Vectors
Vectors are used to enable semantic search within Aiimi Insight Engine. Items within your system are vectorised during a Python Rest Enrichment Step and grouped together based on the vectors created in mappings.
A Vector must be created before the Python Rest enrichment step.
Create a New Vector
Vectors cannot be deleted from the Control Hub. If a vector needs removing speak to your Elastic administrator.
Within the Control Hub go to Mappings > Vectors.
Select Create New Vector.
Enter a unique ID for this vector.
This must be in camel case and only contain alphanumeric characters and underscores.
The Vector ID must match the enrichment steps Model ID.
Enter a user friendly name within Vector Name.
Give the vector a description to explain what it is for within Description.
At the moment we are only able to support Dense Vector types.
Select the structure of your vectors from Element Type.
Choose between Float or Byte.
Enter the number of Dimensions to compare for similarity.
Indexed vector dimensions must be less than 1024.
Non-Indexed vector dimensions must be less than 2048.
Select a metric to use to compare your vectors from Similarity Metric.
Enter the number of vectors to create within Count.
Check 'Index?' to allow this field to be searched using the kNN search API.
Select Create Vector to finalise.
