11 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…
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…
What is the value of open geographic data?
Geographic data allow us to learn about the world around us. From locating optimal travel routes to monitoring natural ecosystems, from urban planning and development to emergency management, geographic data has great potential to drive development and efficiency in multiple economic and social area…
How Artificial Intelligence and Open Data can re-imagine our cultural future
We are currently in the midst of an unprecedented race to master innovations in Artificial Intelligence. Over the past year, the star of the show has been Generative Artificial Intelligence (GenAI), i.e., that which is capable of generating original and creative content such as images, text or music…
GeoParquet 1.0.0: new format for more efficient access to spatial data
Cloud data storage is currently one of the fastest growing segments of enterprise software, which is facilitating the incorporation of a large number of new users into the field of analytics.
As we introduced in a previous post, a new format, Parquet, has among its…
Open data as a source of knowledge for generative artificial intelligence
Generative artificial intelligence refers to machine’s ability to generate original and creative content, such as images, text or music, from a set of input data. As far as text generation is concerned, these models have been accessible, in an experimental format, for some time, but began to generat…
The second edition of Asedie's top 3, available in seven autonomous communities
The Multisectorial Association of Information (ASEDIE), which brings together the infomediary companies of our country, once again includes among its annual objectives the promotion of the reuse of public and private information. Thus, and almost in parallel to the beginning of the new year, last De…
Artificial Intelligence applied to the identification and classification of diseases detected by radiodiagnosis
In this post we have described step-by-step a data science exercise in which we try to train a deep learning model with a view to automatically classifying medical images of healthy and sick people.
Diagnostic imaging has been around for many years in the hospitals of develo…
Why should you use Parquet files if you process a lot of data?
It's been a long time since we first heard about the Apache Hadoop ecosystem for distributed data processing. Things have changed a lot since then, and we now use higher-level tools to build solutions based on big data payloads. However, it is important to highlight some best practices related to ou…
4 examples of harmonisation of datasets
In any project related to data, it is common to have different sources of information. Data is key for companies and public administrations, in decision making or as a basis for the implementation of projects, services or products. But if these data sources display information in a heterogeneous way…
