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 default 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>` ,"Default local models (BERT, CLIP, T5, Llama), model providers, registering custom local models, and llama.cpp GGUF models"
  :ref:`External model connections<External model connections>` ,"OpenAI-compatible APIs, the native OpenAI Responses and Anthropic Messages APIs, NVIDIA NIM, Google Gemini, and OpenRouter"
  :ref:`Support matrix<Support matrix>` ,Pre-vetted local model variants and supported NVIDIA NIM models

.. toctree::
  :maxdepth: 3

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