Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Raiffeisen Switzerland builds an 'Ask your documents' RAG chat tool for employees on Azure
…path towards more efficient information retrieval and processing. The Solution Our cloud and data science team developed an Azure-based prototype of an innovative web application called ‘Ask your documents’. This application allows employees to ask text-based questions via an interactiv…
Description
Raiffeisen Switzerland worked with Zühlke to build an Azure-based prototype web application, 'Ask your documents', where employees ask questions in natural language and receive answers generated from company-specific documents using GPT-4 and retrieval-augmented generation, with references shown for verification. The source says it improves hit rates and answer quality compared with traditional search; it gives no figures.
…e-based prototype of an innovative web application called ‘Ask your documents’. This application allows employees to ask text-based questions via an interactive chat interface. Answers are then generated automatically based on company-specific documents to ensure a fact-based response. Relevant references are also shown for verification and to provide deeper context. Large language models like GPT-4 as well as Retrieval-Augmented Generation (RAG…
…ient in retrieving information and getting answers to their specific questions. The solution not only improves hit rates, but also the general quality of the answers in comparison to traditional search methods. Our collaboration with Raiffeisen Switzerland and the development of the ‘Ask y…
Company
Raiffeisen Switzerland
…GPT, have created new ways of interacting with users and handling textual data. Raiffeisen Switzerland wanted to leverage this advanced technology to capitalise on the collective internal knowledge hidden within its extensive…
Country
Switzerland
…GPT, have created new ways of interacting with users and handling textual data. Raiffeisen Switzerland wanted to leverage this advanced technology to capitalise on the collective internal knowledge hidden within its extensive…
Region
Europe
…GPT, have created new ways of interacting with users and handling textual data. Raiffeisen Switzerland wanted to leverage this advanced technology to capitalise on the collective internal knowledge hidden within its extensive…
Industry
Financial Services
…tions & more! Sign up here Language navigation. The current language is english Banking Raiffeisen: Enhancing knowledge management with generative AI We helped create an LLM-powered ‘Ask your documents’ tool, boosting information…
Problem
Raiffeisen Switzerland wanted to capitalise on the collective internal knowledge hidden within its extensive company-specific text database, by creating a chat solution that accurately answers employees' questions in natural language.
…GPT, have created new ways of interacting with users and handling textual data. Raiffeisen Switzerland wanted to leverage this advanced technology to capitalise on the collective internal knowledge hidden within its extensive company-specific text database. The aim was to create a chat solution to accurately answer questions from employees in a natural language. This would be a key step on the path towards more efficient information retriev…
Solution
Zühlke's cloud and data science team developed an Azure-based prototype web application called 'Ask your documents'. Employees ask text-based questions in an interactive chat interface; answers are generated automatically from company-specific documents, with references shown for verification. It uses large language models such as GPT-4 and Retrieval-Augmented Generation (RAG).
…path towards more efficient information retrieval and processing. The Solution Our cloud and data science team developed an Azure-based prototype of an innovative web application called ‘Ask your documents’. This application allows employees to ask text-based questions via an interactive chat interface. Answers are then generated automatically based on company-specific documents to…
…evant references are also shown for verification and to provide deeper context. Large language models like GPT-4 as well as Retrieval-Augmented Generation (RAG) are used for these advanced functions. The Results The ‘Ask your documents’ application allows employees at Raiffeisen…
Business value
According to the case study, the application lets employees retrieve information and get answers more efficiently, and improves hit rates and the general quality of answers compared with traditional search methods. No figures are given.
…l-Augmented Generation (RAG) are used for these advanced functions. The Results The ‘Ask your documents’ application allows employees at Raiffeisen Switzerland to be more efficient in retrieving information and getting answers to their specific questions. The solution not only improves hit rates, but also the general quality of the a…
…ient in retrieving information and getting answers to their specific questions. The solution not only improves hit rates, but also the general quality of the answers in comparison to traditional search methods. Our collaboration with Raiffeisen Switzerland and the development of the ‘Ask y…
AI capabilities
Generative AI, Conversational AI
…e-based prototype of an innovative web application called ‘Ask your documents’. This application allows employees to ask text-based questions via an interactive chat interface. Answers are then generated automatically based on company-specific documents to…
…evant references are also shown for verification and to provide deeper context. Large language models like GPT-4 as well as Retrieval-Augmented Generation (RAG) are used for these advanced functions. The Results The ‘Ask your documents’ application allows employees at Raiffeisen…
Technology
Azure
…path towards more efficient information retrieval and processing. The Solution Our cloud and data science team developed an Azure-based prototype of an innovative web application called ‘Ask your documents’. This application…
Deployment model
Cloud
…path towards more efficient information retrieval and processing. The Solution Our cloud and data science team developed an Azure-based prototype of an innovative web application called ‘Ask your documents’. This application…
Deployment options
cloud
…path towards more efficient information retrieval and processing. The Solution Our cloud and data science team developed an Azure-based prototype of an innovative web application called ‘Ask your documents’. This application…
Headline outcome
…ient in retrieving information and getting answers to their specific questions. The solution not only improves hit rates, but also the general quality of the answers in comparison to traditional search methods. Our collaboration with Raiffeisen Switzerland and the development of the ‘Ask y…
Use case type
Knowledge search
…s english Banking Raiffeisen: Enhancing knowledge management with generative AI We helped create an LLM-powered ‘Ask your documents’ tool, boosting information retrieval efficiency and response accuracy. The Challenge Generative AI has opened the door to new business applications of…
