Gen AI data management

The first stage is to build an automated ML pipeline for data collection, data preparation, training and evaluation, including: data collection, data filtering, data processing, labelling, embeddings.

In this section

• Using LLMs to process unstructured data
• Vector databases
• Guardrails for data management

See also

• Deploying an LLM using MLRun

• Model monitoring using LLM

• Alerts and notifications