AI Engines & AI Tables

MindsDB offers a wide range of AI engines used to create models and incorporate them in the data landscape as virtual AI-tables. MinsdDB abstracts AI models as virtual tables, or Generative AI Tables, that can generate data from the underlying model upon being queried.

MindsDB provides over 20 AI/ML handlers to connect the available ML frameworks.

If you don’t find an ML framework of your interest, you can request a feature here or build an ML handler following this instruction.

This section contains instructions on how to create models in MindsDB, utilizing different ML frameworks.

Large Language Models

Ollama

Anyscale Endpoints

ReplicateLLM

Vertex AI (Google)

Anthropic

Cohere

OpenAI

Hugging Face

LangChain

LlamaIndex

MonkeyLearn

RAG

Bring Your Own Models

BYOM

Ray Serve

MLflow

AutoML

Lightwood

PyCaret

Ludwig

Autokeras

Autosklearn

Time Series Models

StatsForecast

NeuralForecast

TimeGPT

Audio Models

Replicate (Audio)

Image Models

Replicate (Text2Img)

Replicate (Img2Text)

Large Video Models

TweleveLabs (Video Semantic Search)

Repliate (text2video)

Metadata SQL Syntax

Here is how you can query for all the available ML handlers used to create AI engines.

SELECT *
FROM information_schema.handlers
WHERE type = 'ml';

Or, alternatively:

SHOW HANDLERS
WHERE type = 'ml';

And here is how you can query for all the created AI engines:

SELECT *
FROM information_schema.ml_engines;

Or, alternatively:

SHOW ML_ENGINES;