Text embedding processor -

OpenSearch
, ,
1

Hello,

I was wondering if it was possible to use the Text embedding processor to process a list of text (i.e. [“text1”, “text2”, “text3”, …]) where the output would be a list of its individual embedding.

NOTE: The list of text will be of variable length for each document.

If not, can someone suggest alternatives?

Managed clusters Opensearch version: 2.13

2

What you purpose is to make multiple lists of embedded vectors like:
[[0.1, -0.2, …], …] right?

3

In the end, I would like the embedding for the individual text in the list. This could be in the form you spoke of, a list of embedded vectors (i.e. [ [embedded vectors1], [embedded vectors2], [embedded vectors3], etc…])