Query with an embedding and field about pyvespa

[TTitcombe]

I got it working by wrapping only the nearest neighbour search in brackets, i.e.

response = app.query(body={
    "yql": 'select * from sources * where value=100 and ([{"targetNumHits":100}]nearestNeighbor(embedding_image,embedding_text));',
    "hits": 100,
    "ranking.features.query(embedding_text)": [0.632, -0.987, ..., 0.534],
    "ranking.profile": "embedding_similarity"
})

I'll work on a minimal notebook example and share it

[thigm85]

Hi @TTitcombe, this should work. Do you have code and sample data so that I can try to reproduce and understand the error?

[jobergum]

Note that you don't need [] or to quote targetHit , many examples in https://docs.vespa.ai/en/nearest-neighbor-search-guide.html

select title, artist from track where {targetHits:10}nearestNeighbor(embedding,q)

[thigm85]

Great that you got it to work @TTitcombe.