View only. Sign in to run this demo.

Sign in

Knowledge Curator

Collect the facts for a fixed set of topics from normalized sources. Every fact carries an exact quote, its file and its location. Edit the facts and check the quotes again.

How to use the Knowledge Curator

  1. 1Bring the sourcesSend them from the Source Normalizer, upload its .zip, or start from a ready-made set.
  2. 2Define the topicsA topic is a subject to collect facts about, with the items it must cover.
  3. 3CurateA model reads the sources and writes facts. Each fact has an exact quote, its file and its place.
  4. 4Explore and checkFilter the facts, see each quote in its source, follow conflicts and missing items, edit, and verify the quotes.
  • Every quote must appear word for word in its source. A fact whose quote is not there, even after asking again, is dropped and listed. The instructions decide whether a conflict between sources is resolved: for example, primary sources outrank secondary ones.
  • The result lives in this browser tab. Reloading or closing the tab loses it, so download the .zip first.

Start from a ready-made set of sources

1. The sources
Send them from the Source Normalizer, or upload the .zip it downloads.
3. Instructions
Which sources to trust more, scope and style, and the language of the summaries. When sources disagree, this decides whether a conflict is resolved.
2. Topics
The topics to collect facts for. Under Advanced, list the items a topic must cover; the ones no source covers are reported as missing.
1

No topic defined yet. Add a title and what to look for, or load an example.

No knowledge yet

Load an example or add normalized sources, then click Curate. The facts appear here, where you can filter them and see each quote in its source.

GAIK Toolkit

Generative AI building blocks for knowledge capture, access and synthesis.

Co-funded by the European Union

Demos

Use CasesSoftware ModulesSoftware ComponentsNo-code Assets

Resources

GitHubDocsPyPI

Project

gaik.aiRequest AccessPrivacy

Disclaimer: The demo website uses Microsoft Azure APIs for OpenAI's and Anthropic's models, and Google's Vertex AI for Gemini models. No user data is retained, and neither Azure nor Vertex AI uses any user data for model training.

© 2026 GAIK ProjectThe gaik package is open source under the MIT licence.
GAIK