enhanced_parent_self_query_retriever
====================================

.. py:module:: enhanced_parent_self_query_retriever

.. autoapi-nested-parse::

   Enhanced MCP Retriever combining Parent Document Retriever with Self-Query.

   This implementation combines:
   1. Parent-child document retrieval for context preservation
   2. Self-query metadata filtering for natural language queries
   3. Metadata propagation from parent to child chunks

   The key insight: Store metadata on BOTH parent docs AND child chunks,
   enabling self-query filtering on chunks while returning full parents.



Classes
-------

.. autoapisummary::

   enhanced_parent_self_query_retriever.EnhancedMCPRetriever


Functions
---------

.. autoapisummary::

   enhanced_parent_self_query_retriever.main


Module Contents
---------------

.. py:class:: EnhancedMCPRetriever(engine: haive.core.engine.aug_llm.AugLLMConfig)

   Enhanced retriever that combines parent-child documents with self-query.

   The trick: Create a custom retriever that:
   1. Uses self-query to filter child chunks by metadata
   2. Returns parent documents for matching chunks
   3. Maintains all metadata relationships


   .. py:method:: create_self_query_retriever(k: int = 5) -> langchain.retrievers.self_query.base.SelfQueryRetriever

      Create a self-query retriever that works with parent documents.



   .. py:method:: demonstrate_queries() -> None
      :async:


      Demonstrate various query patterns.



   .. py:method:: find_and_analyze_best_server(requirements: str) -> langchain_core.documents.Document | None
      :async:


      Find the best server matching requirements using enhanced retrieval.



   .. py:method:: query_with_parent_context(query: str, k: int = 5) -> list[langchain_core.documents.Document]
      :async:


      Query using self-query on chunks but return full parent documents.

      This is the key method that combines both approaches!



   .. py:method:: setup_enhanced_retriever() -> None
      :async:


      Set up the enhanced parent-child retriever with self-query.



   .. py:attribute:: child_vectorstore
      :value: None



   .. py:attribute:: doc_loader


   .. py:attribute:: engine


   .. py:attribute:: metadata_fields
      :value: []



   .. py:attribute:: parent_retriever
      :value: None



   .. py:attribute:: parent_store


.. py:function:: main()
   :async:


   Run the enhanced retriever example.