...
This toolkit element passes the document text to an external (or embedded) extraction engine to return entities and associations (and optionally metadata).
TODO
Warning |
---|
Most feature extractors require for text to have been extracted with a "textEngine" or "text" object before it in the pipeline, unless the data comes from file (which automatically fills in a document's "fullText" field). AlchemyAPI is an exception for URLs because it can do both steps. Other custom extractors may not require text, eg because they operate on existing metadata fields, or entities etc. |
Format
TODO convert to JSON
...