Use case: Forensic Data Analysis RAG (retrieval augmented generation) is one of the hottest use cases of Large Language Models (LLMs such as GPT) in a business context: It allows to analyse your own company internal information while benefitting from the power of LLMs. And all that without having to share the data with third … Continue reading Using Kairntech RAG to analyse large Volumes of Email Data
Blog
We are pleased to share the recording of our webinar we held on April 4, 2024. https://youtu.be/OWlpMxB0cK0 Use case: Exploiting the Enron e-mail corpus During this product update webinar we show firstly the perspective of an end-user using the Enron e-mail corpus as an example:đ Ask a question or select from pre-configured questions (convenient for … Continue reading (Webinar) Question-answering on internal documents (RAG)
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 highlight 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 release (code name "Manta") allowing you 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 for question-answering The implementation of Retrieval Augmented Generation (RAG) framework in the platform allows you … Continue reading New Release (Manta)
Consortium investigates links between Covid and neurodegenerative diseases â Kairntech contributes AI / NLP capabilities Bonn, Dec 14-15. The EU Research project COMMUTE (âCOMORBIDITY MECHANISMS UTILIZED IN HEALTHCAREâ) has been kicked off at a two day meeting at the International Center of Information Technology (B-IT) at the University Bonn. Hosted and coordinated by the Fraunhofer … Continue reading EU Research Project COMMUTE has started
While LLMs (Large Language Models) address generic knowledge very well, it is the combination of LLMs with internal documents that delivers results that can be trusted. 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 leveraging … Continue reading (Whitepaper) Get more value out of LLMs and your own documents with RAG
Kairntech Question&Answer allows you to interact in natural language with your own content. Finding answers 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. Still they … Continue reading You have questions? Make your documents answer to you!
Natural language questions and answers on local and confidential information Introduction Large Language Models (LLMs such as GPT) have sparked significant progress in the way, users can interact with text: they deliver impressive results on tasks such as text generation, text summarization and many other scenarios. The predominant mode of interaction with LLMs is using … Continue reading Use the power of LLMs on your own documents using Kairntech
Yet another paper on AI/NLP-powered knowledge graph creation Elsevierâs âArtificial Intelligence in the Life Sciences" is to publish another text from Fraunhofer SCAI with contributions from Kairntech about "A natural language processing system for the efficient updating of highly curated pathophysiology mechanism knowledge graphsâ. Lead author Negin Babaiha and her colleagues outline the architecture of … Continue reading Fraunhofer SCAI and Kairntech publish joint work about analysing scientific information
Submission successful - project to start in Dec 2023. Good news from Bruxelles: The research proposal for project COMMUTE got accepted with pretty good grades. Starting Dec 2023 Kairntech will work with a fine team of research organisations from Cambridge, Amsterdam, Barcelona and led by Martin Hofmann-Apitius from Fraunhofer SCAI in Sankt Augustin on applying … Continue reading Kairntech to contribute text2graph capabilities to EU-funded project “COMMUTE”