I am trying to sort data by top_hits parameter in search query Elasticsearch but somehow it didn't affect anything. can anyone please help me with this one?
so I've tried using sort as some people said like this :
{
"size" : 0,
"from" : 0,
"aggs": {
"by_filter": {
"filter": {
"bool": {
"must": [
{
"range": {
"published_at": {
"gte": "2019-08-01 00:00:00",
"lte": "2023-10-30 23:59:59"
}
}
},
{
"match": {
"status": "published"
}
}
]
}
},
"aggs": {
"by_created": {
"terms": {
"field": "created_by.id",
"size": 10
},
"aggs" : {
"count_data": {
"terms": {
"field": "created_by.id"
}
},
"hits": {
"top_hits": {
"sort": [ <---- the sort query that I found
{
"created_by.id": {
"order": "desc"
}
}
],
"_source":["created_by.id"],
"size": 1
}
}
}
}
}
}
}
}
but the result didn't change :
"aggregations": {
"by_filter": {
"doc_count": 21,
"by_created": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 3,
"buckets": [
{
"key": 34,
"doc_count": 3,
"hits": {
"hits": {
"total": {
"value": 3,
"relation": "eq"
},
"max_score": null,
"hits": [
{
"_index": "re_article",
"_id": "53822",
"_score": null,
"_source": {
"created_by": {
"id": 34
}
},
"sort": [ <--- I think this is the result of the sort
34
]
}
]
}
},
"count_data": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": 34,
"doc_count": 3
}
]
}
},
{
"key": 52,
"doc_count": 3,
"hits": {
"hits": {
"total": {
"value": 3,
"relation": "eq"
},
"max_score": null,
"hits": [
{
"_index": "re_article",
"_id": "338610",
"_score": null,
"_source": {
"created_by": {
"id": 52
}
},
"sort": [
52
]
}
]
}
},
"count_data": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": 52,
"doc_count": 3
}
]
}
}
]
}
}
}
what I expected is the buckets shows key 52 first then 34, like this :
"aggregations": {
"by_filter": {
"doc_count": 21,
"by_created": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 3,
"buckets": [
{
"key": 52,
"doc_count": 3,
"hits": {
"hits": {
"total": {
"value": 3,
"relation": "eq"
},
"max_score": null,
"hits": [
{
"_index": "re_article",
"_id": "338610",
"_score": null,
"_source": {
"created_by": {
"id": 52
}
}
}
]
}
},
"count_data": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": 52,
"doc_count": 3
}
]
}
},
{
"key": 34,
"doc_count": 3,
"hits": {
"hits": {
"total": {
"value": 3,
"relation": "eq"
},
"max_score": null,
"hits": [
{
"_index": "re_article",
"_id": "53822",
"_score": null,
"_source": {
"created_by": {
"id": 34
}
}
}
]
}
},
"count_data": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": 34,
"doc_count": 3
}
]
}
}
]
}
}
}
I think I pick a wrong example since there's new "sort" field in top_hits result but not really what I'm looking for
You are close, you just need to move "order" to the aggregation that you actually want to be sorted and change the syntax a bit. "order" in top_hits will sort hits if you want to sort keys in the by_created aggregation you need to add "order" to that aggregation:
{
"size" : 0,
"from" : 0,
"aggs": {
"by_filter": {
"filter": {
"bool": {
"must": [
{
"range": {
"published_at": {
"gte": "2019-08-01 00:00:00",
"lte": "2023-10-30 23:59:59"
}
}
},
{
"match": {
"status": "published"
}
}
]
}
},
"aggs": {
"by_created": {
"terms": {
"field": "created_by.id",
"size": 10,
"order": { <--- try applying it here
"_key": "desc"
}
},
"aggs" : {
"count_data": {
"terms": {
"field": "created_by.id"
}
},
"hits": {
"top_hits": {
"sort": [ <---- the sort query that I found
{
"created_by.id": {
"order": "desc"
}
}
],
"_source":["created_by.id"],
"size": 1
}
}
}
}
}
}
}
}
You can find more option in the terms aggregation docs. If you need to sort other aggregations, you might find bucket_sort aggregation useful.