---
title: "Wikimedia Deutschland enables AI search across Wikidata using DataStax Astra DB within watsonx.data; faster multilingual retrieval"
sdDatePublished: "2026-08-14T05:11:00Z"
source: "https://www.ibm.com/case-studies/wikimedia-deutschland"
topics:
  - name: "artificial intelligence"
    identifier: "medtop:20001298"
  - name: "software and applications"
    identifier: "medtop:20000231"
  - name: "scientific innovation"
    identifier: "medtop:20000736"
  - name: "online media industry"
    identifier: "medtop:20000311"
  - name: "education policy"
    identifier: "medtop:20001338"
locations:
  - "Germany"
---


Wikimedia Deutschland enables AI search across Wikidata using DataStax Astra DB within watsonx.data; faster multilingual retrieval

Making open knowledge Gen-AI-ready

Wikimedia Deutschland enables AI search across Wikidata using DataStax Astra DB within watsonx.data

Wikimedia runs some of the world’s most widely used open knowledge platforms, including Wikipedia and Wikidata. Every month, billions of people rely on Wikipedia to explore and understand the world’s knowledge across languages and topics. Behind the scenes, this ecosystem is powered by Wikidata, a vast open knowledge graph containing hundreds of millions of entities and relationships that connect information about people, places and events. While this structure makes it possible to organize knowledge at a global scale, it also creates challenges for accessing and exploring that information. Developers and researchers often need specialized query languages and complex workflows to retrieve relevant insights. As interest grows in applying generative AI to navigate and interpret this knowledge, Wikimedia Deutschland, which develops Wikidata, faces a critical challenge: how to make this enormous body of structured information easier to access, explore and use in modern generative AI applications.

To address this challenge, the Wikimedia Deutschland team introduced a new approach to exploring Wikidata, shifting from specialized query languages to semantic search techniques that allow generative AI systems to retrieve knowledge using natural language. Built on IBM® DataStax® Astra DB within IBM watsonx.data® , the architecture enables large language models to quickly identify relevant entities and relationships across Wikidata’s massive knowledge graph. This approach opens new possibilities for how developers, researchers and generative AI systems interact with open knowledge.

Instead of writing complex queries, users can explore information through natural language prompts, discover connections between concepts and retrieve relevant context across multiple languages. By combining vector search with Wikidata’s structured knowledge, the platform makes it easier to build generative AI applications that can surface insights, navigate relationships between entities and help people explore one of the world’s largest open knowledge repositories in more intuitive ways.

By introducing vector search and semantic retrieval techniques, the Wikimedia Deutschland team has taken an important step toward making Wikidata more accessible for modern generative AI applications. The new approach allows developers and generative AI systems to retrieve relevant knowledge more easily, helping surface connections between entities and explore information across languages and domains. Looking ahead, the team is continuing to expand these capabilities by adding support for more languages, testing the architecture with larger datasets and combining semantic search with the precision of Wikidata’s structured knowledge. These efforts aim to further improve how generative AI systems discover and interpret information within one of the world’s largest open knowledge graphs.

Wikimedia Deutschland is a non-profit association with over 111,000 members and 180 employees that is committed to promoting freely available knowledge in the digital space. The association supports the volunteer communities of Wikipedia and other Wikimedia projects in Germany. Wikimedia Deutschland develops and maintains free software and the free database Wikidata. The association is committed to creating conditions in the areas of digital and education policy that enable free access to knowledge and data. We also cooperate with cultural institutions to make more cultural heritage freely accessible.