select
*
from mldb.ONNXEmbeddings(
on (SELECT CAST(rev_id AS VARCHAR(21)) AS rev_id, rev_text AS txt FROM amazon_reviews_25)
on (select model_id, model from onnx_models where model_id = 'bge-small-en-v1.5') DIMENSION
on (select tokenizer from embeddings_tokenizers where model_id = 'bge-small-en-v1.5') DIMENSION
USING
Accumulate('rev_id')
ModelOutputTensor('sentence_embedding')
OutputFormat('BLOB(1536)')
) a
;
*** Query completed. 25 rows found. 2 columns returned.
*** Total elapsed time was 1 second.
The following example is a snippet of the total output:
rev_id sentence_embedding ----------------------------------------------------------------------------------------------- A3V1MKC2BVWY48 DD6D293CE936223D4377A63C60558C3CAB4C453A6D7B43BBF132AC3DDE138FBD4D04983A475589BDF55D2CBDA701923B6712533DE9171C3DB9C5D7BBA694283CF3B2043DCBF6D83C274959BD3 A26GKZPS079GFF B9AC08BDBF59593C1D48233D353D003DC97626BCA4950D3B0490123DAA4A41BB17131F3D7664D4BC2D26A93C6D522ABC2D2EBB3AB5E379BC2AACAB3C8959153D79664ABC0C68913CF67C01BE7 AUTNO7VDY4H4A 8A0D42BC8926B63C311AB2BBD7C3C23C5FB338BCF02CE2BA30598E3C2B1BAB3C5A1436BC617B9ABDBC81283CD31A573DEE212ABB01922D3D360082BC69FE4EBC6FAD143D816AC93CDD5393BD3 A2S166WSCFIFP5 04273B3BC1DD6BBCC6E588BC52EE0DBC1D1E2CBC472C563DA9A6153D470DB8BA907B483D57451BBDCBB001BC970E66BC9BCD033BB40D263D2116283DD32069392182FEBB74B0C23C6F18E6BD2 ...