-
Type:
Question
-
Resolution: Unresolved
-
Priority:
Minor - P4
-
Affects Version/s: None
-
Component/s: AI/ML, AutoEmbedding, LangChain
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.