PgVectorEmbeddingStore: remove by ID

langchain4j-core/src/main/java/dev/langchain4j/store/embedding/EmbeddingStore.java

@@ -5,6 +5,7 @@
 import dev.langchain4j.store.embedding.filter.Filter;
 
 import java.util.List;
+import java.util.stream.Collectors;
 
 /**
  * Represents a store for embeddings, also known as a vector database.
@@ -13,135 +14,155 @@
  */
 public interface EmbeddingStore<Embedded> {
 
-    /**
-     * Adds a given embedding to the store.
-     *
-     * @param embedding The embedding to be added to the store.
-     * @return The auto-generated ID associated with the added embedding.
-     */
-    String add(Embedding embedding);
+  /**
+   * Adds a given embedding to the store.
+   *
+   * @param embedding The embedding to be added to the store.
+   * @return The auto-generated ID associated with the added embedding.
+   */
+  String add(Embedding embedding);
 
-    /**
-     * Adds a given embedding to the store.
-     *
-     * @param id        The unique identifier for the embedding to be added.
-     * @param embedding The embedding to be added to the store.
-     */
-    void add(String id, Embedding embedding);
+  /**
+   * Adds a given embedding to the store.
+   *
+   * @param id        The unique identifier for the embedding to be added.
+   * @param embedding The embedding to be added to the store.
+   */
+  void add(String id, Embedding embedding);
 
-    /**
-     * Adds a given embedding and the corresponding content that has been embedded to the store.
-     *
-     * @param embedding The embedding to be added to the store.
-     * @param embedded  Original content that was embedded.
-     * @return The auto-generated ID associated with the added embedding.
-     */
-    String add(Embedding embedding, Embedded embedded);
+  /**
+   * Adds a given embedding and the corresponding content that has been embedded to the store.
+   *
+   * @param embedding The embedding to be added to the store.
+   * @param embedded  Original content that was embedded.
+   * @return The auto-generated ID associated with the added embedding.
+   */
+  String add(Embedding embedding, Embedded embedded);
 
-    /**
-     * Adds multiple embeddings to the store.
-     *
-     * @param embeddings A list of embeddings to be added to the store.
-     * @return A list of auto-generated IDs associated with the added embeddings.
-     */
-    List<String> addAll(List<Embedding> embeddings);
+  /**
+   * Adds multiple embeddings to the store.
+   *
+   * @param embeddings A list of embeddings to be added to the store.
+   * @return A list of auto-generated IDs associated with the added embeddings.
+   */
+  List<String> addAll(List<Embedding> embeddings);
 
-    /**
-     * Adds multiple embeddings and their corresponding contents that have been embedded to the store.
-     *
-     * @param embeddings A list of embeddings to be added to the store.
-     * @param embedded   A list of original contents that were embedded.
-     * @return A list of auto-generated IDs associated with the added embeddings.
-     */
-    List<String> addAll(List<Embedding> embeddings, List<Embedded> embedded);
+  /**
+   * Adds multiple embeddings and their corresponding contents that have been embedded to the store.
+   *
+   * @param embeddings A list of embeddings to be added to the store.
+   * @param embedded   A list of original contents that were embedded.
+   * @return A list of auto-generated IDs associated with the added embeddings.
+   */
+  List<String> addAll(List<Embedding> embeddings, List<Embedded> embedded);
 
-    /**
-     * Searches for the most similar (closest in the embedding space) {@link Embedding}s.
-     * <br>
-     * All search criteria are defined inside the {@link EmbeddingSearchRequest}.
-     * <br>
-     * {@link EmbeddingSearchRequest#filter()} can be used to filter by user/memory ID.
-     * Please note that not all {@link EmbeddingStore} implementations support {@link Filter}ing.
-     *
-     * @param request A request to search in an {@link EmbeddingStore}. Contains all search criteria.
-     * @return An {@link EmbeddingSearchResult} containing all found {@link Embedding}s.
-     */
-    @Experimental
-    default EmbeddingSearchResult<Embedded> search(EmbeddingSearchRequest request) {
-        List<EmbeddingMatch<Embedded>> matches =
-                findRelevant(request.queryEmbedding(), request.maxResults(), request.minScore());
-        return new EmbeddingSearchResult<>(matches);
-    }
+  /**
+   * Removes an embedding from the store.
+   *
+   * @param id The unique identifier of the embedding to be removed.
+   * @return True if the embedding was successfully removed, false otherwise.
+   */
+  default boolean remove(String id) {
+    return false;
+  }
 
-    /**
-     * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
-     * By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
-     *
-     * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
-     * @param maxResults         The maximum number of embeddings to be returned.
-     * @return A list of embedding matches.
-     * Each embedding match includes a relevance score (derivative of cosine distance),
-     * ranging from 0 (not relevant) to 1 (highly relevant).
-     */
-    // TODO deprecate once the new experimental API is settled
-    default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults) {
-        return findRelevant(referenceEmbedding, maxResults, 0);
-    }
+  /**
+   * Removes multiple embeddings from the store.
+   *
+   * @param ids A list of unique identifiers of the embeddings to be removed.
+   * @return A list of unique identifiers of the embeddings that were successfully removed.
+   */
+  default List<String> removeAll(List<String> ids) {
+    return ids.stream().filter(this::remove).collect(Collectors.toList());
+  }
 
-    /**
-     * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
-     *
-     * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
-     * @param maxResults         The maximum number of embeddings to be returned.
-     * @param minScore           The minimum relevance score, ranging from 0 to 1 (inclusive).
-     *                           Only embeddings with a score of this value or higher will be returned.
-     * @return A list of embedding matches.
-     * Each embedding match includes a relevance score (derivative of cosine distance),
-     * ranging from 0 (not relevant) to 1 (highly relevant).
-     */
-    // TODO deprecate once the new experimental API is settled
-    default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults, double minScore) {
-        EmbeddingSearchRequest embeddingSearchRequest = EmbeddingSearchRequest.builder()
-                .queryEmbedding(referenceEmbedding)
-                .maxResults(maxResults)
-                .minScore(minScore)
-                .build();
-        EmbeddingSearchResult<Embedded> embeddingSearchResult = search(embeddingSearchRequest);
-        return embeddingSearchResult.matches();
-    }
+  /**
+   * Searches for the most similar (closest in the embedding space) {@link Embedding}s.
+   * <br>
+   * All search criteria are defined inside the {@link EmbeddingSearchRequest}.
+   * <br>
+   * {@link EmbeddingSearchRequest#filter()} can be used to filter by user/memory ID.
+   * Please note that not all {@link EmbeddingStore} implementations support {@link Filter}ing.
+   *
+   * @param request A request to search in an {@link EmbeddingStore}. Contains all search criteria.
+   * @return An {@link EmbeddingSearchResult} containing all found {@link Embedding}s.
+   */
+  @Experimental
+  default EmbeddingSearchResult<Embedded> search(EmbeddingSearchRequest request) {
+    List<EmbeddingMatch<Embedded>> matches =
+            findRelevant(request.queryEmbedding(), request.maxResults(), request.minScore());
+    return new EmbeddingSearchResult<>(matches);
+  }
 
-    /**
-     * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
-     * By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
-     *
-     * @param memoryId           The memoryId used Distinguishing query requests from different users.
-     * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
-     * @param maxResults         The maximum number of embeddings to be returned.
-     * @return A list of embedding matches.
-     * Each embedding match includes a relevance score (derivative of cosine distance),
-     * ranging from 0 (not relevant) to 1 (highly relevant).
-     */
-    // TODO deprecate once the new experimental API is settled
-    default List<EmbeddingMatch<Embedded>> findRelevant(
-            Object memoryId, Embedding referenceEmbedding, int maxResults) {
-        return findRelevant(memoryId, referenceEmbedding, maxResults, 0);
-    }
+  /**
+   * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
+   * By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
+   *
+   * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
+   * @param maxResults         The maximum number of embeddings to be returned.
+   * @return A list of embedding matches.
+   * Each embedding match includes a relevance score (derivative of cosine distance),
+   * ranging from 0 (not relevant) to 1 (highly relevant).
+   */
+  // TODO deprecate once the new experimental API is settled
+  default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults) {
+    return findRelevant(referenceEmbedding, maxResults, 0);
+  }
 
-    /**
-     * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
-     *
-     * @param memoryId           The memoryId used Distinguishing query requests from different users.
-     * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
-     * @param maxResults         The maximum number of embeddings to be returned.
-     * @param minScore           The minimum relevance score, ranging from 0 to 1 (inclusive).
-     *                           Only embeddings with a score of this value or higher will be returned.
-     * @return A list of embedding matches.
-     * Each embedding match includes a relevance score (derivative of cosine distance),
-     * ranging from 0 (not relevant) to 1 (highly relevant).
-     */
-    // TODO deprecate once the new experimental API is settled
-    default List<EmbeddingMatch<Embedded>> findRelevant(
-            Object memoryId, Embedding referenceEmbedding, int maxResults, double minScore) {
-        throw new RuntimeException("Not implemented");
-    }
+  /**
+   * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
+   *
+   * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
+   * @param maxResults         The maximum number of embeddings to be returned.
+   * @param minScore           The minimum relevance score, ranging from 0 to 1 (inclusive).
+   *                           Only embeddings with a score of this value or higher will be returned.
+   * @return A list of embedding matches.
+   * Each embedding match includes a relevance score (derivative of cosine distance),
+   * ranging from 0 (not relevant) to 1 (highly relevant).
+   */
+  // TODO deprecate once the new experimental API is settled
+  default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults, double minScore) {
+    EmbeddingSearchRequest embeddingSearchRequest = EmbeddingSearchRequest.builder()
+            .queryEmbedding(referenceEmbedding)
+            .maxResults(maxResults)
+            .minScore(minScore)
+            .build();
+    EmbeddingSearchResult<Embedded> embeddingSearchResult = search(embeddingSearchRequest);
+    return embeddingSearchResult.matches();
+  }
+
+  /**
+   * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
+   * By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
+   *
+   * @param memoryId           The memoryId used Distinguishing query requests from different users.
+   * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
+   * @param maxResults         The maximum number of embeddings to be returned.
+   * @return A list of embedding matches.
+   * Each embedding match includes a relevance score (derivative of cosine distance),
+   * ranging from 0 (not relevant) to 1 (highly relevant).
+   */
+  // TODO deprecate once the new experimental API is settled
+  default List<EmbeddingMatch<Embedded>> findRelevant(
+          Object memoryId, Embedding referenceEmbedding, int maxResults) {
+    return findRelevant(memoryId, referenceEmbedding, maxResults, 0);
+  }
+
+  /**
+   * Finds the most relevant (closest in space) embeddings to the provided reference embedding.
+   *
+   * @param memoryId           The memoryId used Distinguishing query requests from different users.
+   * @param referenceEmbedding The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
+   * @param maxResults         The maximum number of embeddings to be returned.
+   * @param minScore           The minimum relevance score, ranging from 0 to 1 (inclusive).
+   *                           Only embeddings with a score of this value or higher will be returned.
+   * @return A list of embedding matches.
+   * Each embedding match includes a relevance score (derivative of cosine distance),
+   * ranging from 0 (not relevant) to 1 (highly relevant).
+   */
+  // TODO deprecate once the new experimental API is settled
+  default List<EmbeddingMatch<Embedded>> findRelevant(
+          Object memoryId, Embedding referenceEmbedding, int maxResults, double minScore) {
+    throw new RuntimeException("Not implemented");
+  }
 }