AIDB
====

Where to start
--------------

If you’re new to AIDB, follow this end-to-end workflow:

1. \*\* :ref:`Pipelines overview <Pipelines overview>`  \*\* — Learn the core concepts: what pipelines and
   knowledge bases are, and how they fit together.

2. \*\* :ref:`Installing AIDB <Installing AIDB>`  \*\* — Install the ``aidb`` package, configure
   ``shared_preload_libraries`` , and enable the extension in your
   database.

3. \*\* :ref:`Integrating models <Integrating models>`  \*\* — Register the AI model that will power your
   pipeline. Every pipeline step that generates embeddings or processes
   text requires a model — either a built-in local model (no setup
   needed) or an external API model that you register with
   ``aidb.create_model()`` . Do this before creating pipelines.

4. \*\* :ref:`Configuring external storage <Configuring external storage>`  \*\* *(optional)* — If your source data lives in
   S3 or a local file system rather than a Postgres table, configure a
   volume using PGFS so pipelines can read from it.

5. \*\* :ref:`Data pipelines <Pipelines reference>`  \*\* — Define a pipeline that reads from your data
   source, transforms it (chunk, parse, embed), and writes the output to
   a knowledge base. This is where the model you registered in step 3 is
   put to work.

6. \*\* :ref:`Knowledge bases reference <Knowledge bases reference>`  \*\* — Query the vector embeddings your pipeline
   produced. Use ``aidb.retrieve_text()`` or ``aidb.retrieve_key()`` for
   semantic search, or combine vector and keyword search with hybrid
   search.

Documentation map
-----------------

.. csv-table::
  :header: Section,What it covers
  :widths: 10,30
  :align: left
  :class: longtable

  :ref:`AIDB 7.2.0 release notes<AIDB 7.2.0 release notes>` ,What changed in each version
  :ref:`Compatibility<Compatibility>` ,Supported platforms and Postgres versions for AIDB and PGFS
  :ref:`Installing AIDB<Installing AIDB>` ,How to install and configure the AIDB extension
  :ref:`Integrating models<Integrating models>` ,"Local models, external APIs (OpenAI, NIM, Gemini, OpenRouter), and supported model variants"
  :ref:`Configuring external storage<Configuring external storage>` ,Using S3-compatible object stores and local file systems as pipeline data sources
  :ref:`Reference → Functions <Pipelines reference>` ,"Defining pipelines, pipeline steps, orchestration, and examples"
  :ref:`Knowledge bases reference<Knowledge bases reference>` ,"Semantic search, hybrid search, and vector index options"
  :ref:`SQL functions<SQL functions>` ,"Standalone SQL functions for chunking, parsing, OCR, summarization, and embedding"
  ":ref:`Reference → Functions <Pipelines API reference>` ",Full API reference for all AIDB functions and views