Back to Mindsdb

AI Integrations

docs/integrations/ai-overview.mdx

26.1.02.2 KB
Original Source

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

<p align="center"> </p>

MindsDB offers a wide range of <strong>AI engines</strong> 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.

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

Large Language Models

<CardGroup cols={4}> <Card title="Anthropic" icon="link" href="/integrations/ai-engines/anthropic"></Card> <Card title="Cohere" icon="link" href="/integrations/ai-engines/cohere"></Card> <Card title="Google Gemini" icon="link" href="/integrations/ai-engines/google_gemini"></Card> <Card title="Hugging Face Inference API" icon="link" href="/integrations/ai-engines/huggingface_inference_api"></Card> <Card title="Ollama" icon="link" href="/integrations/ai-engines/ollama"></Card> <Card title="OpenAI" icon="link" href="/integrations/ai-engines/openai"></Card> <Card title="Vertex AI" icon="link" href="/integrations/ai-engines/vertex"></Card> </CardGroup>

Bring Your Own Models

<CardGroup cols={4}> <Card title="BYOM" icon="link" href="/integrations/ai-engines/byom"></Card> <Card title="MLflow" icon="link" href="/integrations/ai-engines/mlflow"></Card> </CardGroup> </br> <Info> **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.

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

Or, alternatively:

sql
SHOW HANDLERS
WHERE type = 'ml';

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

sql
SELECT *
FROM information_schema.ml_engines;

Or, alternatively:

sql
SHOW ML_ENGINES;
</Info>