Package dev.langchain4j.rag.content.retriever

Interface ContentRetriever

All Known Implementing Classes:
EmbeddingStoreContentRetriever, WebSearchContentRetriever
public interface ContentRetriever
Retrieves Contents from an underlying data source using a given Query.
The goal is to retrieve only relevant Contents in relation to a given Query.
The underlying data source can be virtually anything: 
 - Embedding (vector) store (see EmbeddingStoreContentRetriever)
 - Full-text search engine (see AzureAiSearchContentRetriever in langchain4j-azure-ai-search module)
 - Hybrid of vector and full-text search (see AzureAiSearchContentRetriever in langchain4j-azure-ai-search module)
 - Web Search Engine (see WebSearchContentRetriever)
 - Knowledge graph (see Neo4jContentRetriever in langchain4j-neo4j module)
 - SQL database (see SqlDatabaseContentRetriever in langchain4j-experimental-sql module)
 - etc.
See Also:

  • Method Summary

    Modifier and Type
    Method
    Description
    List<Content>
    retrieve(Query query)
    Retrieves relevant Contents using a given Query.

  • Method Details

    • retrieve

      List<Content> retrieve(Query query)
      Retrieves relevant Contents using a given Query. The Contents are sorted by relevance, with the most relevant Contents appearing at the beginning of the returned List<Content>.
      Parameters:
      query - The Query to use for retrieval.
      Returns:
      A list of retrieved Contents.