Publications on AI for internal auditing practices are few and far between, and therefore deserve a mention. In Repères 2024 (Editions La Découverte), a PhD student and an associate professor at Paris-Dauphine University, a partner at Grant Thornton France, Hayk Hovhannisyan, Beatrice Bon Michelet, Nicolas Gasnier-Duparc, have written a report on the subject of:"The impact … Continue reading AI for internal audit – a promising start
Tag: Retrieval Augmented Generation
Retrieval Augmented Generation (RAG) is an approach used with Natural Language Processing. The corresponding use-case is called Question-Answering.
When a question is asked the so-called retriever searches for relevant segments within a set of documents. These search results are then summarized using a Large Language Model.
We highly recommend reading the Kairntech whitepaper on RAG.
How to setup question answering? – Kairntech Documentation
How to use the question answering interface? – Kairntech Documentation
How to compare results in question answering project? – Kairntech Documentation
The german DGI (Association for Information and Knowledge) organized a webinar on June 26 on Kairntech RAG. The objective: analyse documents with Large Language Models following the retrieval-augmented generation (RAG) approach. Webinars are a fine tool to comfortably convene an audience and deliver a presentation. But often they tend to do a lot of frontal … Continue reading DGI webinar on Kairntech RAG
We are proud to announce that Kairntech wins a European Defense Fund (EDF) project. This call for projects received in total €1,031 million of EU funding. Kairntech is a leading technology provider of the NEMO consortium which is led by Sintef AS (Norway). Over the course of this 5-year project NEMO will develop a state-of-the-art … Continue reading Kairntech wins European Defense Fund project
The EU-funded Mindspeak project starts Digital mental healthcare interventions (DMHIs) powered by GenAI are a solution to provide accessible treatment for patients suffering from common mental health problems (i.e., depression and anxiety disorders). NiceDay's DMHIs platform is an academically verified effective tool for treating depression or anxiety disorders. Within the Mindspeak project this platform will … Continue reading GenAi for mental healthcare
Data analytics on Enron emails Kairntech RAG (Retrieval Augmented Generation) for forensics is one of the hottest use cases of Large Language Models. It allows to analyse internal information while benefitting from the power of LLMs. And all that without having to share the data with third parties or running costly retraining or finetuning campaigns. … Continue reading Kairntech RAG for forensics
We are pleased to share the recording of our webinar we held on April 4, 2024 on RAG question answering of Enron emails. https://youtu.be/OWlpMxB0cK0 Use case: RAG on the Enron e-mail corpus During this product update webinar we showed the perspective of an end-user using the Enron e-mail corpus as an example: Ask a question … Continue reading (Webinar) RAG on Enron emails
Kairntech delivered a new DGI Webinar on Feb 26, 2024 The advent of Large Language Models such as GPT as profoundly affected the way we access information and consume, assess and generate content. In the webinar hosted by the DGI-Info we highlighted aspects of this development and emphasize what challenges need to be addressed in … Continue reading (Webinar) I am asking the questions – my documents answer
We are very proud to present our latest software release (code name "Manta"). This release allows customers to create business value even faster with exciting new components (RAG, Whisper for Speech-to-text conversion...) and the latest Large Language Models (GPT, Llama2, Mistral...). Fast prototyping The implementation of the Retrieval Augmented Generation (RAG) framework in the platform … Continue reading Software release (Manta)
While LLMs (Large Language Models) address generic knowledge very well. Our whitepaper explains that it is the combination of LLMs with internal documents that delivers trustworthy outcomes. This so-called RAG (Retrieval Augmented Generation) approach consists of a preparation phase whereby documents are uploaded, converted, segmented, vectorized and indexed. Once a question is asked a retriever … Continue reading Whitepaper: get more value out of LLMs and internal documents with Kairntech RAG
Kairntech Question Answering allows you to interact in natural language with your own content Finding answers to specific question in complex documents or large collections of documents can be a cumbersome effort, despite powerful search engine technologies. Often users find themselves trying different combinations of AND and OR and exact phrase searches and so on. … Continue reading You have questions? Make your documents answer to you!