Platforms to show: All Mac Windows Linux Cross-Platform
NLContextualEmbeddingResultMBS class New in 26.2
| Type | Topic | Plugin | Version | macOS | Windows | Linux | iOS | Targets |
| class | Natural Language | MBS MacFrameworks Plugin | 26.2 | ✅ Yes | ❌ No | ❌ No | ✅ Yes | All |
This object returns embeddings at the subword level, meaning a single word may generate multiple vectors, especially for rare or complex terms. If you need to work with whole-word embeddings or create single representations for entire text inputs, pool or combine subword vectors.
This is an abstract class. You can't create an instance, but you can get one from various plugin functions.
- 4 properties
- property Handle as Integer
- property Language as String
- property SequenceLength as UInt64
- property Text as String
- 4 methods
- method averageToken as NLContextualEmbeddingResultVectorMBS
- method Constructor Private
- method tokenVectorAtIndex(characterIndex as Integer) as NLContextualEmbeddingResultVectorMBS
- method tokenVectors as NLContextualEmbeddingResultVectorMBS()
This class has no sub classes.
Blog Entries
Release notes
- Version 26.2
- Added NLContextualEmbeddingMBS, NLContextualEmbeddingResultMBS and NLContextualEmbeddingResultVectorMBS classes.
Some methods using this class:
- NLContextualEmbeddingMBS.embeddingResultForString(Text as String, Language as String = "", byref Error as NSErrorMBS) as NLContextualEmbeddingResultMBS
Some related classes:
The items on this page are in the following plugins: MBS MacFrameworks Plugin.
NLContextualEmbeddingMBS - NLContextualEmbeddingResultVectorMBS
