ベクトルデータベース

@FunctionalInterface
public interface VectorStoreRetriever {

    List<Document> similaritySearch(SearchRequest request);

    default List<Document> similaritySearch(String query) {
        return this.similaritySearch(SearchRequest.builder().query(query).build());
    }
}

public interface VectorStore extends DocumentWriter, VectorStoreRetriever {

    default String getName() {
		return this.getClass().getSimpleName();
	}

    void add(List<Document> documents);

    default void upsert(List<EmbeddedDocument> entries) { ... }

    void delete(List<String> idList);

    void delete(Filter.Expression filterExpression);

    default void delete(String filterExpression) { ... }

    default <T> Optional<T> getNativeClient() {
		return Optional.empty();
	}
}

public class SearchRequest {

	public static final double SIMILARITY_THRESHOLD_ACCEPT_ALL = 0.0;

	public static final int DEFAULT_TOP_K = 4;

	private String query = "";

	private int topK = DEFAULT_TOP_K;

	private double similarityThreshold = SIMILARITY_THRESHOLD_ACCEPT_ALL;

	@Nullable
	private Filter.Expression filterExpression;

    public static Builder from(SearchRequest originalSearchRequest) {
		return builder().query(originalSearchRequest.getQuery())
			.topK(originalSearchRequest.getTopK())
			.similarityThreshold(originalSearchRequest.getSimilarityThreshold())
			.filterExpression(originalSearchRequest.getFilterExpression());
	}

	public static class Builder {

		private final SearchRequest searchRequest = new SearchRequest();

		public Builder query(String query) {
			Assert.notNull(query, "Query can not be null.");
			this.searchRequest.query = query;
			return this;
		}

		public Builder topK(int topK) {
			Assert.isTrue(topK >= 0, "TopK should be positive.");
			this.searchRequest.topK = topK;
			return this;
		}

		public Builder similarityThreshold(double threshold) {
			Assert.isTrue(threshold >= 0 && threshold <= 1, "Similarity threshold must be in [0,1] range.");
			this.searchRequest.similarityThreshold = threshold;
			return this;
		}

		public Builder similarityThresholdAll() {
			this.searchRequest.similarityThreshold = 0.0;
			return this;
		}

		public Builder filterExpression(@Nullable Filter.Expression expression) {
			this.searchRequest.filterExpression = expression;
			return this;
		}

		public Builder filterExpression(@Nullable String textExpression) {
			this.searchRequest.filterExpression = (textExpression != null)
					? new FilterExpressionTextParser().parse(textExpression) : null;
			return this;
		}

		public SearchRequest build() {
			return this.searchRequest;
		}

	}

	public String getQuery() {...}
	public int getTopK() {...}
	public double getSimilarityThreshold() {...}
	public Filter.Expression getFilterExpression() {...}
}

@Configuration
public class EmbeddingConfig {
    @Bean
    public BatchingStrategy customTokenCountBatchingStrategy() {
        return new TokenCountBatchingStrategy(
            EncodingType.CL100K_BASE,  // Specify the encoding type
            8000,                      // Set the maximum input token count
            0.1                        // Set the reserve percentage
        );
    }
}

TokenCountEstimator customEstimator = new YourCustomTokenCountEstimator();
TokenCountBatchingStrategy strategy = new TokenCountBatchingStrategy(
		this.customEstimator,
    8000,  // maxInputTokenCount
    0.1,   // reservePercentage
    Document.DEFAULT_CONTENT_FORMATTER,
    MetadataMode.NONE
);

@Configuration
public class EmbeddingConfig {
    @Bean
    public BatchingStrategy customBatchingStrategy() {
        return new CustomBatchingStrategy();
    }
}

@Autowired
VectorStore vectorStore;

void load(String sourceFile) {
    JsonReader jsonReader = new JsonReader(new FileSystemResource(sourceFile),
            "price", "name", "shortDescription", "description", "tags");
    List<Document> documents = jsonReader.get();
    this.vectorStore.add(documents);
}

public record EmbeddedDocument(Document document, float[] embedding) {
}

@Autowired
VectorStore vectorStore;

// a vector you computed elsewhere
float[] embedding = ...;
Document document = new Document("8f14e45f-ceea-467a-9a3e-5b1c2d6f7a90", "some text",
        Map.of("source", "manual"));

this.vectorStore.upsert(List.of(new EmbeddedDocument(document, embedding)));

@Autowired
EmbeddingModel embeddingModel;

float[] vector = this.embeddingModel.embed(document);
this.vectorStore.upsert(List.of(new EmbeddedDocument(document, vector)));

byte[] frame = ...;                                 // the image/video/audio bytes
float[] embedding = multimodalModel.embed(frame);   // your multimodal model

String key = "video-42/frame-4711";

Document reference = Document.builder()
    // Stable and UUID-shaped, so a re-run replaces this row
    .id(UUID.nameUUIDFromBytes(key.getBytes(UTF_8)).toString())
    .text("")                                       // empty: the content lives elsewhere
    .metadata(DocumentMetadata.CONTENT_REF.value(), "s3://media/video-42.mp4#t=4711")
    .metadata("camera", "north-gate")               // still filterable like any row
    .build();

this.vectorStore.upsert(List.of(new EmbeddedDocument(reference, embedding)));

Document chunk = Document.builder()
    .text(chunkText)                                                  // real text, so add can embed it
    .metadata(DocumentMetadata.CONTENT_REF.value(), "articles/1042")  // where the full article lives
    .build();

this.vectorStore.add(List.of(chunk));

List<Document> results = this.vectorStore.similaritySearch(SearchRequest.builder()
    .query("a truck at the north gate after dark")   // embedded by the same multimodal model
    .filterExpression("camera == 'north-gate'")
    .build());

for (Document doc : results) {
    String ref = (String) doc.getMetadata().get(DocumentMetadata.CONTENT_REF.value());
    byte[] frame = mediaStorage.fetch(ref);           // S3, CDN, wherever the pointer leads
}

@Autowired
VectorStoreRetriever retriever; // Could also use VectorStore here

String question = "<question from user>";
List<Document> similarDocuments = retriever.similaritySearch(question);

// Or with more specific search parameters
SearchRequest request = SearchRequest.builder()
    .query(question)
    .topK(5)                       // Return top 5 results
    .similarityThreshold(0.7)      // Only return results with similarity score >= 0.7
    .build();

List<Document> filteredDocuments = retriever.similaritySearch(request);

// Write operations in a service that needs full access
@Service
class DocumentIndexer {
    private final VectorStore vectorStore;

    DocumentIndexer(VectorStore vectorStore) {
        this.vectorStore = vectorStore;
    }

    public void indexDocuments(List<Document> documents) {
        vectorStore.add(documents);
    }
}

// Read-only operations in a service that only needs retrieval
@Service
class DocumentRetriever {
    private final VectorStoreRetriever retriever;

    DocumentRetriever(VectorStoreRetriever retriever) {
        this.retriever = retriever;
    }

    public List<Document> findSimilar(String query) {
        return retriever.similaritySearch(query);
    }
}

@Service
public class DocumentRetrievalService {

    private final VectorStoreRetriever retriever;

    public DocumentRetrievalService(VectorStoreRetriever retriever) {
        this.retriever = retriever;
    }

    public List<Document> findSimilarDocuments(String query) {
        return retriever.similaritySearch(query);
    }

    public List<Document> findSimilarDocumentsWithFilters(String query, String country) {
        SearchRequest request = SearchRequest.builder()
            .query(query)
            .topK(5)
            .filterExpression("country == '" + country + "'")
            .build();

        return retriever.similaritySearch(request);
    }
}

@Service
public class RagService {

    private final VectorStoreRetriever retriever;
    private final ChatModel chatModel;

    public RagService(VectorStoreRetriever retriever, ChatModel chatModel) {
        this.retriever = retriever;
        this.chatModel = chatModel;
    }

    public String generateResponse(String userQuery) {
        // Retrieve relevant documents
        List<Document> relevantDocs = retriever.similaritySearch(userQuery);

        // Extract content from documents to use as context
        String context = relevantDocs.stream()
            .map(Document::getContent)
            .collect(Collectors.joining("\n\n"));

        // Generate response using the retrieved context
        String prompt = "Context information:\n" + context + "\n\nUser query: " + userQuery;
        return chatModel.generate(prompt);
    }
}

FilterExpressionBuilder b = new FilterExpressionBuilder();
Expression expression = this.b.eq("country", "BG").build();

EQUALS: '=='
MINUS : '-'
PLUS: '+'
GT: '>'
GE: '>='
LT: '<'
LE: '<='
NE: '!='

AND: 'AND' | 'and' | '&&';
OR: 'OR' | 'or' | '||';

Expression exp = b.and(b.eq("genre", "drama"), b.gte("year", 2020)).build();

IN: 'IN' | 'in';
NIN: 'NIN' | 'nin';
NOT: 'NOT' | 'not';

Expression exp = b.and(b.in("genre", "drama", "documentary"), b.not(b.lt("year", 2020))).build();

IS: 'IS' | 'is';
NULL: 'NULL' | 'null';
NOT NULL: 'NOT NULL' | 'not null';

Expression exp = b.and(b.isNull("year")).build();
Expression exp = b.and(b.isNotNull("year")).build();

// When writing, record the group the document belongs to.
Document document = new Document(content, Map.of("group", groupId));
vectorStore.add(List.of(document));

// When searching, select documents from that group.
List<Document> results = vectorStore.similaritySearch(SearchRequest.builder()
    .query(query)
    .filterExpression("group == '" + groupId + "'")
    .build());

// When deleting by filter, target the same group.
Filter.Expression scoped = new FilterExpressionBuilder().eq("group", groupId).build();
vectorStore.delete(scoped);

void delete(List<String> idList);

// Create and add document
Document document = new Document("The World is Big",
    Map.of("country", "Netherlands"));
vectorStore.add(List.of(document));

// Delete document by ID
vectorStore.delete(List.of(document.getId()));

void delete(Filter.Expression filterExpression);

// Create test documents with different metadata
Document bgDocument = new Document("The World is Big",
    Map.of("country", "Bulgaria"));
Document nlDocument = new Document("The World is Big",
    Map.of("country", "Netherlands"));

// Add documents to the store
vectorStore.add(List.of(bgDocument, nlDocument));

// Delete documents from Bulgaria using filter expression
Filter.Expression filterExpression = new Filter.Expression(
    Filter.ExpressionType.EQ,
    new Filter.Key("country"),
    new Filter.Value("Bulgaria")
);
vectorStore.delete(filterExpression);

// Verify deletion with search
SearchRequest request = SearchRequest.builder()
    .query("World")
    .filterExpression("country == 'Bulgaria'")
    .build();
List<Document> results = vectorStore.similaritySearch(request);
// results will be empty as Bulgarian document was deleted

void delete(String filterExpression);

// Create and add documents
Document bgDocument = new Document("The World is Big",
    Map.of("country", "Bulgaria"));
Document nlDocument = new Document("The World is Big",
    Map.of("country", "Netherlands"));
vectorStore.add(List.of(bgDocument, nlDocument));

// Delete Bulgarian documents using string filter
vectorStore.delete("country == 'Bulgaria'");

// Verify remaining documents
SearchRequest request = SearchRequest.builder()
    .query("World")
    .topK(5)
    .build();
List<Document> results = vectorStore.similaritySearch(request);
// results will only contain the Netherlands document

try {
    vectorStore.delete("country == 'Bulgaria'");
}
catch (Exception  e) {
    logger.error("Invalid filter expression", e);
}

// Create initial document (v1) with version metadata
Document documentV1 = new Document(
    "AI and Machine Learning Best Practices",
    Map.of(
        "docId", "AIML-001",
        "version", "1.0",
        "lastUpdated", "2024-01-01"
    )
);

// Add v1 to the vector store
vectorStore.add(List.of(documentV1));

// Create updated version (v2) of the same document
Document documentV2 = new Document(
    "AI and Machine Learning Best Practices - Updated",
    Map.of(
        "docId", "AIML-001",
        "version", "2.0",
        "lastUpdated", "2024-02-01"
    )
);

// First, delete the old version using filter expression
Filter.Expression deleteOldVersion = new Filter.Expression(
    Filter.ExpressionType.AND,
    new Filter.Expression(
        Filter.ExpressionType.EQ,
        new Filter.Key("docId"),
        new Filter.Value("AIML-001")
    ),
    new Filter.Expression(
        Filter.ExpressionType.EQ,
        new Filter.Key("version"),
        new Filter.Value("1.0")
    )
);
vectorStore.delete(deleteOldVersion);

// Add the new version
vectorStore.add(List.of(documentV2));

// Verify only v2 exists
SearchRequest request = SearchRequest.builder()
    .query("AI and Machine Learning")
    .filterExpression("docId == 'AIML-001'")
    .build();
List<Document> results = vectorStore.similaritySearch(request);
// results will contain only v2 of the document

// Delete old version using string filter
vectorStore.delete("docId == 'AIML-001' AND version == '1.0'");

// Add new version
vectorStore.add(List.of(documentV2));