Run a Vector Search with a Couchbase SDK

package main

import (
    "fmt"
    "log"
    "time"
    "os"
    "github.com/couchbase/gocb/v2"
    // Include this import if you want to run a Search query using regular Search index features.
    // "github.com/couchbase/gocb/v2/search"
    "github.com/couchbase/gocb/v2/vector"
)
// Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database.
func main() {
    connstr := "couchbases://" + os.Getenv("CB_HOSTNAME") 
    username := os.Getenv("CB_USERNAME")
    password := os.Getenv("CB_PASSWORD")
	// Make sure to change the bucket, and scope names to match where you stored the sample data in your database. 
    bucket_name := "vector-sample"
    scope_name := "color"

    cluster, err := gocb.Connect(connstr, gocb.ClusterOptions{
        Authenticator: gocb.PasswordAuthenticator{
            Username: username,
            Password: password,
        },
        SecurityConfig: gocb.SecurityConfig{
            TLSSkipVerify: true, // Disables TLS certificate verification
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    bucket := cluster.Bucket(bucket_name)
    err = bucket.WaitUntilReady(5*time.Second, nil)
    if err != nil {
        log.Fatal(err)
    }

    scope := bucket.Scope(scope_name)

    request := gocb.SearchRequest{
        VectorSearch: vector.NewSearch(
            []*vector.Query{
			//  You can change the RGB values {0.0, 0.0, 128.0} to search for a different color.
            vector.NewQuery("colorvect_l2", []float32{0.0, 0.0, 128.0}),
        },
        nil,
       ),
    }
	// Change the limit value to return more results. Change the fields array to return different fields from your Search index.
    opts := &gocb.SearchOptions{Limit: 3, Fields: []string{"color"}}

	// Make sure to change the index name to match your Search index. 
    matchResult, err := scope.Search("color-index", request, opts)
    if err != nil {
        log.Fatal(err)
    }

    for matchResult.Next() {
        row := matchResult.Row()
        docID := row.ID
        var fields interface{}
        err := row.Fields(&fields)
        if err != nil {
            log.Fatal(err)
        }
        fmt.Printf("Document ID: %s, Fields: %v\n", docID, fields)
    }

    if err = matchResult.Err(); err != nil {
        log.Fatal(err)
    }
}

import com.couchbase.client.core.error.*;
import com.couchbase.client.java.*;
import com.couchbase.client.java.kv.*;
import com.couchbase.client.java.json.*;
import com.couchbase.client.java.search.*;
import com.couchbase.client.java.search.queries.*;
import com.couchbase.client.java.search.result.*;
import com.couchbase.client.java.search.vector.*;

import java.time.Duration;
import java.util.Map;

public class RunVectorSearchSimpleColor {

    public static void main(String[] args) {
    // Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database.
	String endpoint = "couchbases://" + System.getenv("CB_HOSTNAME") + "?tls_verify=none"; 
	String username = System.getenv("CB_USERNAME");
	String password = System.getenv("CB_PASSWORD");
    // Make sure to change the bucket, scope, collection, and index names to match where you stored the sample data in your database. 
	String bucketName = "vector-sample";
	String scopeName = "color";
	String collectionName = "rgb";
	String searchIndexName = "color-index";

	try {
	    // Connect to database/cluster with specified credentials
	    Cluster cluster = Cluster.connect(
		    endpoint,
		    ClusterOptions.clusterOptions(username, password).environment(env -> {
			    // Use the pre-configured profile below to avoid latency issues with your connection.
			    env.applyProfile("wan-development");
		    })
	    );

	    Bucket bucket = cluster.bucket(bucketName);
	    bucket.waitUntilReady(Duration.ofSeconds(10));
	    Scope scope = bucket.scope(scopeName);
	    Collection collection = scope.collection(collectionName);

	    SearchRequest request = SearchRequest
	        .create(VectorSearch.create(
                    // Change the floats in the array to search for a different color.
                    VectorQuery.create("colorvect_l2", new float[]{ 0.0f, 0.0f, 128.0f }
                ).numCandidates(3)));
        // Make sure to change the index name to match your Search index. 
	    SearchResult result = scope.search("color-index", request,
        // Change the limit value to return more results. Change the value or values in fields to return different fields from your Search index.
                SearchOptions.searchOptions().limit(3).fields("color","brightness"));

	    for (SearchRow row : result.rows()) {
	      System.out.println("Found row: " + row);
	      System.out.println("   Fields: " + row.fieldsAs(Map.class));
	    } 

	} catch (UnambiguousTimeoutException ex) {
	    boolean authFailure = ex.toString().contains("Authentication Failure");
	    if (authFailure) {
		    System.out.println("Authentication Failure Detected");
	    } else {
		    System.out.println("Error:");
		    System.out.println(ex.getMessage());
	    }
	}
    }
}

#!/usr/bin/env python3

import os
import sys
from couchbase.cluster import Cluster
from couchbase.options import ClusterOptions
from couchbase.auth import PasswordAuthenticator
from couchbase.exceptions import CouchbaseException
import couchbase.search as search
from couchbase.options import SearchOptions
from couchbase.vector_search import VectorQuery, VectorSearch

# You can change the RGB values to search for a different color
vector = [0.0,0.0,128.0]

# Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database.                                                                                                     
pa = PasswordAuthenticator(os.getenv("CB_USERNAME"), os.getenv("CB_PASSWORD"))
cluster = Cluster("couchbases://" + os.getenv("CB_HOSTNAME") + "/?ssl=no_verify", ClusterOptions(pa))
# Make sure to change the bucket, scope, and index names to match where you stored the sample data in your database.  
bucket = cluster.bucket("vector-sample")
scope = bucket.scope("color")
search_index = "color-index"
try:
    search_req = search.SearchRequest.create(search.MatchNoneQuery()).with_vector_search(
        VectorSearch.from_vector_query(VectorQuery('colorvect_l2', vector, num_candidates=3)))
        # Change the limit value to return more results. Change the fields array to return different fields from your Search index.
    result = scope.search(search_index, search_req, SearchOptions(limit=13,fields=["color", "id"]))
    for row in result.rows():
        print("Found row: {}".format(row))
    print("Reported total rows: {}".format(
        result.metadata().metrics().total_rows()))
except CouchbaseException as ex:
    import traceback
    traceback.print_exc()

package main

import (
    "fmt"
    "log"
    "time"
    "os"
    "github.com/couchbase/gocb/v2"
	// Include this import if you want to run a Search query using regular Search index features.
    // "github.com/couchbase/gocb/v2/search"
    "github.com/couchbase/gocb/v2/vector"
    "bytes"
    "encoding/json"
    "io/ioutil"
    "net/http"
)

type OpenAIResponse struct {
    Data []struct {
        Embedding []float32 `json:"embedding"`
    } `json:"data"`
}

// generateVector makes a request to OpenAI's API to get an embedding vector for the given input text.
// Make sure to replace OPENAI_API_KEY with your own API Key.
func generateVector(inputText string) ([]float32, error) {
    openaiAPIKey := os.Getenv("OPENAI_API_KEY")
    if openaiAPIKey == "" {
        return nil, fmt.Errorf("OPENAI_API_KEY environment variable is not set")
    }

    requestBody, err := json.Marshal(map[string]interface{}{
        "input":  inputText,
        "model": "text-embedding-ada-002",
    })
    if err != nil {
        return nil, fmt.Errorf("error marshaling request body: %w", err)
    }

    request, err := http.NewRequest("POST", "https://api.openai.com/v1/embeddings", bytes.NewBuffer(requestBody))
    if err != nil {
        return nil, fmt.Errorf("error creating request: %w", err)
    }

    request.Header.Set("Content-Type", "application/json")
    request.Header.Set("Authorization", "Bearer "+openaiAPIKey)

    client := &http.Client{}
    response, err := client.Do(request)
    if err != nil {
        return nil, fmt.Errorf("error making request: %w", err)
    }
    defer response.Body.Close()

    if response.StatusCode != http.StatusOK {
        bodyBytes, _ := ioutil.ReadAll(response.Body)
        return nil, fmt.Errorf("API request failed with status %d: %s", response.StatusCode, string(bodyBytes))
    }

    var openAIResponse OpenAIResponse
    if err := json.NewDecoder(response.Body).Decode(&openAIResponse); err != nil {
        return nil, fmt.Errorf("error decoding response: %w", err)
    }

    if len(openAIResponse.Data) == 0 || len(openAIResponse.Data[0].Embedding) == 0 {
        return nil, fmt.Errorf("no embedding vector found in response")
    }

    return openAIResponse.Data[0].Embedding, nil
}
// Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database.
func main() {
    connstr := "couchbases://" + os.Getenv("CB_HOSTNAME") 
    username := os.Getenv("CB_USERNAME")
    password := os.Getenv("CB_PASSWORD")
	// Make sure to change the bucket, and scope names to match where you stored the sample data in your database. 
    bucket_name := "vector-sample"
    scope_name := "color"

    cluster, err := gocb.Connect(connstr, gocb.ClusterOptions{
        Authenticator: gocb.PasswordAuthenticator{
            Username: username,
            Password: password,
        },
        SecurityConfig: gocb.SecurityConfig{
            TLSSkipVerify: true, // Disables TLS certificate verification
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    bucket := cluster.Bucket(bucket_name)
    err = bucket.WaitUntilReady(5*time.Second, nil)
    if err != nil {
        log.Fatal(err)
    }

    scope := bucket.Scope(scope_name)
	// Change the question to whatever you want to ask.
    question := "What color hides everything like the night?"
    vect, err := generateVector(question)
    if err != nil {
        log.Fatalf("Error generating vector: %v", err)
    }

    request := gocb.SearchRequest{
        VectorSearch: vector.NewSearch(
            []*vector.Query{
            vector.NewQuery("embedding_vector_dot", vect),
        },
        nil,
       ),
    }
	// Change the limit value to return more results. Change the fields array to return different fields from your Search index.
    opts := &gocb.SearchOptions{Limit: 2, Fields: []string{"color","description"}}
	
	// Make sure to change the index name to match your Search index. 
    matchResult, err := scope.Search("color-index", request, opts)
    if err != nil {
        log.Fatal(err)
    }

    for matchResult.Next() {
        row := matchResult.Row()
        docID := row.ID
        var fields interface{}
        err := row.Fields(&fields)
        if err != nil {
            log.Fatal(err)
        }
        fmt.Printf("Document ID: %s, Fields: %v\n", docID, fields)
    }

    if err = matchResult.Err(); err != nil {
        log.Fatal(err)
    }
}

import com.couchbase.client.core.error.*;
import com.couchbase.client.java.*;
import com.couchbase.client.java.kv.*;
import com.couchbase.client.java.json.*;
import com.couchbase.client.java.search.*;
import com.couchbase.client.java.search.queries.*;
import com.couchbase.client.java.search.result.*;
import com.couchbase.client.java.search.vector.*;

import java.io.IOException;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.http.HttpResponse.BodyHandlers;
import java.util.List;

import java.time.Duration;
import java.util.Map;

public class RunVectorSearchGenerateEmbed {
    // Make sure to replace OPENAI_API_KEY with your own API Key.
    private static final String OPENAI_API_KEY = System.getenv("OPENAI_API_KEY");
    private static final String OPENAI_URL = "https://api.openai.com/v1/embeddings";

    public static float[] generateVector(String inputText) {
        HttpClient client = HttpClient.newHttpClient();

        JsonObject jsonBody = JsonObject.create()
                .put("input", inputText)
                .put("model", "text-embedding-ada-002");

        HttpRequest request = HttpRequest.newBuilder()
                .uri(URI.create(OPENAI_URL))
                .header("Content-Type", "application/json")
                .header("Authorization", "Bearer " + OPENAI_API_KEY)
                .POST(HttpRequest.BodyPublishers.ofString(jsonBody.toString()))
                .build();

        try {
            HttpResponse<String> response = client.send(request, BodyHandlers.ofString());

            JsonObject jsonResponse = JsonObject.fromJson(response.body());
            List<Object> embeddingList = jsonResponse.getArray("data")
                .getObject(0)
                .getArray("embedding")
                .toList();

            return toFloatArray(embeddingList);
        } catch (IOException | InterruptedException e) {
            e.printStackTrace();
            return null; // or handle more gracefully
        }
    }

    private static float[] toFloatArray(List<Object> list) {
        float[] result = new float[list.size()];
        for (int i = 0; i < list.size(); i++) {
            result[i] = ((Number) list.get(i)).floatValue();
        }
        return result;
    }

    public static void main(String[] args) {
// Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database.
	String endpoint = "couchbases://" + System.getenv("CB_HOSTNAME") + "?tls_verify=none"; 
	String username = System.getenv("CB_USERNAME");
	String password = System.getenv("CB_PASSWORD");
// Make sure to change the bucket, scope, collection, and index names to match where you stored the sample data in your database. 
	String bucketName = "vector-sample";
	String scopeName = "color";
	String collectionName = "rgb";
	String searchIndexName = "color-index";

	try {
	    // Connect to database/cluster with specified credentials
	    Cluster cluster = Cluster.connect(
		    endpoint,
		    ClusterOptions.clusterOptions(username, password).environment(env -> {
			    // Use the pre-configured profile below to avoid latency issues with your connection.
			    env.applyProfile("wan-development");
		    })
	    );

	    Bucket bucket = cluster.bucket(bucketName);
	    bucket.waitUntilReady(Duration.ofSeconds(10));
	    Scope scope = bucket.scope(scopeName);
	    Collection collection = scope.collection(collectionName);
            // Change the question to whatever you want to ask.
            String question = "What color hides everything like the night?";
            float[] vector = generateVector(question);

	    SearchRequest request = SearchRequest
	        .create(VectorSearch.create(
                    VectorQuery.create("embedding_vector_dot", vector).numCandidates(2)));
        // Make sure to change the index name to match your Search index. 
	    SearchResult result = scope.search("color-index", request,
        // Change the limit value to return more results. Change the value or values in fields to return different fields from your Search index.
                SearchOptions.searchOptions().limit(3).fields("color","description"));

	    for (SearchRow row : result.rows()) {
	      System.out.println("Found row: " + row);
	      System.out.println("   Fields: " + row.fieldsAs(Map.class));
	    } 

	} catch (UnambiguousTimeoutException ex) {
	    boolean authFailure = ex.toString().contains("Authentication Failure");
	    if (authFailure) {
		    System.out.println("Authentication Failure Detected");
	    } else {
		    System.out.println("Error:");
		    System.out.println(ex.getMessage());
	    }
	}
    }
}

#!/usr/bin/env python3

import os
import sys
from couchbase.cluster import Cluster
from couchbase.options import ClusterOptions
from couchbase.auth import PasswordAuthenticator
from couchbase.exceptions import CouchbaseException
import couchbase.search as search
from couchbase.options import SearchOptions
from couchbase.vector_search import VectorQuery, VectorSearch
from openai import OpenAI

# Change the question to whatever you want to ask
question = "What color hides everything like the night?"

# Make sure to replace OPENAI_API_KEY with your own API Key
openai_api_key = os.getenv("OPENAI_API_KEY")
client = OpenAI()

# Make sure to change CB_USERNAME, CB_PASSWORD, and CB_HOSTNAME to the username, password, and hostname for your database. 
pa = PasswordAuthenticator(os.getenv("CB_USERNAME"), os.getenv("CB_PASSWORD"))
cluster = Cluster("couchbases://" + os.getenv("CB_HOSTNAME") + "/?ssl=no_verify", ClusterOptions(pa))
# Make sure to change the bucket, scope, and index names to match where you stored the sample data in your database. 
bucket = cluster.bucket("vector-sample")
scope = bucket.scope("color")
search_index = "color-index"
try:
    vector = client.embeddings.create(input = [question], model="text-embedding-ada-002").data[0].embedding
    search_req = search.SearchRequest.create(search.MatchNoneQuery()).with_vector_search(
        VectorSearch.from_vector_query(VectorQuery('embedding_vector_dot', vector, num_candidates=2)))
        # Change the limit value to return more results. Change the fields array to return different fields from your Search index.
    result = scope.search(search_index, search_req, SearchOptions(limit=13,fields=["color", "description"]))
    for row in result.rows():
        print("Found row: {}".format(row))
    print("Reported total rows: {}".format(
        result.metadata().metrics().total_rows()))
except CouchbaseException as ex:
    import traceback
    traceback.print_exc()