Add methods to programmatically generate search indexes for Hybrid and FullText Retrievers

XMLWordPrintableJSON

    • None
    • Python Drivers
    • Hide

      1. What would you like to communicate to the user about this feature?
      2. Would you like the user to see examples of the syntax and/or executable code and its output?
      3. Which versions of the driver/connector does this apply to?

      Show
      1. What would you like to communicate to the user about this feature? 2. Would you like the user to see examples of the syntax and/or executable code and its output? 3. Which versions of the driver/connector does this apply to?
    • None
    • None
    • None
    • None
    • None
    • None

      Context

      The primary VectorStore MongoDBAtlasVectorSearch looks for and automatically creates a vector search index. By extension, so does the VectorSearch*Retriever* via the .as_retriever method. The FullText and Hybrid SearchRetrievers, however, require one to manually set up the full text search index.

      This may matter more now that we've introduced the $rankFusion operator.

      Acceptance Criteria

      • Review all the retrievers in the retriever subpackage
        • FullTextSearchRetriever
        • HybridSearchRetriever
        • ParentDocumentRetriever
      • Integrate a function in the {}init{} kwargs to automatically generate a search index.
      • Leverage `pymongo-search-utils` function.

      Pitfalls

      • Be on the lookout for AutoEmbedding as this will affect the overall design.

            Assignee:
            Noah Stapp
            Reporter:
            Casey Clements
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

              Created:
              Updated: