MindsDB integrates with numerous AI frameworks, facilitating deployment and management of AI models.

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

This section contains instructions on how to create and deploy models within MindsDB, utilizing different AI/ML frameworks.

​
Large Language Models

Anthropic

Anyscale Endpoints

Cohere

Google Gemini

Hugging Face

Hugging Face Inference API

LangChain

LlamaIndex

MonkeyLearn

Ollama

OpenAI

Portkey

Replicate (LLM)

Vertex AI

​
Bring Your Own Models

BYOM

MLflow

Ray Serve

​
Anomaly Detection

Anomaly Detection

​
AutoML

Lightwood

PyCaret

​
Time Series Models

NeuralForecast

StatsForecast

TimeGPT

​
Recommender Models

LightFM

Popularity Recommender

​
Audio Models

Replicate (Audio)

​
Image Models

Clipdrop

Replicate (Text2Img)

Replicate (Img2Text)

​
Video Models

TweleveLabs (Video Semantic Search)

Replicate (Text2Video)


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

Metadata about AI handlers and AI engines

AI handlers represent a raw implementation of the integration between MindsDB and an AI/ML framework. These are used to create AI engines.

Here is how you can query for all the available AI 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;