벡터 임베딩을 만드는 방법

Atlas Vector Search 인덱스를 정의합니다.

데이터에서 벡터 검색 쿼리를 사용하려면 컬렉션에 Atlas Vector Search 인덱스를 만들어야 합니다.

embedding 필드를 벡터 유형으로 지정하고 유사성 측정값을 euclidean으로 지정하는 sample_db.embeddings 컬렉션에 인덱스를 생성하려면 다음 단계를 완료하세요.

1. create-index.go라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   create-index.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"os"
   	"time"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   func main() {
   	ctx := context.Background()
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_db").Collection("embeddings")
   	indexName := "vector_index"
   	opts := options.SearchIndexes().SetName(indexName).SetType("vectorSearch")
   	type vectorDefinitionField struct {
   		Type          string `bson:"type"`
   		Path          string `bson:"path"`
   		NumDimensions int    `bson:"numDimensions"`
   		Similarity    string `bson:"similarity"`
   	}
   	type vectorDefinition struct {
   		Fields []vectorDefinitionField `bson:"fields"`
   	}
   	indexModel := mongo.SearchIndexModel{
   		Definition: vectorDefinition{
   			Fields: []vectorDefinitionField{{
   				Type:          "vector",
   				Path:          "embedding",
   				NumDimensions: <dimensions>,
   				Similarity:    "euclidean"}},
   		},
   		Options: opts,
   	}
   	log.Println("Creating the index.")
   	searchIndexName, err := coll.SearchIndexes().CreateOne(ctx, indexModel)
   	if err != nil {
   		log.Fatalf("failed to create the search index: %v", err)
   	}
   	// Await the creation of the index.
   	log.Println("Polling to confirm successful index creation.")
   	searchIndexes := coll.SearchIndexes()
   	var doc bson.Raw
   	for doc == nil {
   		cursor, err := searchIndexes.List(ctx, options.SearchIndexes().SetName(searchIndexName))
   		if err != nil {
   			fmt.Errorf("failed to list search indexes: %w", err)
   		}
   		if !cursor.Next(ctx) {
   			break
   		}
   		name := cursor.Current.Lookup("name").StringValue()
   		queryable := cursor.Current.Lookup("queryable").Boolean()
   		if name == searchIndexName && queryable {
   			doc = cursor.Current
   		} else {
   			time.Sleep(5 * time.Second)
   		}
   	}
   	log.Println("Name of Index Created: " + searchIndexName)
   }

2. 오픈 소스 모델을 사용한 경우 <dimensions> 자리 표시자 값을 1024 (으)로 바꾸고, OpenAI의 모델을 사용한 경우 1536 (으)로 바꿉니다.

3. 파일을 저장하고 다음 명령을 실행 합니다.

   go run create-index.go

   출력 숨기기

   2024/10/09 17:38:51 Creating the index.
   2024/10/09 17:38:52 Polling to confirm successful index creation.
   2024/10/09 17:39:22 Name of Index Created: vector_index

자세한 내용은 Atlas Vector Search 인덱스 생성하기를 참조하세요.

벡터 검색 쿼리에 대한 임베딩을 생성하고 쿼리를 실행 합니다.

1. vector-query.go라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   벡터 검색 쿼리를 실행하려면 집계 파이프라인에 전달할 쿼리 벡터를 생성하세요.

   예를 들어 이 코드는 다음을 수행합니다.

   • 정의한 임베딩 함수를 호출하여 샘플 쿼리 임베딩을 만듭니다.

   • 집계 파이프라인의 queryVector 필드에 임베딩을 전달합니다.

   • 샘플 벡터 검색 쿼리를 실행합니다. 이 쿼리는 $vectorSearch 단계를 사용하여 임베딩에 대한 ENN 검색을 수행합니다. 이는 관련성과 벡터 검색 점수에 따라 의미적으로 유사한 문서를 반환합니다.

     참고

     환경의 차이로 인해 임베딩에 약간의 변화가 생겨 결과물이 달라질 수 있습니다.

     자세한 내용은 벡터 검색 쿼리 실행을 참조하세요.

   오픈 소스

   OpenAI

   vector-query.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"my-embeddings-project/common"
   	"os"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   type TextAndScore struct {
   	Text  string  `bson:"text"`
   	Score float32 `bson:"score"`
   }
   func main() {
   	ctx := context.Background()
   	// Connect to your Atlas cluster
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_db").Collection("embeddings")
   	query := "ocean tragedy"
   	queryEmbedding := common.GetEmbeddings([]string{query})
   	pipeline := mongo.Pipeline{
   		bson.D{
   			{"$vectorSearch", bson.D{
   				{"queryVector", queryEmbedding[0]},
   				{"index", "vector_index"},
   				{"path", "embedding"},
   				{"exact", true},
   				{"limit", 5},
   			}},
   		},
   		bson.D{
   			{"$project", bson.D{
   				{"_id", 0},
   				{"text", 1},
   				{"score", bson.D{
   					{"$meta", "vectorSearchScore"},
   				}},
   			}},
   		},
   	}
   	// Run the pipeline
   	cursor, err := coll.Aggregate(ctx, pipeline)
   	if err != nil {
   		log.Fatalf("failed to run aggregation: %v", err)
   	}
   	defer func() { _ = cursor.Close(ctx) }()
   	var matchingDocs []TextAndScore
   	if err = cursor.All(ctx, &matchingDocs); err != nil {
   		log.Fatalf("failed to unmarshal results to TextAndScore objects: %v", err)
   	}
   	for _, doc := range matchingDocs {
   		fmt.Printf("Text: %v\nScore: %v\n", doc.Text, doc.Score)
   	}
   }

   vector-query.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"my-embeddings-project/common"
   	"os"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   type TextAndScore struct {
   	Text  string  `bson:"text"`
   	Score float64 `bson:"score"`
   }
   func main() {
   	ctx := context.Background()
   	// Connect to your Atlas cluster
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_db").Collection("embeddings")
   	query := "ocean tragedy"
   	queryEmbedding := common.GetEmbeddings([]string{query})
   	pipeline := mongo.Pipeline{
   		bson.D{
   			{"$vectorSearch", bson.D{
   				{"queryVector", queryEmbedding[0]},
   				{"index", "vector_index"},
   				{"path", "embedding"},
   				{"exact", true},
   				{"limit", 5},
   			}},
   		},
   		bson.D{
   			{"$project", bson.D{
   				{"_id", 0},
   				{"text", 1},
   				{"score", bson.D{
   					{"$meta", "vectorSearchScore"},
   				}},
   			}},
   		},
   	}
   	// Run the pipeline
   	cursor, err := coll.Aggregate(ctx, pipeline)
   	if err != nil {
   		log.Fatalf("failed to run aggregation: %v", err)
   	}
   	defer func() { _ = cursor.Close(ctx) }()
   	var matchingDocs []TextAndScore
   	if err = cursor.All(ctx, &matchingDocs); err != nil {
   		log.Fatalf("failed to unmarshal results to TextAndScore objects: %v", err)
   	}
   	for _, doc := range matchingDocs {
   		fmt.Printf("Text: %v\nScore: %v\n", doc.Text, doc.Score)
   	}
   }

2. 파일을 저장하고 다음 명령을 실행 합니다.

   오픈 소스

   OpenAI

   go run vector-query.go

   출력 숨기기

   Text: Titanic: The story of the 1912 sinking of the largest luxury liner ever built
   Score: 0.0042472864
   Text: Avatar: A marine is dispatched to the moon Pandora on a unique mission
   Score: 0.0031167597
   Text: The Lion King: Lion cub and future king Simba searches for his identity
   Score: 0.0024476869

   go run vector-query.go

   출력 숨기기

   Text: Titanic: The story of the 1912 sinking of the largest luxury liner ever built
   Score: 0.4552372694015503
   Text: Avatar: A marine is dispatched to the moon Pandora on a unique mission
   Score: 0.4050072133541107
   Text: The Lion King: Lion cub and future king Simba searches for his identity
   Score: 0.35942140221595764

Atlas Vector Search 인덱스를 정의합니다.

데이터에서 벡터 검색 쿼리를 사용하려면 컬렉션에 Atlas Vector Search 인덱스를 만들어야 합니다.

embeddings 필드를 벡터 유형으로 지정하고 유사성 측정값을 euclidean으로 지정하는 sample_airbnb.listingsAndReviews 컬렉션에 인덱스를 생성하려면 다음 단계를 완료하세요.

1. create-index.go라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   create-index.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"os"
   	"time"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   func main() {
   	ctx := context.Background()
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_airbnb").Collection("listingsAndReviews")
   	indexName := "vector_index"
   	opts := options.SearchIndexes().SetName(indexName).SetType("vectorSearch")
   	type vectorDefinitionField struct {
   		Type          string `bson:"type"`
   		Path          string `bson:"path"`
   		NumDimensions int    `bson:"numDimensions"`
   		Similarity    string `bson:"similarity"`
   	}
   	type vectorDefinition struct {
   		Fields []vectorDefinitionField `bson:"fields"`
   	}
   	indexModel := mongo.SearchIndexModel{
   		Definition: vectorDefinition{
   			Fields: []vectorDefinitionField{{
   				Type:          "vector",
   				Path:          "embeddings",
   				NumDimensions: <dimensions>,
   				Similarity:    "euclidean"}},
   		},
   		Options: opts,
   	}
   	log.Println("Creating the index.")
   	searchIndexName, err := coll.SearchIndexes().CreateOne(ctx, indexModel)
   	if err != nil {
   		log.Fatalf("failed to create the search index: %v", err)
   	}
   	// Await the creation of the index.
   	log.Println("Polling to confirm successful index creation.")
   	searchIndexes := coll.SearchIndexes()
   	var doc bson.Raw
   	for doc == nil {
   		cursor, err := searchIndexes.List(ctx, options.SearchIndexes().SetName(searchIndexName))
   		if err != nil {
   			fmt.Errorf("failed to list search indexes: %w", err)
   		}
   		if !cursor.Next(ctx) {
   			break
   		}
   		name := cursor.Current.Lookup("name").StringValue()
   		queryable := cursor.Current.Lookup("queryable").Boolean()
   		if name == searchIndexName && queryable {
   			doc = cursor.Current
   		} else {
   			time.Sleep(5 * time.Second)
   		}
   	}
   	log.Println("Name of Index Created: " + searchIndexName)
   }

2. 오픈 소스 모델을 사용한 경우 <dimensions> 자리 표시자 값을 1024 (으)로 바꾸고, OpenAI의 모델을 사용한 경우 1536 (으)로 바꿉니다.

3. 파일을 저장하고 다음 명령을 실행 합니다.

   go run create-index.go

   출력 숨기기

   2024/10/10 10:03:12 Creating the index.
   2024/10/10 10:03:13 Polling to confirm successful index creation.
   2024/10/10 10:03:44 Name of Index Created: vector_index

자세한 내용은 Atlas Vector Search 인덱스 생성하기를 참조하세요.

벡터 검색 쿼리에 대한 임베딩을 생성하고 쿼리를 실행 합니다.

1. vector-query.go라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   벡터 검색 쿼리를 실행하려면 집계 파이프라인에 전달할 쿼리 벡터를 생성하세요.

   예를 들어 이 코드는 다음을 수행합니다.

   • 정의한 임베딩 함수를 호출하여 샘플 쿼리 임베딩을 만듭니다.

   • 집계 파이프라인의 queryVector 필드에 임베딩을 전달합니다.

   • 샘플 벡터 검색 쿼리를 실행합니다. 이 쿼리는 $vectorSearch 단계를 사용하여 임베딩에 대한 ENN 검색을 수행합니다. 이는 관련성과 벡터 검색 점수에 따라 의미적으로 유사한 문서를 반환합니다.

     참고

     환경의 차이로 인해 임베딩에 약간의 변화가 생겨 결과물이 달라질 수 있습니다.

     자세한 내용은 벡터 검색 쿼리 실행을 참조하세요.

   오픈 소스

   OpenAI

   vector-query.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"my-embeddings-project/common"
   	"os"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   type SummaryAndScore struct {
   	Summary string  `bson:"summary"`
   	Score   float32 `bson:"score"`
   }
   func main() {
   	ctx := context.Background()
   	// Connect to your Atlas cluster
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_airbnb").Collection("listingsAndReviews")
   	query := "beach house"
   	queryEmbedding := common.GetEmbeddings([]string{query})
   	pipeline := mongo.Pipeline{
   		bson.D{
   			{"$vectorSearch", bson.D{
   				{"queryVector", queryEmbedding[0]},
   				{"index", "vector_index"},
   				{"path", "embeddings"},
   				{"exact", true},
   				{"limit", 5},
   			}},
   		},
   		bson.D{
   			{"$project", bson.D{
   				{"_id", 0},
   				{"summary", 1},
   				{"score", bson.D{
   					{"$meta", "vectorSearchScore"},
   				}},
   			}},
   		},
   	}
   	// Run the pipeline
   	cursor, err := coll.Aggregate(ctx, pipeline)
   	if err != nil {
   		log.Fatalf("failed to run aggregation: %v", err)
   	}
   	defer func() { _ = cursor.Close(ctx) }()
   	var matchingDocs []SummaryAndScore
   	if err = cursor.All(ctx, &matchingDocs); err != nil {
   		log.Fatalf("failed to unmarshal results to SummaryAndScore objects: %v", err)
   	}
   	for _, doc := range matchingDocs {
   		fmt.Printf("Summary: %v\nScore: %v\n", doc.Summary, doc.Score)
   	}
   }

   vector-query.go

   package main
   import (
   	"context"
   	"fmt"
   	"log"
   	"my-embeddings-project/common"
   	"os"
   	"github.com/joho/godotenv"
   	"go.mongodb.org/mongo-driver/bson"
   	"go.mongodb.org/mongo-driver/mongo"
   	"go.mongodb.org/mongo-driver/mongo/options"
   )
   type SummaryAndScore struct {
   	Summary string  `bson:"summary"`
   	Score   float64 `bson:"score"`
   }
   func main() {
   	ctx := context.Background()
   	// Connect to your Atlas cluster
   	if err := godotenv.Load(); err != nil {
   		log.Println("no .env file found")
   	}
   	// Connect to your Atlas cluster
   	uri := os.Getenv("ATLAS_CONNECTION_STRING")
   	if uri == "" {
   		log.Fatal("set your 'ATLAS_CONNECTION_STRING' environment variable.")
   	}
   	clientOptions := options.Client().ApplyURI(uri)
   	client, err := mongo.Connect(ctx, clientOptions)
   	if err != nil {
   		log.Fatalf("failed to connect to the server: %v", err)
   	}
   	defer func() { _ = client.Disconnect(ctx) }()
   	// Set the namespace
   	coll := client.Database("sample_airbnb").Collection("listingsAndReviews")
   	query := "beach house"
   	queryEmbedding := common.GetEmbeddings([]string{query})
   	pipeline := mongo.Pipeline{
   		bson.D{
   			{"$vectorSearch", bson.D{
   				{"queryVector", queryEmbedding[0]},
   				{"index", "vector_index"},
   				{"path", "embeddings"},
   				{"exact", true},
   				{"limit", 5},
   			}},
   		},
   		bson.D{
   			{"$project", bson.D{
   				{"_id", 0},
   				{"summary", 1},
   				{"score", bson.D{
   					{"$meta", "vectorSearchScore"},
   				}},
   			}},
   		},
   	}
   	// Run the pipeline
   	cursor, err := coll.Aggregate(ctx, pipeline)
   	if err != nil {
   		log.Fatalf("failed to run aggregation: %v", err)
   	}
   	defer func() { _ = cursor.Close(ctx) }()
   	var matchingDocs []SummaryAndScore
   	if err = cursor.All(ctx, &matchingDocs); err != nil {
   		log.Fatalf("failed to unmarshal results to SummaryAndScore objects: %v", err)
   	}
   	for _, doc := range matchingDocs {
   		fmt.Printf("Summary: %v\nScore: %v\n", doc.Summary, doc.Score)
   	}
   }

2. 파일을 저장하고 다음 명령을 실행 합니다.

   오픈 소스

   OpenAI

   go run vector-query.go

   출력 숨기기

   Summary: Near to underground metro station. Walking distance to seaside. 2 floors 1 entry. Husband, wife, girl and boy is living.
   Score: 0.0045180833
   Summary: A beautiful and comfortable 1 Bedroom Air Conditioned Condo in Makaha Valley - stunning Ocean & Mountain views All the amenities of home, suited for longer stays. Full kitchen & large bathroom.  Several gas BBQ's for all guests to use & a large heated pool surrounded by reclining chairs to sunbathe.  The Ocean you see in the pictures is not even a mile away, known as the famous Makaha Surfing Beach. Golfing, hiking,snorkeling  paddle boarding, surfing are all just minutes from the front door.
   Score: 0.004480799
   Summary: Having a large airy living room. The apartment is well divided. Fully furnished and cozy. The building has a 24h doorman and camera services in the corridors. It is very well located, close to the beach, restaurants, pubs and several shops and supermarkets. And it offers a good mobility being close to the subway.
   Score: 0.0042421296
   Summary: Room 2  Private room in charming recently renovated federation guest house at Coogee Beach. Prices are per room for 2 People only. A queen  and a single bed. Not suitable for group booking All rooms have  TV, desk, wardrobe, beds, unlimited wifi 2 mins from the beach, cafes and transport. This is not a party house but a safe and clean place to stay. Share bathrooms and kitchen... All common areas are cleaned daily.
   Score: 0.004227752
   Summary: A friendly apartment block where everyone knows each other and there is a strong communal vibe. Property has a huge backyard with vege garden and skate ramp. 7min walk to the beach and 2min to buses.
   Score: 0.0042201905

   go run vector-query.go

   출력 숨기기

   Summary: A friendly apartment block where everyone knows each other and there is a strong communal vibe. Property has a huge backyard with vege garden and skate ramp. 7min walk to the beach and 2min to buses.
   Score: 0.4832950830459595
   Summary: Room 2  Private room in charming recently renovated federation guest house at Coogee Beach. Prices are per room for 2 People only. A queen  and a single bed. Not suitable for group booking All rooms have  TV, desk, wardrobe, beds, unlimited wifi 2 mins from the beach, cafes and transport. This is not a party house but a safe and clean place to stay. Share bathrooms and kitchen... All common areas are cleaned daily.
   Score: 0.48093676567077637
   Summary: THIS IS A VERY SPACIOUS 1 BEDROOM FULL CONDO (SLEEPS 4) AT THE BEAUTIFUL VALLEY ISLE RESORT ON THE BEACH IN LAHAINA, MAUI!! YOU WILL LOVE THE PERFECT LOCATION OF THIS VERY NICE HIGH RISE! ALSO THIS SPACIOUS FULL CONDO, FULL KITCHEN, BIG BALCONY!!
   Score: 0.4629695415496826
   Summary: A beautiful and comfortable 1 Bedroom Air Conditioned Condo in Makaha Valley - stunning Ocean & Mountain views All the amenities of home, suited for longer stays. Full kitchen & large bathroom.  Several gas BBQ's for all guests to use & a large heated pool surrounded by reclining chairs to sunbathe.  The Ocean you see in the pictures is not even a mile away, known as the famous Makaha Surfing Beach. Golfing, hiking,snorkeling  paddle boarding, surfing are all just minutes from the front door.
   Score: 0.45800843834877014
   Summary: The Apartment has a living room, toilet, bedroom (suite) and American kitchen. Well located, on the Copacabana beach block a 05 Min. walk from Ipanema beach (Arpoador). Internet wifi, cable tv, air conditioning in the bedroom, ceiling fans in the bedroom and living room, kitchen with microwave, cooker, Blender, dishes, cutlery and service area with fridge, washing machine, clothesline for drying clothes and closet with several utensils for use.  The property boasts 45 m2.
   Score: 0.45398443937301636

Atlas Vector Search 인덱스를 정의합니다.

데이터에서 벡터 검색 쿼리를 사용하려면 컬렉션에 Atlas Vector Search 인덱스를 만들어야 합니다.

embedding 필드를 벡터 유형으로 지정하고 유사성 측정값을 euclidean으로 지정하는 sample_db.embeddings 컬렉션에 인덱스를 생성하려면 다음 단계를 완료하세요.

1. create-index.js라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   create-index.js

   import { MongoClient } from 'mongodb';
   // connect to your Atlas deployment
   const client = new MongoClient(process.env.ATLAS_CONNECTION_STRING);
   async function run() {
      try {
        const database = client.db("sample_db");
        const collection = database.collection("embeddings");
       
        // define your Atlas Vector Search index
        const index = {
            name: "vector_index",
            type: "vectorSearch",
            definition: {
              "fields": [
                {
                  "type": "vector",
                  "path": "embedding",
                  "similarity": "euclidean",
                  "numDimensions": <dimensions>
                }
              ]
            }
        }
        // run the helper method
        const result = await collection.createSearchIndex(index);
        console.log(result);
      } finally {
        await client.close();
      }
   }
   run().catch(console.dir);

2. 오픈 소스 모델을 사용한 경우 <dimensions> 자리 표시자 값을 768 (으)로 바꾸고, OpenAI의 모델을 사용한 경우 1536 (으)로 바꿉니다.

3. 파일을 저장하고 다음 명령을 실행 합니다.

   node --env-file=.env create-index.js

자세한 내용은 Atlas Vector Search 인덱스 생성하기를 참조하세요.

벡터 검색 쿼리에 대한 임베딩을 생성하고 쿼리를 실행 합니다.

1. vector-query.js라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   벡터 검색 쿼리를 실행하려면 집계 파이프라인에 전달할 쿼리 벡터를 생성하세요.

   예를 들어 이 코드는 다음을 수행합니다.

   • 정의한 임베딩 함수를 호출하여 샘플 쿼리 임베딩을 만듭니다.

   • 집계 파이프라인의 queryVector 필드에 임베딩을 전달합니다.

   • 샘플 벡터 검색 쿼리를 실행합니다. 이 쿼리는 $vectorSearch 단계를 사용하여 임베딩에 대한 ENN 검색을 수행합니다. 이는 관련성과 벡터 검색 점수에 따라 의미적으로 유사한 문서를 반환합니다.

     참고

     환경의 차이로 인해 임베딩에 약간의 변화가 생겨 결과물이 달라질 수 있습니다.

     자세한 내용은 벡터 검색 쿼리 실행을 참조하세요.

   vector-query.js

   import { MongoClient } from 'mongodb';
   import { getEmbedding } from './get-embeddings.js';
   // MongoDB connection URI and options
   const client = new MongoClient(process.env.ATLAS_CONNECTION_STRING);
   async function run() {
       try {
           // Connect to the MongoDB client
           await client.connect();
           // Specify the database and collection
           const database = client.db("sample_db"); 
           const collection = database.collection("embeddings"); 
           // Generate embedding for the search query
           const queryEmbedding = await getEmbedding("ocean tragedy");
           // Define the sample vector search pipeline
           const pipeline = [
               {
                   $vectorSearch: {
                       index: "vector_index",
                       queryVector: queryEmbedding,
                       path: "embedding",
                       exact: true,
                       limit: 5
                   }
               },
               {
                   $project: {
                       _id: 0,
                       text: 1,
                       score: {
                           $meta: "vectorSearchScore"
                       }
                   }
               }
           ];
           // run pipeline
           const result = collection.aggregate(pipeline);
           // print results
           for await (const doc of result) {
               console.dir(JSON.stringify(doc));
           }
           } finally {
           await client.close();
       }
   }
   run().catch(console.dir);

2. 파일을 저장하고 다음 명령을 실행 합니다.

   오픈 소스

   OpenAI

   node --env-file=.env vector-query.js

   출력 숨기기

   '{"text":"Titanic: The story of the 1912 sinking of the largest luxury liner ever built","score":0.5103757977485657}'
   '{"text":"Avatar: A marine is dispatched to the moon Pandora on a unique mission","score":0.4616812467575073}'
   '{"text":"The Lion King: Lion cub and future king Simba searches for his identity","score":0.4115804433822632}'

   node --env-file=.env vector-query.js

   출력 숨기기

   {"text":"Titanic: The story of the 1912 sinking of the largest luxury liner ever built","score":0.4551968574523926}
   {"text":"Avatar: A marine is dispatched to the moon Pandora on a unique mission","score":0.4050074517726898}
   {"text":"The Lion King: Lion cub and future king Simba searches for his identity","score":0.3594386577606201}

Atlas Vector Search 인덱스를 정의합니다.

데이터에서 벡터 검색 쿼리를 사용하려면 컬렉션에 Atlas Vector Search 인덱스를 만들어야 합니다.

embedding 필드를 벡터 유형으로 지정하고 유사성 측정값을 euclidean으로 지정하는 sample_airbnb.listingsAndReviews 컬렉션에 인덱스를 생성하려면 다음 단계를 완료하세요.

1. create-index.js라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   create-index.js

   import { MongoClient } from 'mongodb';
   // connect to your Atlas deployment
   const client = new MongoClient(process.env.ATLAS_CONNECTION_STRING);
   async function run() {
     try {
       const database = client.db("sample_airbnb");
       const collection = database.collection("listingsAndReviews");
      
       // Define your Atlas Vector Search index
       const index = {
           name: "vector_index",
           type: "vectorSearch",
           definition: {
             "fields": [
               {
                 "type": "vector",
                 "path": "embedding",
                 "similarity": "euclidean",
                 "numDimensions": <dimensions>
               }
             ]
           }
       }
       // Call the method to create the index
       const result = await collection.createSearchIndex(index);
       console.log(result);
     } finally {
       await client.close();
     }
   }
   run().catch(console.dir);

2. 오픈 소스 모델을 사용한 경우 <dimensions> 자리 표시자 값을 768 (으)로 바꾸고, OpenAI의 모델을 사용한 경우 1536 (으)로 바꿉니다.

3. 파일을 저장하고 다음 명령을 실행 합니다.

   node --env-file=.env create-index.js

자세한 내용은 Atlas Vector Search 인덱스 생성하기를 참조하세요.

벡터 검색 쿼리에 대한 임베딩을 생성하고 쿼리를 실행 합니다.

1. vector-query.js라는 이름의 파일을 만들고 다음 코드를 붙여넣습니다.

   벡터 검색 쿼리를 실행하려면 집계 파이프라인에 전달할 쿼리 벡터를 생성하세요.

   예를 들어 이 코드는 다음을 수행합니다.

   • 정의한 임베딩 함수를 호출하여 샘플 쿼리 임베딩을 만듭니다.

   • 집계 파이프라인의 queryVector 필드에 임베딩을 전달합니다.

   • 샘플 벡터 검색 쿼리를 실행합니다. 이 쿼리는 $vectorSearch 단계를 사용하여 임베딩에 대한 ENN 검색을 수행합니다. 이는 관련성과 벡터 검색 점수에 따라 의미적으로 유사한 문서를 반환합니다.

     참고

     환경의 차이로 인해 임베딩에 약간의 변화가 생겨 결과물이 달라질 수 있습니다.

     자세한 내용은 벡터 검색 쿼리 실행을 참조하세요.

   vector-query.js

   import { MongoClient } from 'mongodb';
   import { getEmbedding } from './get-embeddings.js';
   // MongoDB connection URI and options
   const client = new MongoClient(process.env.ATLAS_CONNECTION_STRING);
   async function run() {
       try {
           // Connect to the MongoDB client
           await client.connect();
           // Specify the database and collection
           const database = client.db("sample_airbnb"); 
           const collection = database.collection("listingsAndReviews"); 
           // Generate embedding for the search query
           const queryEmbedding = await getEmbedding("beach house");
           // Define the sample vector search pipeline
           const pipeline = [
               {
                   $vectorSearch: {
                       index: "vector_index",
                       queryVector: queryEmbedding,
                       path: "embedding",
                       exact: true,
                       limit: 5
                   }
               },
               {
                   $project: {
                       _id: 0,
                       summary: 1,
                       score: {
                           $meta: "vectorSearchScore"
                       }
                   }
               }
           ];
           // run pipeline
           const result = collection.aggregate(pipeline);
           // print results
           for await (const doc of result) {
               console.dir(JSON.stringify(doc));
           }
           } finally {
           await client.close();
       }
   }
   run().catch(console.dir);

2. 파일을 저장하고 다음 명령을 실행 합니다.

   오픈 소스

   OpenAI

   node --env-file=.env vector-query.js

   출력 숨기기

   '{"summary":"Having a large airy living room. The apartment is well divided. Fully furnished and cozy. The building has a 24h doorman and camera services in the corridors. It is very well located, close to the beach, restaurants, pubs and several shops and supermarkets. And it offers a good mobility being close to the subway.","score":0.5334879159927368}'
   '{"summary":"A beautiful and comfortable 1 Bedroom Air Conditioned Condo in Makaha Valley - stunning Ocean & Mountain views All the amenities of home, suited for longer stays. Full kitchen & large bathroom.  Several gas BBQ's for all guests to use & a large heated pool surrounded by reclining chairs to sunbathe.  The Ocean you see in the pictures is not even a mile away, known as the famous Makaha Surfing Beach. Golfing, hiking,snorkeling  paddle boarding, surfing are all just minutes from the front door.","score":0.5240535736083984}'
   '{"summary":"The Apartment has a living room, toilet, bedroom (suite) and American kitchen. Well located, on the Copacabana beach block a 05 Min. walk from Ipanema beach (Arpoador). Internet wifi, cable tv, air conditioning in the bedroom, ceiling fans in the bedroom and living room, kitchen with microwave, cooker, Blender, dishes, cutlery and service area with fridge, washing machine, clothesline for drying clothes and closet with several utensils for use.  The property boasts 45 m2.","score":0.5232879519462585}'
   '{"summary":"Room 2  Private room in charming recently renovated federation guest house at Coogee Beach. Prices are per room for 2 People only. A queen  and a single bed. Not suitable for group booking All rooms have  TV, desk, wardrobe, beds, unlimited wifi 2 mins from the beach, cafes and transport. This is not a party house but a safe and clean place to stay. Share bathrooms and kitchen... All common areas are cleaned daily.","score":0.5186381340026855}'
   '{"summary":"A friendly apartment block where everyone knows each other and there is a strong communal vibe. Property has a huge backyard with vege garden and skate ramp. 7min walk to the beach and 2min to buses.","score":0.5078228116035461}'

   node --env-file=.env vector-query.js

   출력 숨기기

   {"summary": "A friendly apartment block where everyone knows each other and there is a strong communal vibe. Property has a huge backyard with vege garden and skate ramp. 7min walk to the beach and 2min to buses.", "score": 0.483333021402359}
   {"summary": "Room 2  Private room in charming recently renovated federation guest house at Coogee Beach. Prices are per room for 2 People only. A queen  and a single bed. Not suitable for group booking All rooms have  TV, desk, wardrobe, beds, unlimited wifi 2 mins from the beach, cafes and transport. This is not a party house but a safe and clean place to stay. Share bathrooms and kitchen... All common areas are cleaned daily.", "score": 0.48092877864837646}
   {"summary": "THIS IS A VERY SPACIOUS 1 BEDROOM FULL CONDO (SLEEPS 4) AT THE BEAUTIFUL VALLEY ISLE RESORT ON THE BEACH IN LAHAINA, MAUI!! YOU WILL LOVE THE PERFECT LOCATION OF THIS VERY NICE HIGH RISE! ALSO THIS SPACIOUS FULL CONDO, FULL KITCHEN, BIG BALCONY!!", "score": 0.46294474601745605}
   {"summary": "A beautiful and comfortable 1 Bedroom Air Conditioned Condo in Makaha Valley - stunning Ocean & Mountain views All the amenities of home, suited for longer stays. Full kitchen & large bathroom.  Several gas BBQ's for all guests to use & a large heated pool surrounded by reclining chairs to sunbathe.  The Ocean you see in the pictures is not even a mile away, known as the famous Makaha Surfing Beach. Golfing, hiking,snorkeling  paddle boarding, surfing are all just minutes from the front door.", "score": 0.4580020606517792}
   {"summary": "The Apartment has a living room, toilet, bedroom (suite) and American kitchen. Well located, on the Copacabana beach block a 05 Min. walk from Ipanema beach (Arpoador). Internet wifi, cable tv, air conditioning in the bedroom, ceiling fans in the bedroom and living room, kitchen with microwave, cooker, Blender, dishes, cutlery and service area with fridge, washing machine, clothesline for drying clothes and closet with several utensils for use.  The property boasts 45 m2.", "score": 0.45400717854499817}

Atlas Vector Search 인덱스를 정의합니다.

벡터 검색 쿼리에 대한 임베딩을 생성하고 쿼리를 실행 합니다.

벡터 검색 쿼리를 실행하려면 집계 파이프라인에 전달할 쿼리 벡터를 생성하세요.

예를 들어 이 코드는 다음을 수행합니다.

• 정의한 임베딩 함수를 호출하여 샘플 쿼리 임베딩을 만듭니다.

• 집계 파이프라인의 queryVector 필드에 임베딩을 전달합니다.

• 샘플 벡터 검색 쿼리를 실행합니다. 이 쿼리는 $vectorSearch 단계를 사용하여 임베딩에 대한 ENN 검색을 수행합니다. 이는 관련성과 벡터 검색 점수에 따라 의미적으로 유사한 문서를 반환합니다.

  참고

  환경의 차이로 인해 임베딩에 약간의 변화가 생겨 결과물이 달라질 수 있습니다.

  자세한 내용은 벡터 검색 쿼리 실행을 참조하세요.

# Generate embedding for the search query
query_embedding = get_embedding("ocean tragedy")
# Sample vector search pipeline
pipeline = [
   {
      "$vectorSearch": {
            "index": "vector_index",
            "queryVector": query_embedding,
            "path": "embedding",
            "exact": True,
            "limit": 5
      }
   }, 
   {
      "$project": {
         "_id": 0, 
         "text": 1,
         "score": {
            "$meta": "vectorSearchScore"
         }
      }
   }
]
# Execute the search
results = collection.aggregate(pipeline)
# Print results
for i in results:
   print(i)

{"text": "Titanic: The story of the 1912 sinking of the largest luxury liner ever built", "score": 0.5166476964950562}
{"text": "Avatar: A marine is dispatched to the moon Pandora on a unique mission", "score": 0.4587385058403015}
{"text": "The Lion King: Lion cub and future king Simba searches for his identity", "score": 0.41374602913856506}

# Generate embedding for the search query
query_embedding = get_embedding("ocean tragedy")
# Sample vector search pipeline
pipeline = [
   {
      "$vectorSearch": {
            "index": "vector_index",
            "queryVector": query_embedding,
            "path": "embedding",
            "exact": True,
            "limit": 5
      }
   }, 
   {
      "$project": {
         "_id": 0, 
         "text": 1,
         "score": {
            "$meta": "vectorSearchScore"
         }
      }
   }
]
# Execute the search
results = collection.aggregate(pipeline)
# Print results
for i in results:
   print(i)