Learn how to connect your nodegoat environment to Transkribus and other services

CORE Admin
An example of a document that can be transcribed and ingested into nodegoat.

The nodegoat Guides have been extended with a new section on 'Ingestion Processes'. An Ingestion Process allows you to query an external resource and ingest the returned data in your nodegoat environment. Once the data is stored in nodegoat, it can be used for tagging, referencing, filtering, analysis, and visualisation purposes.

You can ingest data in order to gather a set of people or places that you intend to use in your research process. You can also ingest data that enriches your own research data. Any collection of primary sources or secondary sources that have been published to the web can be ingested as well. This means that you can ingest transcription data from Transkribus, or your complete (or filtered) Zotero library.

The development of the Ingestion Process was part of the project 'Dynamic Data Ingestion (DDI)' and builds upon the Linked Data Resource feature, initially commissioned by the TIC-project in 2015 and extended in collaboration with ADVN in 2019. Every nodegoat user is able to make use of these features. Every endpoint that outputs JSON or XML can be queried. nodegoat data can be exported in CSV and ODT formats, or published via the nodegoat API as JSON and JSON-LD.

data transformation

Latest Blog Posts

Data and Dialogue: Retrieval-Augmented Generation in nodegoat

CORE Admin

We have extended nodegoat in order to be able to communicate with large language models (LLMs). Conceptually this allows users of nodegoat to prompt their structured data. Technically this means nodegoat users are able to create vector embeddings for their objects and use these embeddings to perform retrieval-augmented generation (RAG) processes in nodegoat.

This development connects three of nodegoat’s main functionalities into a dynamic workflow:  Linked Data Resources, the new vector store (nodegoat documentation: Object Descriptions, see ‘vector’), and Filtering. The steps to take are as follows:

Vector Embedding

The first step is to use one or multiple Reversed Collection templates to determine the textual content for each Object. This step transforms any dataset stored as structured data into a textual representation that can be used as input value for the generation of a vector embedding. This allows the user to select only those elements that are relevant for the process.

A Reversed Collection using a template (left) to collect structured data into full text (right).

Next, the textual representation of each Object is sent to an LLM in order to create an embedding for each Object. The communication between nodegoat and an LLM is achieved by making use of Linked Data Resources and Ingestion Processes.[....]

AIdata analysisnodegoat
Continue reading

Upcoming nodegoat workshops

CORE Admin

In the next couple of months we will be running these events at various locations throughout Europe. Find the latest information about this here: https://nodegoat.net/workshop

  • 05-02-2026: nodegoat Workshop at the University of Basel organised by the Research and Infrastructure Support team and the Swiss National Data and Service Center for the Humanities.
  • 19-02-2026: nodegoat Workshop at the University of Jena.
  • 25-03-2026: Workshop: Einführung in nodegoat at the University of Bonn.
  • 16-04-2026: nodegoat Workshop at the Research Centre of the Slovenian Academy of Sciences and Arts in Ljubljana.
  • 24-04-2026: nodegoat Workshop at KU Leuven, organised by CLARIAH-VL.
  • 10-07-2026: nodegoat Curious: Building a Custom Relational Database for Your Research at the Digital Medieval Studies Institute, IMC Leeds.
training
Continue reading