Integrating models
==================

Models are the AI engines that power AIDB’s core operations — embedding
generation, text chunking, summarization, OCR, and completions. Every
pipeline step and SQL function that performs an AI operation requires a
model to be registered and reachable before it can run.

**When to add models:** Register your models after installing and
configuring AIDB, and before creating pipelines or knowledge bases that
reference them. If you’re using one of AIDB’s built-in local models
(such as BERT or CLIP), no registration is needed — they’re available
immediately. For external APIs (OpenAI, NVIDIA NIM, Gemini) or custom
HuggingFace variants, use ``aidb.create_model()`` to register the model
first.

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

  :ref:`Local models<Local models>` ,"Built-in local models (BERT, CLIP, T5, Llama) and how to register custom variants"
  :ref:`Support matrix<Support matrix>` ,Pre-vetted HuggingFace model variants confirmed to work with AIDB's local providers
  :ref:`External model connections<External model connections>` ,"Connecting to OpenAI-compatible APIs, NVIDIA NIM, Google Gemini, and OpenRouter"

.. toctree::
  :maxdepth: 3

  integrating-models--integrated-models
  integrating-models--support-matrix
  integrating-models--external-model-connections