The first step to building great voice-driven content discovery is creating a document collection.
You can index documents by crawling a website or by using our API – and we’ve just open-sourced a new way to post documents to the MindMeld API! Using our new Node.js poster script, you can programmatically upload a very large collection of documents for your app (we’re talking millions of nodes). Once you add your document collection, we build a custom knowledge graph that enables highly accurate natural language understanding for your application domain.
To learn more, check out our Github repository and ReadMe. Feel free to contact us with any questions!