For each of the text trunk models a number of different embedding strategies are available, by default the Chunk Average + Classification Token strategy is used, but there may be times where it may be helpful to use an alternative strategy based on your use case and available data to optimize the embedding results. You can create multiple Entities each with a different strategy to evaluate which is best.
Details of each available strategy and its use can be found in this section.
Changing an embedding strategy
Embedding strategies are an advanced option which can be found under the pencil icon in the embedding selection screen.
- Click on the drop down list to present the current options
- Select the required strategy
This is a special token introduced in order to capture the semantics of the entire input