MySQL AI — AutoML and GenAI

MySQL AI provides integrated, automated, and secure machine learning (ML) and generative AI capabilities. AutoML simplifies ML processes, helping you build, train, and explain ML models without data movement or added costs. Similarly, in-database LLMs, a built-in vector store, and embedding models enable GenAI, semantic search, and retrieval-augmented generation (RAG) at reduced infrastructure costs and without data movement.

• GenAI — Use in-database LLMs to help retrieve data and generate or summarize content—without the hassle of external LLM selection and integration. Reduce infrastructure costs by eliminating the need to provision GPUs.
• Vector store — Let LLMs search your proprietary documents to help get more accurate and contextually relevant answers—without moving data to a separate vector database. MySQL automates embedding generation. The vector store houses your proprietary documents in various formats, acting as the knowledge base for RAG to help you get more accurate and contextually relevant answers.
• Comprehensive ML capabilities — Eliminate complex and time-consuming data movements to a separate ML service with integrated ML. Easily apply ML training, inference, and explanation to data in MySQL. AutoML supports anomaly detection, forecasting, classification, regression, and recommender system tasks, including on text columns.
• Explainable models and data drift detection — All the models trained by AutoML are explainable. It delivers predictions with an explanation of the results, supporting you with trust, fairness, and regulatory compliance. Data drift detection helps analysts determine when to retrain models by detecting the differences between the data used for training and new incoming data.
• Text to SQL (NL2SQL) — Query your database using natural language. NL2SQL uses the LLM to convert a natural query into SQL. It harvests relevant metadata to help the model better interpret the user's intent and generate SQL statements tailored to the database's structure.