Embeddings Configuration Parameters
The [Embeddings]
section allows you to configure embedding models in QMS to use to generate embeddings.
Embeddings are an alternative way to encode unstructured information. Embeddings, also known as vectors, are numerical values that represent the concepts in a particular piece of text. In general, the vectors generated for pieces of text with a similar meaning are close in the vector space. Therefore embeddings allow you to perform vector-based comparisons to find similar content.
You can include the embeddings in your documents to index into the IDOL Content component, and use them to query Content for similar vectors.
QMS uses the configured embedding models to generate embeddings when you use the ModelEncode
action.