adesso Blog

Companies and authorities are often faced with the challenge of finding relevant information in huge amounts of data. Although Retrieval Augmented Generation (RAG) is still a relatively new technology for targeted retrieval of local domain knowledge, the technology often fails to aggregate complex distributed information. This is where GraphRAG comes into play. We present it in detail in this blog post.

A lot has happened since the breakthrough for Large Language Models (LLMs) with ChatGPT. What has remained is our desire to supplement these language models with further knowledge. There is no longer a one-size-fits-all solution, but there are numerous possibilities. This blog post provides an overview of the various options for optimising LLMs.

In the world of data processing, there are various approaches to improving efficiency and accuracy. One particularly promising approach is the use of Large Language Models (LLMs) to improve the linking of entities through entity linking. In this blog post, I will highlight the new possibilities and advantages of this technology.

Artificial intelligence is developing rapidly and Retrieval Augmented Generation (RAG) in particular has attracted a lot of attention recently. Large language models such as ChatGPT show their full potential when they are enriched with domain-specific knowledge through RAG. Despite this potential, users often face challenges. In this blog post, we look at the transition from basic to advanced RAG approaches and show how typical problems can be overcome.

Snowflake has taken a late but big step in the field of generative AI (GenAI). With services such as the Snowpark Container Service, Snowflake Cortex and Snowflake's own Large Language Model (LLM) 'Arctic', Snowflake wants to secure its place in the world of generative AI. The second part of the blog post looks at these three services and the opportunities they offer (for companies).

Large Language Models (LLMs), above all ChatGPT, have taken all areas of computer science by storm over the past year. As they are trained on a broad database, LLMs are fundamentally application-agnostic. Despite their extensive knowledge, however, they have gaps, particularly in highly specialised applications, which in the worst case can only appear to be compensated for by hallucinations. To reduce this risk, "Retrieval Augmented Generation" (RAG) has been established.

The world of artificial intelligence is developing at a breathtaking speed, and large language models (LLMs) are at the forefront of this revolution. LLM operationalisation is an essential part of this development and offers companies the opportunity not only to push the boundaries of technology, but also to set new standards for human–machine interaction. We explain why this is the case in our blog post.

In the world of artificial intelligence (AI), it has often been assumed that larger models are better. However, recent research shows that smaller language models, which were previously considered to only be an intermediate step on the path towards larger models, outperform or at least match the performance of large language models (LLMs) in various applications. In my blog post, I explore this point and present a variety of small language models. I will also take a look at the pros and cons of SLMs in a direct comparison with LLMs.

Running large language models using a fancy, ready-to-use interface increases accessibility for many, even for people who do not know any programming languages. Part two of my blog series focuses on technical aspects such as specifying the scope of the summary, prompt engineering and quality factors.