AI in Action

This initiative enables data scientists and engineers to benefit from Ontotext’s AI capabilities: GraphDB and Ontotext Metadata Studio features, public services, demonstrators, and datasets

AI in Action shares design patterns, sample queries and configs, evaluations and benchmarks – everything you need in order to understand how these capabilities can be used and what performance and quality should be expected.

New call-to-action


You can also join our dedicated LinkedIn Group and start the conversation there.

News & Blog Posts

Who is AI in Action for?

Early-stage AI enthusiasts tend to be overenthusiastic about a single model and approach. They often think that vector representations were invented recently, while in fact, the “A Vector Space Model for Automatic Indexing” paper was published in 1975 and each FTS engine developed in the last 30 years has a vector database component in it. Adept AI engineers know that there is no silver bullet and you should make a thoughtful decision about the most efficient and practical combination of data, tools, models and engines. AI-in-action is aimed to help both groups.

Showcase Demonstrators

NOW – News On The Web

NOW – News On The Web

Test how your datasets can get enriched and annotated as a result of providing rich digital content to users with NOW – a free public service designed to show you the capabilities of semantic technology for publishing purposes.

See it in action

OTKG - Ontotext Knowledge Graph

OTKG – Ontotext Knowledge Graph 

Navigate content enriched with semantic metadata and chat with Ontotext’s marketing content in OTKG – a free public demonstrator showcasing Ontotext’s signature semantic technology products working in concert with AI.

See it in action

Products, Solutions and Services Involved

Ontotext GraphDB

Ontotext Metadata Studio

AI in Action Fundamentals

What Is a Large Language Model?

Read about LLMs – deep learning models that learn patterns and relationships from large volumes of textual data and can be used for generating new text, based on inputs, by predicting the most probable sequence of words to follow

What Is Natural Language Querying?

Read about how NLQ enables users to interact with complex databases using ordinary human language, eliminating the need for specialized query language skills.

What Is Graph RAG?

Discover the transformative potential of Retrieval Augmented Generation (RAG), a method that enhances large language models (LLMs) with external knowledge for more accurate, contextual question answering.

What is Entity Linking?

Read about the basics of entity linking, how it works, why it’s vital for Natural Language Processing and why its synergy with knowledge graphs facilitates deeper understanding and processing of textual content

What Is Extractive Question Answering?

Discover how extractive question answering unlocks the doors to a new world where every question’s answer is provided clearly and concisely.

What is Event Extraction?

Event extraction transforms unstructured text into a structured description of what happened. Add semantic modeling and a knowledge graph and you get knowledge discovery through complex querying and faceted search