Record Pipelines

Record pipelines can update and augment information as it is indexed. Steps can include:
  • Data transformation - e.g. trimming a title
  • Data enrichment - e.g. generating a latitude and longitude from an address
  • Classification - e.g. labeling content with a category based on an existing model
  • Vectorization - e.g. clustering uncategorized records
  • Image recognition - e.g. detection of objects and faces, read printed and handwritten text, extraction of metadata