10 posts found
SLM, LLM, RAG and Fine-tuning: Pillars of Modern Generative AI
In the fast-paced world of Generative Artificial Intelligence (AI), there are several concepts that have become fundamental to understanding and harnessing the potential of this technology. Today we focus on four: Small Language Models(SLM), Large Language Models(LLM), Retrieval Augmented Generation…
Open data and generative AI: synergies and use cases
Artificial intelligence (AI) is revolutionising the way we create and consume content. From automating repetitive tasks to personalising experiences, AI offers tools that are changing the landscape of marketing, communication and creativity.
These artificial intelligences need to be trained wi…
RAG techniques: how they work and examples of use cases
In recent months we have seen how the large language models (LLMs ) that enable Generative Artificial Intelligence (GenAI) applications have been improving in terms of accuracy and reliability. RAG (Retrieval Augmented Generation) techniques have allowed us to use the full power of n…
GRAPH QL. Your best ally for the creation of data products.
The era of digitalisation in which we find ourselves has filled our daily lives with data products or data-driven products. In this post we discover what they are and show you one of the key data technologies to design and build this kind of products: GraphQL.
Introduction
Let's start at the beginni…
RAG - Retrieval Augmented Generation: The key that unlocks the door to precision language models
Teaching computers to understand how humans speak and write is a long-standing challenge in the field of artificial intelligence, known as natural language processing (NLP). However, in the last two years or so, we have seen the fall of this old stronghold with the advent of large language models (L…
Aplicación de la Especificación UNE 0079:2023 de gestión de calidad a los datos abiertos
Continuamos en esta segunda entrega de la serie de artículos con la aplicación de las especificaciones UNE. Antes de nada, recordemos que las Especificaciones UNE 0077, UNE 0078 y UNE 0079 introducen las buenas prácticas en el gobierno del dato, gestión del dato y gestión de calidad del dato con una…
Aplicación de las Especificación UNE 0078: 2023 a los datos abiertos
Este artículo constituye la tercera y última entrega de la serie de artículos dedicados dedicado a la aplicación de las especificaciones UNE de Gobierno, Gestión y Gestión de la calidad del dato a la publicación de datos abiertos. Recordemos que lo estamos realizando, aplicándolo al caso ficticio de…
The data sphere we live in: the interconnected data system
As technology and connectivity have advanced in recent years, we have entered a new era in which data never sleeps and the amount of data circulating is greater than ever. Today, we could say that we live enclosed in a sphere surrounded by data and this has made us more and more dependent on it. On…
Technical Standards to achieve Data Quality
Transforming data into knowledge has become one of the main objectives facing both public and private organizations today. But, in order to achieve this, it is necessary to start from the premise that the data processed is governed and of quality.
In this sense, the Spanish Association for Standardi…
Factors that define open data impact
The final impact that can be obtained through an open data initiative will ultimately depend on multiple interrelated factors that will be present (or absent) in these initiatives. That is why the GovLab of New York University has analyzed these factors thanks to the study of the several use cases c…
