Frau mit Brille

You want to learn more about generative AI and iFinder Enterprise Search?

Are you currently thinking about using generative AI, do you have current projects or use cases for large language models such as GPT and would like to learn how these can be integrated with iFinder? We will discuss the new AI application possibilities for your individual case with you.
Contact us

Save time and resources with AI Language Models

Large Language Models make it easier to deal with large volumes of documents, improve search, summarize relevant text and provide valid answers to your questions
  • Do you work with large volumes of data and documents?
  • Do documents need to be processed or evaluated quickly and effectively?
  • Large amounts of text and document content need to be summarized (e.g. as a support for the creation of notes/memos)?
  • It is important to you that 
    - the summaries contain accurate information from the organization's own sources, 
    - the user's access authorizations are taken into account and 
    - the sources are transparently traceable?
  • You want to retrieve information from large amounts of data, e.g. via dialog with a chatbot (question answering system)?

Large Language Models such as GPT (OpenAI), LaMDA (Google) or Luminous (Aleph Alpha) can help here.

Good to know: Large Language Models I LLMs I AI Language Models I Generative AI I Retrieval Augmented Generation (RAG)

Large Language Models (abbrev.: LLMs) are based on artificial intelligence and machine learning. They understand longer texts and are able to create a concise and summarized version with the key messages of the original text. Based on the relevant search results in the hit list, LLMs provide answers in natural language.

Generative AI (abbrev.: GenAI) refers to AI-based systems that use machine learning and large amounts of training data to generate new content, such as text, images, videos, or code. In the context of search, generative AI is primarily used for the generation of answers based on search results as well as for their enrichment.

The term Retrieval Augmented Generation (RAG) is important for Natural Language Processing. Retrieval augmented generation combines the strengths of search and LLMs. Using existing information, the model is able to better understand the context of user queries and generate more precise answers.

Our Enterprise Search Software iFinder integrates LLMs.

With a combination of search and language models, organizations can overcome data silos, realize the full potential of their data, facilitate effective knowledge discovery, and increase productivity. The iFinder can integrate both on-premises LLMs and SaaS models - we select the most suitable LLM for your use case.
Example Use Case: Learn more about the use of AI in a German federal agency

                                 The use case presented can of course be mapped for any sector, whether industry, the financial sector or public administration.

Example Use Case: Summary of documents in a federal agency
Government work often requires dealing with large documents and reports. The ability to receive these documents quickly and effectively can increase the efficiency of the work enormously.

Our use case addresses the task of "summarizing documents" and uses AI to automatically condense texts to the most important key messages.
Suchfeld Laptop
The Challenge:
This use case focuses on the selection of an appropriate Generative Large Language model for summarization.
This model is trained to analyze long texts and create an informative summary from them.

The goal is to find the optimal balance between information density and comprehensibility.
Zwei Kollegen im Gespräch
The Solution:
Selecting the best LLM for text summarization requires not only technical know-how, but also the content expertise of the federal agency. Although AI-driven models are capable of producing text summaries, their effectiveness depends heavily on the context and the specific nature of the text being summarized.

Therefore, it is crucial that the summaries are assessed and validated by federal agency experts.
Kollegen geben High-Five

Do you have your own special use case?

Icon Lupe

You want to use AI tools like LLMs for language processing?

Icon Kontakt

Contact us via the form providing the rough key data of your use case

Icon Glühbirne

We analyze your use case and advise you without obligation


Realize AI innovations with us - always keep control of your data

What we offer

  • A non-binding, concise assessment of which solution is right for your case and your organization
  • Explanations of benefits and points to consider (e.g. data security and privacy)
  • You do not enter into any obligations, we analyze your use case and advise you
  • Get in contact with:

    Franz Kögl, CEO                    Breno Faria, Product Lead AI         

Ihre Ansprechpartner

I consent to the collection and processing of my data from the contact form for the purpose of answering my query.
Consent can be withdrawn at any time.

Detailed information can be found in our privacy policy.  

Learn more about how AI tools will make search even better in the future


Maximum efficiency through Enterprise Search with genAI

How can organizations use large AI language models profitably and in compliance with data protection regulations? Our AI expert Breno Faria describes use cases with potential for companies and public authorities.
Read blog

Semantic Search

With the advent of Large Language Models and Deep Learning comes the need to redefine search engines. Read more in our blog article.
Read blog
Blick in die Glaskugel

Is the search engine dead?

ChatGPT has become a hot topic of discussion lately. Dr. Christoph Goller, Head of Research at search expert IntraFind, has experimented with ChatGPT and reflected its implications for search engines.
Read blog


Frequently Asked Questions concerning LLMs

👉 How does an LLM differ from traditional AI models and other language models?

The difference between LLMs and "traditional" AI models lies in the way they are trained and the types of tasks they can perform. Traditional AI models are often designed for specific tasks, such as text classification or entity extraction. They are usually trained on specific annotated datasets and are limited to the specific task for which they were trained.

LLMs, on the other hand, can perform a wide range of natural language processing (NLP) tasks, including (but not limited to) text generation, text classification, sentiment analysis, machine translation, and more.

LLMs are trained on gigantic datasets that can include billions of words or texts. They require large amounts of data and significant computational resources for training. Typically, working with such models requires specialized hardware and software, as well as considerable technical expertise. Due to the size of the models and training data, the quality of the output is very high and, especially when generating texts, often indistinguishable from human-generated information.


👉 What are the application areas for Large Language Model (LLM)?

LLMs can be used in a variety of ways. Among other things, LLMs can provide support in the following cases:

> LLMs can be used to analyze large amounts of text, recognize topics, and summarize long texts and articles.
> LLMs can serve as the basis for interactive chatbots and virtual assistants that can conduct human-like conversations.
> LLMs can serve as the basis for intelligent question-answering systems that can answer complex questions and provide solutions to specific problems.


👉 What are the advantages of combining LLMs with a search engine?

The delivery of false information (hallucination) is a known risk when using LLMs.

If the LLM is integrated into a search engine such as iFinder, this risk is minimized. The summaries and answers are based on the facts from the hit lists, which are determined by the search engine and not generated by the language model. The hit lists are also rights-checked, which means that the summaries and answers only contain information for which the respective user is authorized. This also prevents data protection violations.


👉 LLMs as SaaS or On-Premises?

The decision as to whether an LLM is operated on your own in-house servers (on-premises) or rented as a cloud solution as SaaS (Software-as-a-Service) depends on various factors.

In favor of an on-premises solution is the control that you as a company or authority have over the entire infrastructure and data. All data and processes are managed internally to minimize potential security concerns and meet compliance requirements.

What speaks in favor of a SaaS solution is that you don't have to set up the hardware infrastructure for operating the LLMs yourself.

With iFinder, we can process your data both on-premises and in the cloud with LLMs.


Do you have further questions?