Integrations with the Knowledge graph

[Harsha]

Hi Team,
Is there any way to save the annotated data to knowledge graph directly, I have gone through the Database · Prodigy · An annotation tool for AI, Machine Learning & NLP page and couldn't find any.
Thanks.

[ryanwesslen]

Per the Prodigy database docs, Prodigy only provides out-of-the-box DB support for SQLite, MySQL, and Postgres.

I understand you want a knowledge graph, but what database tool are you looking to use? For example, Neo4j, MongoDB, etc.? If you're using anything outside of the built-in databases you'll need to create a custom DB class.

To give you an example, if you wanted to use MongoDB as a graph database as a knowledge graph, a community member has created a custom DB class for Prodigy: mondigy. That code is 2+ years and it's not owned by us so we can't guarantee it still works, but hopefully it should give you a start in thinking about how to develop this on your own.

Also, in addition to a graph database, typically knowledge graphs will also have an entity linking step. Here's a post that reviews what may be needed to create that:

Text to Knowledge Graph - Prodigy+Spacy

Hi, Yes, that approach sounds very reasonable! As these are three very different (and often complex) tasks, it definitely makes sense to run then in sequence, to allow annotators to focus on one specific task at the time. Just as a little tip: When you start off with your project, I would start by annotating a small portion of your corpus with all three tasks first. This will help you see whether your annotation guidelines of the first steps support the annotations you want to make in the last…