddings represent semantic information. This allows a query to find elements with a similar meaning even if the text is different. For example, the word "entertainer" doesn't appear in any of the descriptions but if you use it as a query, the actors and musicians are ranked highest in the results list:

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

Similarly, if you use "science" as a query, you get the following results:

'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol

The scientists are ranked highest but they are then followed by the mathematicians. This seems reasonable given the connection between mathematics and science.

You can also use filter expressions with VSimWithArgs() to restrict the search further. For example, repeat the "science" query, but this time limit the results to people who died before the year 2000:

Language:

package main

import (
	"context"
	"fmt"
	"strings"

	"github.com/knights-analytics/hugot"
	"github.com/redis/go-redis/v9"
)


type PersonData struct {
	Born        int
	Died        int
	Description string
}

var peopleData = map[string]PersonData{
	"Marie Curie": {
		Born: 1867, Died: 1934,
		Description: `Polish-French chemist and physicist. The only person ever to win
		two Nobel prizes for two different sciences.
		`,
	},
	"Linus Pauling": {
		Born: 1901, Died: 1994,
		Description: `American chemist and peace activist. One of only two people to win two
		Nobel prizes in different fields (chemistry and peace).
		`,
	},
	"Freddie Mercury": {
		Born: 1946, Died: 1991,
		Description: `British musician, best known as the lead singer of the rock band
		Queen.
		`,
	},
	"Marie Fredriksson": {
		Born: 1958, Died: 2019,
		Description: `Swedish multi-instrumentalist, mainly known as the lead singer and
		keyboardist of the band Roxette.
		`,
	},
	"Paul Erdos": {
		Born: 1913, Died: 1996,
		Description: `Hungarian mathematician, known for his eccentric personality almost
		as much as his contributions to many different fields of mathematics.
		`,
	},
	"Maryam Mirzakhani": {
		Born: 1977, Died: 2017,
		Description: `Iranian mathematician. The first woman ever to win the Fields medal
		for her contributions to mathematics.
		`,
	},
	"Masako Natsume": {
		Born: 1957, Died: 1985,
		Description: `Japanese actress. She was very famous in Japan but was primarily
		known elsewhere in the world for her portrayal of Tripitaka in the
		TV series Monkey.
		`,
	},
	"Chaim Topol": {
		Born: 1935, Died: 2023,
		Description: `Israeli actor and singer, usually credited simply as 'Topol'. He was
		best known for his many appearances as Tevye in the musical Fiddler
		on the Roof.
		`,
	},
}


func main() {
	ctx := context.Background()

	// Create a new Hugot session
	session, err := hugot.NewGoSession()
	if err != nil {
		panic(err)
	}
	defer func() {
		err := session.Destroy()
		if err != nil {
			panic(err)
		}
	}()

	// Download the model.
	downloadOptions := hugot.NewDownloadOptions()
	downloadOptions.OnnxFilePath = "onnx/model.onnx"
	modelPath, err := hugot.DownloadModel(
		"sentence-transformers/all-MiniLM-L6-v2",
		"./models/",
		downloadOptions,
	)
	if err != nil {
		panic(err)
	}

	// Create feature extraction pipeline configuration
	config := hugot.FeatureExtractionConfig{
		ModelPath: modelPath,
		Name:      "embeddingPipeline",
	}

	// Create the feature extraction pipeline
	embeddingPipeline, err := hugot.NewPipeline(session, config)
	if err != nil {
		panic(err)
	}

	rdb := redis.NewClient(&redis.Options{
		Addr:     "localhost:6379",
		Password: "", // no password
		DB:       0,  // use default DB
	})

	for name, details := range peopleData {
		// Generate embeddings using Hugot
		result, err := embeddingPipeline.RunPipeline([]string{details.Description})
		if err != nil {
			panic(err)
		}

		// Convert embedding to float64 slice
		embFloat32 := result.Embeddings[0]
		embFloat64 := make([]float64, len(embFloat32))
		for i, v := range embFloat32 {
			embFloat64[i] = float64(v)
		}

		// Add vector to vector set
		_, err = rdb.VAdd(ctx, "famousPeople", name, &redis.VectorValues{Val: embFloat64}).Result()
		if err != nil {
			panic(err)
		}

		// Set attributes for the element
		_, err = rdb.VSetAttr(ctx, "famousPeople", name, map[string]interface{}{
			"born": details.Born,
			"died": details.Died,
		}).Result()
		if err != nil {
			panic(err)
		}
	}

	queryValue := "actors"

	queryResult, err := embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 := queryResult.Embeddings[0]
	queryFloat64 := make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	actorsResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors': %v\n", strings.Join(actorsResults, ", "))
	// >>> 'actors': Masako Natsume, Chaim Topol, Linus Pauling,
	// Marie Fredriksson, Maryam Mirzakhani, Marie Curie, Freddie Mercury,
	// Paul Erdos

	queryValue = "actors"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	twoActorsResults, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Count: 2}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'actors (2)': %v\n", strings.Join(twoActorsResults, ", "))
	// >>> 'actors (2)': Masako Natsume, Chaim Topol

	queryValue = "entertainer"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	entertainerResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'entertainer': %v\n", strings.Join(entertainerResults, ", "))
	// >>> 'entertainer': Chaim Topol, Freddie Mercury, Marie Fredriksson,
	// Linus Pauling, Masako Natsume, Paul Erdos,
	// Maryam Mirzakhani, Marie Curie

	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	scienceResults, err := rdb.VSim(ctx, "famousPeople", &redis.VectorValues{Val: queryFloat64}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science': %v\n", strings.Join(scienceResults, ", "))
	// >>> 'science': Marie Curie, Linus Pauling, Maryam Mirzakhani, Paul Erdos,
	// Marie Fredriksson, Freddie Mercury, Masako Natsume, Chaim Topol
	queryValue = "science"

	queryResult, err = embeddingPipeline.RunPipeline([]string{queryValue})
	if err != nil {
		panic(err)
	}

	// Convert embedding to float64 slice
	queryFloat32 = queryResult.Embeddings[0]
	queryFloat64 = make([]float64, len(queryFloat32))
	for i, v := range queryFloat32 {
		queryFloat64[i] = float64(v)
	}

	science2000Results, err := rdb.VSimWithArgs(ctx, "famousPeople",
		&redis.VectorValues{Val: queryFloat64},
		&redis.VSimArgs{Filter: ".died < 2000"}).Result()
	if err != nil {
		panic(err)
	}

	fmt.Printf("'science2000': %v\n", strings.Join(science2000Results, ", "))
	// >>> 'science2000': Marie Curie, Linus Pauling, Paul Erdos, Freddie Mercury,
	// Masako Natsume
}

Note that the boolean filter expression is applied to items in the list before the vector distance calculation is performed. Items that don't pass the filter test are removed from the results completely, rather than just reduced in rank. This can help to improve the performance of the search because there is no need to calculate the vector distance for elements that have already been filtered out of the search.

More information

See the vector sets docs for more information and code examples. See the Redis for AI section for more details about text embeddings and other AI techniques you can use with Redis.

You may also be interested in vector search. This is a feature of the Redis query engine that lets you retrieve JSON and hash documents based on vector data stored in their fields.

Products

Tools

Get Redis

Connect

Learn

Latest

See how it works

Vector set embeddings

Initialize

Create the data

Add the data to a vector set

Query the vector set

More information

On this page