# Inconsistent hybrid search hits total results lead to incorrect aggregations **URL:** \ **Category:** Elasticsearch\ **Tags:** vector-search\ **Created:** [November 8, 2024, 4:59am UTC](https://discuss.elastic.co/t/inconsistent-hybrid-search-hits-total-results-lead-to-incorrect-aggregations/370196 "2024-11-08T04:59:32Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![andrewquang512](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/andrewquang512/32/139031_2.png) [@andrewquang512](https://discuss.elastic.co/u/andrewquang512)\ **Post date:** [November 8, 2024, 4:59am UTC](https://discuss.elastic.co/t/inconsistent-hybrid-search-hits-total-results-lead-to-incorrect-aggregations/370196/1 "2024-11-08T04:59:32Z")
Hi All, My team is working on system using hybrid search combining knn search and full-text queries. There is a usecase that we need to count a tag field data which we are using [Term Aggregation](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-terms-aggregation.html) and display these counts on UI and support filtering result by tag. And then we found that in this guide [Aggregation with kNN](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html#_combine_approximate_knn_with_other_features) which state that for approximate kNN search, aggregations are calculated on the top `k` nearest documents - this may messed up the aggregation counting results as the kNN search will make sure that `k` matching documents with tag-filter are returned - which make the aggregation of first search request without filtering incorrect We do some research and try to apply [kNN query](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-knn-query.html#knn-query-aggregations) and although it may sounds matching our needs, but the hits total results are inconsistent between search requests with the same request body - which lead to aggregation results are incorrect too. ![search count results](https://us1.discourse-cdn.com/elastic/original/3X/3/2/32ec91bc58e0995f5c6b6a119d5d154f9dcc98e3.png) We don't understand this behavior, we find that when we keep only one vector knn search or small size , this will not happen again. Can your guys help me explain what is happening in background here and any solutions/workarounds to implement term aggregation and filter by it with hybrid search. Any suggestions or opinions are appreciated. Thank you. Below are my queries; This is hybrid search with kNN ```auto GET product_books/_search { "size": 200, "query": { "bool": { "must": [ { "bool": { "should": [ { "match_phrase": { "product_title": { "query": "Hello World", "boost": 3.27 } } }, { "match_phrase": { "product_title_kana": { "query": "Hello World", "boost": 2.84 } } }, { "match_phrase": { "author_1": { "query": "Hello World", "boost": 2.44 } } }, { "match_phrase": { "author_1_kana": { "query": "Hello World", "boost": 2.3 } } }, { "match_phrase": { "author_2": { "query": "Hello World", "boost": 2.44 } } }, { "match_phrase": { "author_2_kana": { "query": "Hello World", "boost": 2.3 } } }, { "match_phrase": { "search_text.search_text": { "query": "Hello World", "boost": 1.04 } } }, { "match_phrase": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.24 } } }, { "match_phrase": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.17 } } }, { "match_phrase_prefix": { "product_title": { "query": "Hello World", "boost": 1.64 } } }, { "match_phrase_prefix": { "product_title_kana": { "query": "Hello World", "boost": 1.44 } } }, { "match_phrase_prefix": { "author_1": { "query": "Hello World", "boost": 1.2 } } }, { "match_phrase_prefix": { "author_1_kana": { "query": "Hello World", "boost": 1.14 } } }, { "match_phrase_prefix": { "author_2": { "query": "Hello World", "boost": 1.2 } } }, { "match_phrase_prefix": { "author_2_kana": { "query": "Hello World", "boost": 1.14 } } }, { "match_phrase_prefix": { "search_text.search_text": { "query": "Hello World", "boost": 0.5 } } }, { "match_phrase_prefix": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.14 } } }, { "match_phrase_prefix": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.1 } } }, { "match": { "product_title": { "query": "Hello World", "boost": 0.67 } } }, { "match": { "product_title_kana": { "query": "Hello World", "boost": 0.57 } } }, { "match": { "author_1": { "query": "Hello World", "boost": 0.5 } } }, { "match": { "author_1_kana": { "query": "Hello World", "boost": 0.47 } } }, { "match": { "author_2": { "query": "Hello World", "boost": 0.5 } } }, { "match": { "author_2_kana": { "query": "Hello World", "boost": 0.47 } } }, { "match": { "search_text.search_text": { "query": "Hello World", "boost": 0.2 } } }, { "match": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.04 } } }, { "match": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.03 } } }, { "term": { "jan": { "value": "Hello World", "boost": 3.27 } } }, { "term": { "isbn_10": { "value": "Hello World", "boost": 3.27 } } } ], "minimum_should_match": 6 } } ], "filter": [ { "term": { "tags": "コミック" } } ] } }, "knn": [ { "field": "semantic_description_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "Hello World" } }, "k": 15, "num_candidates": 50, "boost": 28, "filter": [ { "term": { "tags": "コミック" } } ] }, { "field": "semantic_description_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "Hello World" } }, "k": 15, "num_candidates": 50, "boost": 28, "filter": [ { "term": { "tags": "コミック" } } ] }, { "field": "semantic_metadata_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "Hello World" } }, "k": 15, "num_candidates": 50, "boost": 28, "filter": [ { "term": { "tags": "コミック" } } ] } ] } ``` This is hybrid search with query DSL kNN query : ```auto GET product_books/_search { "size": 200, "query": { "bool": { "should": [ { "bool": { "must": [ { "bool": { "should": [ { "match_phrase": { "product_title": { "query": "Hello World", "boost": 3.27 } } }, { "match_phrase": { "product_title_kana": { "query": "Hello World", "boost": 2.84 } } }, { "match_phrase": { "author_1": { "query": "Hello World", "boost": 2.44 } } }, { "match_phrase": { "author_1_kana": { "query": "Hello World", "boost": 2.3 } } }, { "match_phrase": { "author_2": { "query": "Hello World", "boost": 2.44 } } }, { "match_phrase": { "author_2_kana": { "query": "Hello World", "boost": 2.3 } } }, { "match_phrase": { "search_text.search_text": { "query": "Hello World", "boost": 1.04 } } }, { "match_phrase": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.24 } } }, { "match_phrase": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.17 } } }, { "match_phrase_prefix": { "product_title": { "query": "Hello World", "boost": 1.64 } } }, { "match_phrase_prefix": { "product_title_kana": { "query": "Hello World", "boost": 1.44 } } }, { "match_phrase_prefix": { "author_1": { "query": "Hello World", "boost": 1.2 } } }, { "match_phrase_prefix": { "author_1_kana": { "query": "Hello World", "boost": 1.14 } } }, { "match_phrase_prefix": { "author_2": { "query": "Hello World", "boost": 1.2 } } }, { "match_phrase_prefix": { "author_2_kana": { "query": "Hello World", "boost": 1.14 } } }, { "match_phrase_prefix": { "search_text.search_text": { "query": "Hello World", "boost": 0.5 } } }, { "match_phrase_prefix": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.14 } } }, { "match_phrase_prefix": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.1 } } }, { "match": { "product_title": { "query": "Hello World", "boost": 0.67 } } }, { "match": { "product_title_kana": { "query": "Hello World", "boost": 0.57 } } }, { "match": { "author_1": { "query": "Hello World", "boost": 0.5 } } }, { "match": { "author_1_kana": { "query": "Hello World", "boost": 0.47 } } }, { "match": { "author_2": { "query": "Hello World", "boost": 0.5 } } }, { "match": { "author_2_kana": { "query": "Hello World", "boost": 0.47 } } }, { "match": { "search_text.search_text": { "query": "Hello World", "boost": 0.2 } } }, { "match": { "search_text.search_ngram": { "query": "Hello World", "boost": 0.04 } } }, { "match": { "search_text.search_ngram_norm": { "query": "Hello World", "boost": 0.03 } } }, { "term": { "jan": { "value": "Hello World", "boost": 3.27 } } }, { "term": { "isbn_10": { "value": "Hello World", "boost": 3.27 } } } ], "minimum_should_match": 6 } } ] } }, { "knn": { "field": "semantic_title_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "query: Hello World" } }, "_name": "knn_query" } }, { "knn": { "field": "semantic_description_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "query: Hello World" } }, "_name": "knn_query" } }, { "knn": { "field": "semantic_metadata_vector", "query_vector_builder": { "text_embedding": { "model_id": "intfloat__multilingual-e5-base_query", "model_text": "query: Hello World" } }, "_name": "knn_query" } } ] } }, "aggs": { "tags": { "terms": { "field": "tags", "size": 100 } } } } ``` This pretty much the same to this topic [Inconsistency in No of Total Hits](https://discuss.elastic.co/t/inconsistency-in-no-of-total-hits-in-results/258023) but this is hybrid search to our usecase For Elasticsearch version, we are using ElasticCloud with version 8.14.3 of Elasticsearch ---
**Author:** ![Fabrizio\_Fortino](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/fabrizio_fortino/32/1719_2.png) [@Fabrizio\_Fortino](https://discuss.elastic.co/u/Fabrizio_Fortino)\ **Post date:** [November 14, 2024, 5:50pm UTC](https://discuss.elastic.co/t/inconsistent-hybrid-search-hits-total-results-lead-to-incorrect-aggregations/370196/2 "2024-11-14T17:50:57Z")
I am experiencing the same behaviour with hybrid queries and ES 8.15 (using ElasticCloud as well). The knn query clause specifies numCandidates=100. Query executions range between 99 and 101 hits. ---
**Author:** ![andrewquang512](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/andrewquang512/32/139031_2.png) [@andrewquang512](https://discuss.elastic.co/u/andrewquang512)\ **Post date:** [November 18, 2024, 7:38am UTC](https://discuss.elastic.co/t/inconsistent-hybrid-search-hits-total-results-lead-to-incorrect-aggregations/370196/3 "2024-11-18T07:38:45Z")
Yes, this is a bit confusing behavior as far as i know knn will make ES choosing `num_candidates` from each shard during the search and choose the top `k` results. For the same keyword, the `num_candidates` should remain the same and thus the results are consistent. I have just find out that the knn top-level section results will be also inconsistent when putting high `num_candidates` and `k`. But not as much as the knn query, the result from knn top-level section fluctuates around 1-2 documents. For the aggregation, we figure out the way to manage to do this is that we are using [Post Filter](https://www.elastic.co/guide/en/elasticsearch/reference/current/filter-search-results.html) - it took us a while to figure this docs - I think this section should be included in [KNN search filter](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html#knn-search-filter-example) in case any ones are struggling with the same problem we have met.