Hybrid search reference
=======================

AIDB provides helper functions and a metadata view for constructing
hybrid search queries. Use these to encode queries against a specific
knowledge base, rerank retrieved results, and inspect knowledge base
configuration without hardcoding model names or table paths.

aidb.kb_query_encode()
----------------------

Encodes a text query using the embedding model configured for a specific
knowledge base, without needing to look up the model name:

.. code:: sql

   SELECT aidb.kb_query_encode(public.my_kb_vector, test query);

Use this in place of ``aidb.encode_text_query('<model>', '<query>')``
when constructing custom vector queries.

aidb.rerank_text()
------------------

After retrieving candidates, pass them to a reranking model for a final
relevance-ordered result:

.. code:: sql

   SELECT aidb.rerank_text(my_reranking_model, query text, ARRAY[result1, result2, ...]);

Reranking models such as ``nim_reranking`` and ``hf_tei_reranking`` are
supported as a separate post-processing step after retrieval.

``aidb.knowledge_bases`` view
-----------------------------

The ``aidb.knowledge_bases`` view (also accessible as ``aidb.kbs`` )
exposes all the metadata needed to construct hybrid queries:

.. csv-table::
  :header: Column,Type,Description
  :widths: 12,15,25
  :align: left
  :class: longtable

  `id`,integer,Internal identifier
  `name`,text,Knowledge base name
  `vector_schema`,text,Schema of the embeddings table
  `vector_table`,text,Embeddings storage table
  `model_name`,text,Embedding model used by this KB
  `distance_operator`,aidb.distanceoperator,Distance metric enum value
  `distance_operator_sql`,text,The distance operator in SQL-operator syntax
  `vector_data_column`,text,Column storing the embeddings
  `vector_key_column`,text,Column linking embeddings to source rows
  `vector_index`,jsonb,Vector index configuration
  `pipeline_ids`,integer[],IDs of all pipelines attached to this knowledge base
  `pipeline_names`,text[],Names of all pipelines attached to this knowledge base

.. code:: sql

   SELECT name, vector_schema, vector_table, distance_operator_sql
   FROM aidb.knowledge_bases;