How Superlinked represents your complex data better using multiple embedding spaces.
Embed all entity data as single text
Run vector similarity search
Rerank results with additional filters
@schema
, you embed your data using Spaces that are appropriate to your data types. For example, category information uses the CategoricalSimilaritySpace
, and text uses the TextSimilaritySpace
.
Using our simple two-paragraph dataset above, we proceed as follows:
@sl.schema
, you embed these using Spaces that fit your data types:
body_space
, and surface our results in the appropriate order:
Rank | Body | Like Count | ID |
---|---|---|---|
0 | Growing computation power enables advancements in AI. | 75 | paragraph-2 |
1 | Glorious animals live in the wilderness. | 10 | paragraph-1 |