Package dev.langchain4j.store.embedding.azure.search

Class AbstractAzureAiSearchEmbeddingStore

java.lang.Object
dev.langchain4j.store.embedding.azure.search.AbstractAzureAiSearchEmbeddingStore
All Implemented Interfaces:
EmbeddingStore<TextSegment>
Direct Known Subclasses:
AzureAiSearchContentRetriever, AzureAiSearchEmbeddingStore
public abstract class AbstractAzureAiSearchEmbeddingStore extends Object implements EmbeddingStore<TextSegment>

  • Field Details

  • Constructor Details

    • AbstractAzureAiSearchEmbeddingStore

      public AbstractAzureAiSearchEmbeddingStore()

  • Method Details

    • initialize

      protected void initialize(String endpoint, com.azure.core.credential.AzureKeyCredential keyCredential, com.azure.core.credential.TokenCredential tokenCredential, boolean createOrUpdateIndex, int dimensions, com.azure.search.documents.indexes.models.SearchIndex index, String indexName, AzureAiSearchFilterMapper filterMapper)

    • createOrUpdateIndex

      public void createOrUpdateIndex(int dimensions)
      Creates or updates the index using a ready-made index.
      Parameters:
      dimensions - The number of dimensions of the embeddings.

    • deleteIndex

      public void deleteIndex()

    • add

      public String add(Embedding embedding)
      Add an embedding to the store.
      Specified by:
      add in interface EmbeddingStore<TextSegment>
      Parameters:
      embedding - The embedding to be added to the store.
      Returns:
      The auto-generated ID associated with the added embedding.

    • add

      public void add(String id, Embedding embedding)
      Add an embedding to the store.
      Specified by:
      add in interface EmbeddingStore<TextSegment>
      Parameters:
      id - The unique identifier for the embedding to be added.
      embedding - The embedding to be added to the store.

    • add

      public String add(Embedding embedding, TextSegment textSegment)
      Add an embedding and the related content to the store.
      Specified by:
      add in interface EmbeddingStore<TextSegment>
      Parameters:
      embedding - The embedding to be added to the store.
      textSegment - Original content that was embedded.
      Returns:
      The auto-generated ID associated with the added embedding.

    • addAll

      public List<String> addAll(List<Embedding> embeddings)
      Add a list of embeddings to the store.
      Specified by:
      addAll in interface EmbeddingStore<TextSegment>
      Parameters:
      embeddings - A list of embeddings to be added to the store.
      Returns:
      A list of auto-generated IDs associated with the added embeddings.

    • remove

      public void remove(String id)
      Description copied from interface: EmbeddingStore
      Removes a single embedding from the store by ID.
      Specified by:
      remove in interface EmbeddingStore<TextSegment>
      Parameters:
      id - The unique ID of the embedding to be removed.

    • removeAll

      public void removeAll(Collection<String> ids)
      Description copied from interface: EmbeddingStore
      Removes all embeddings that match the specified IDs from the store.
      Specified by:
      removeAll in interface EmbeddingStore<TextSegment>
      Parameters:
      ids - A collection of unique IDs of the embeddings to be removed.

    • removeAll

      public void removeAll()
      Description copied from interface: EmbeddingStore
      Removes all embeddings from the store.
      Specified by:
      removeAll in interface EmbeddingStore<TextSegment>

    • removeAll

      public void removeAll(Filter filter)
      Description copied from interface: EmbeddingStore
      Removes all embeddings that match the specified Filter from the store.
      Specified by:
      removeAll in interface EmbeddingStore<TextSegment>
      Parameters:
      filter - The filter to be applied to the Metadata of the TextSegment during removal. Only embeddings whose TextSegment's Metadata match the Filter will be removed.

    • search

      public EmbeddingSearchResult<TextSegment> search(EmbeddingSearchRequest request)
      Description copied from interface: EmbeddingStore
      Searches for the most similar (closest in the embedding space) Embeddings.
      All search criteria are defined inside the EmbeddingSearchRequest.
      EmbeddingSearchRequest.filter() can be used to filter by various metadata entries (e.g., user/memory ID). Please note that not all EmbeddingStore implementations support Filtering.
      Specified by:
      search in interface EmbeddingStore<TextSegment>
      Parameters:
      request - A request to search in an EmbeddingStore. Contains all search criteria.
      Returns:
      An EmbeddingSearchResult containing all found Embeddings.

    • getEmbeddingMatches

      protected List<EmbeddingMatch<TextSegment>> getEmbeddingMatches(com.azure.search.documents.util.SearchPagedIterable searchResults, Double minScore, AzureAiSearchQueryType azureAiSearchQueryType)

    • addAll

      public void addAll(List<String> ids, List<Embedding> embeddings, List<TextSegment> embedded)
      Description copied from interface: EmbeddingStore
      Adds multiple embeddings and their corresponding contents that have been embedded to the store.
      Specified by:
      addAll in interface EmbeddingStore<TextSegment>
      Parameters:
      ids - A list of IDs associated with the added embeddings.
      embeddings - A list of embeddings to be added to the store.
      embedded - A list of original contents that were embedded.

    • fromAzureScoreToRelevanceScore

      protected static double fromAzureScoreToRelevanceScore(double score)
      Calculates LangChain4j's RelevanceScore from Azure AI Search's score.

      Score in Azure AI Search is transformed into a cosine similarity as described here: https://learn.microsoft.com/en-us/azure/search/vector-search-ranking#scores-in-a-vector-search-results

      RelevanceScore in LangChain4j is a derivative of cosine similarity, but it compresses it into 0..1 range (instead of -1..1) for ease of use.

    • fromAzureScoreToRelevanceScore

      public static double fromAzureScoreToRelevanceScore(com.azure.search.documents.models.SearchResult searchResult, AzureAiSearchQueryType azureAiSearchQueryType)
      Calculates LangChain4j's RelevanceScore from Azure AI Search's score, for the 4 types of search.