Thursday, February 08, 2024

free AI book: Generative AI and LLMs for Dummies & Snowflake Text2SQL

 Generative AI and LLMs for Dummies - Snowflake

This book provides an introductory overview to LLMs and gen AI applications, along with techniques for training, tuning, and deploying machine learning (ML) models

Snowflake Copilot (in private preview) is an LLM-powered assistant to generate and refine SQL with natural language. Analysts can ask Snowflake Copilot a question, and it will write a SQL query using relevant tables. Users can also refine queries through conversation to filter down to the insights most relevant to the task. No setup is required. In addition, this text-to-code functionality will be coming soon programmatically via a general purpose function, Text2SQL, with Snowflake Cortex. 

AI: LLMs + Ontology?

Every "language" needs "words", organized in a "vocabulary" 

The name "Ontology" is common in "knowledge management",
and got some attention in late 90's and early 2000's with attempt to establish "Semantic Web"

It is very much relevant even today, and strangely may be also "emerging" from self-organization 
"computing neural networks", in particular those language-oriented: LLMs

Here is an interesting article from a person with deep experience in the Ontology domain.

The Role of the Ontologist in the Age of LLMs by KURT CAGLE

Ontology (information science) - Wikipedia

In information science, an ontology encompasses a representation, formal naming, and definitions of the categories, properties, and relations between the concepts, data, or entities that pertain to one, many, or all domains of discourse. More simply, an ontology is a way of showing the properties of a subject area and how they are related, by defining a set of terms and relational expressions that represent the entities in that subject area.