While trying to do nearestNeighbor search on embeddings I am getting a query error, though no error logs are present in Vespa container.
Documentation link: https://docs.vespa.ai/en/nearest-neighbor-search.html#querying-using-nearestneighbor-query-operator
Request:
{
"yql": "SELECT * FROM products WHERE ([{\"targetHits\":10, \"approximate\": true}]nearestNeighbor(text_embedding, q_embedding))",
"ranking": {
"profile": "default",
"listFeatures": true,
"features": {
"query(q_embedding)": [
0.06836861371994019,
0,
0.005350692197680473,
0.030558381229639053,
0,
0.010386962443590164,
0.03204352408647537,
0.03281643986701965,
0.11372111737728119,
0.10037083923816681,
0,
0.10755997896194458,
0.043405745178461075,
0.08697208017110825,
0,
0.01487557403743267,
0.017064541578292847,
0.050060052424669266,
0.06158211827278137,
0,
0,
0,
0.1395300030708313,
0.040378399193286896,
0,
0.0265999473631382,
0,
0.02867511473596096,
0,
0,
0,
0.10068237036466599,
0.041657011955976486,
0.06862851977348328,
0,
0.014019965194165707,
0,
0,
0,
0,
0.1124025359749794,
0.06834051012992859,
0,
0,
0,
0,
0,
0,
0.01853846199810505,
0.08900538831949234,
0.09758827835321426,
0,
0.08243539184331894,
0,
0,
0,
0,
0,
0,
0,
0,
0.022744037210941315,
0.08361546695232391,
0,
0.03171956539154053,
0.04051847383379936,
0,
0.019974248483777046,
0,
0,
0,
0,
0,
0,
0.08591245859861374,
0.08787022531032562,
0.02056828886270523,
0.05086769163608551,
0,
0.09067854285240173,
0.024191005155444145,
0,
0,
0,
0.07980427145957947,
0.03894811123609543,
0,
0.0007913131266832352,
0,
0.050328031182289124,
0.015318576246500015,
0.0427778922021389,
0.023335546255111694,
0.09074989706277847,
0.014131247065961361,
0,
0,
0,
0,
0.06538441777229309,
0.06360842287540436,
0,
0,
0,
0.03568531945347786,
0.060780078172683716,
0.05406676605343819,
0.014647044241428375,
0.0017168920021504164,
0,
0,
0,
0.020146727561950684,
0.01121614407747984,
0.018305499106645584,
0.026444928720593452,
0.050688087940216064,
0,
0,
0.0071852304972708225,
0,
0,
0.040417373180389404,
0.017755649983882904,
0.017129860818386078,
0.043410494923591614,
0.02412831038236618,
0
]
}
}
}
response:
{
"root": {
"id": "toplevel",
"relevance": 1.0,
"fields": {
"totalCount": 0
},
"errors": [
{
"code": 4,
"summary": "Invalid query parameter",
"source": "products",
"message": "Expected 'query(q_embedding)' to be a tensor, but it is the string '[\n 0.06836861371994019,\n 0,\n 0.005350692197680473,\n 0.030558381229639053,\n 0,\n 0.010386962443590164,\n 0.03204352408647537,\n 0.03281643986701965,\n 0.11372111737728119,\n 0.10037083923816681,\n 0,\n 0.10755997896194458,\n 0.043405745178461075,\n 0.08697208017110825,\n 0,\n 0.01487557403743267,\n 0.017064541578292847,\n 0.050060052424669266,\n 0.06158211827278137,\n 0,\n 0,\n 0,\n 0.1395300030708313,\n 0.040378399193286896,\n 0,\n 0.0265999473631382,\n 0,\n 0.02867511473596096,\n 0,\n 0,\n 0,\n 0.10068237036466599,\n 0.041657011955976486,\n 0.06862851977348328,\n 0,\n 0.014019965194165707,\n 0,\n 0,\n 0,\n 0,\n 0.1124025359749794,\n 0.06834051012992859,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0.01853846199810505,\n 0.08900538831949234,\n 0.09758827835321426,\n 0,\n 0.08243539184331894,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0.022744037210941315,\n 0.08361546695232391,\n 0,\n 0.03171956539154053,\n 0.04051847383379936,\n 0,\n 0.019974248483777046,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0,\n 0.08591245859861374,\n 0.08787022531032562,\n 0.02056828886270523,\n 0.05086769163608551,\n 0,\n 0.09067854285240173,\n 0.024191005155444145,\n 0,\n 0,\n 0,\n 0.07980427145957947,\n 0.03894811123609543,\n 0,\n 0.0007913131266832352,\n 0,\n 0.050328031182289124,\n 0.015318576246500015,\n 0.0427778922021389,\n 0.023335546255111694,\n 0.09074989706277847,\n 0.014131247065961361,\n 0,\n 0,\n 0,\n 0,\n 0.06538441777229309,\n 0.06360842287540436,\n 0,\n 0,\n 0,\n 0.03568531945347786,\n 0.060780078172683716,\n 0.05406676605343819,\n 0.014647044241428375,\n 0.0017168920021504164,\n 0,\n 0,\n 0,\n 0.020146727561950684,\n 0.01121614407747984,\n 0.018305499106645584,\n 0.026444928720593452,\n 0.050688087940216064,\n 0,\n 0,\n 0.0071852304972708225,\n 0,\n 0,\n 0.040417373180389404,\n 0.017755649983882904,\n 0.017129860818386078,\n 0.043410494923591614,\n 0.02412831038236618,\n 0\n ]'"
}
]
}
}
I am expecting to get a list of documents.
schema products {
document products {
field id type int {
}
field gender type string {
indexing: summary | attribute
}
field masterCategory type string {
indexing: summary | attribute
}
field subCategory type string {
indexing: summary | attribute
}
field articleType type string {
indexing: summary | attribute
}
field baseColour type string {
indexing: summary | attribute
}
field season type string {
indexing: summary | attribute
}
field year type int {
indexing: summary | attribute
}
field usage type string {
indexing: summary | attribute
}
field productDisplayName type string {
indexing: summary | attribute
}
field image type string {
indexing: summary | attribute
}
field image_embedding type tensor<float>(x[128]) {
indexing: attribute
attribute {
distance-metric: euclidean
}
}
field text_embedding type tensor<float>(x[128]) {
indexing: attribute
attribute {
distance-metric: euclidean
}
}
}
fieldset default {
fields: id, gender, masterCategory, subCategory, articleType, baseColour, season, year, usage, productDisplayName, image, image_embedding, text_embedding
}
rank-profile default {
first-phase {
expression: closeness(field, image_embedding) + closeness(field, text_embedding)
}
}
}
You need to declare the type of your input query feature. Add this to your rank profile in your products schema:
inputs {
query(q_embedding) tensor(x[128])
}