NLPCraft/org.apache.nlpcraft/NCPipeline

NCPipeline

trait NCPipeline

NLP processing pipeline for the input request. Pipeline is associated with the model.

An NLP pipeline is a container for the sequence of processing components that take the input text at the beginning of the pipeline and produce the list of variants at the end of the pipeline. Schematically the pipeline looks like this:

                                    +----------+        +-----------+         +--------+
 *=========*     +---------+    +---+-------+  |    +---+-------+   |     +---+-----+  |
 :  Text   : ->  |  Token  | -> | Token     |  | -> | Token      |  | ->  | Entity  |  | ----.
 :  Input  :     |  Parser |    | Enrichers |--+    | Validators |--+     | Parsers |--+      \
 *=========*     +---------+    +-----------+       +------------+        +---------+          \
                                                                                                }
                     +--------+        +--------+        +-----------+        +----------+     /
*============*    +---+-----+  |    +---+-----+  |    +---+--------+  |    +---+-------+  |    /
:  Variants  : <- | Variant |  | <- | Entity  |  | <- | Entity     |  | <- | Entity    |  | <-'
:  List      :    | Filters |--+    | Mappers |--+    | Validators |--+    | Enrichers |--+
*============*    +----- ---+       +----- ---+       +------------+       +-----------+

The result variants are then passed further to the intent matching. Note that only one token parser and at least one entity parser is required for the minimal pipeline.

See also:
Source:
NCPipeline.scala
class Object
trait Matchable
class Any

Value members

Abstract methods

def getEntityParsers: List[NCEntityParser]

Gets the list of entity parser. At least one entity parser is required.

Gets the list of entity parser. At least one entity parser is required.

Source:
NCPipeline.scala
def getTokenParser: NCTokenParser

Get the token parser. One token parser is required for the pipeline.

Get the token parser. One token parser is required for the pipeline.

Source:
NCPipeline.scala

Concrete methods

def getEntityEnrichers: List[NCEntityEnricher]

Gets optional list of entity enrichers. Can return an empty list but never null.

Gets optional list of entity enrichers. Can return an empty list but never null.

Source:
NCPipeline.scala
def getEntityMappers: List[NCEntityMapper]

Gets optional list of entity mappers. Can return an empty list but never null.

Gets optional list of entity mappers. Can return an empty list but never null.

Source:
NCPipeline.scala
def getEntityValidators: List[NCEntityValidator]

Gets optional list of entity validators. Can return an empty list but never null.

Gets optional list of entity validators. Can return an empty list but never null.

Source:
NCPipeline.scala
def getTokenEnrichers: List[NCTokenEnricher]

Gets optional list of token enrichers. Can return an empty list but never null.

Gets optional list of token enrichers. Can return an empty list but never null.

Source:
NCPipeline.scala
def getTokenValidators: List[NCTokenValidator]

Gets optional list of token validators. Can return an empty list but never null.

Gets optional list of token validators. Can return an empty list but never null.

Source:
NCPipeline.scala
def getVariantFilters: List[NCVariantFilter]

Gets optional list of variant filters. Can return an empty list but never null.

Gets optional list of variant filters. Can return an empty list but never null.

Source:
NCPipeline.scala