# Pinned query not good with KNN search **URL:** \ **Category:** Elasticsearch\ **Tags:** elastic-stack-machine-learning, vector-search\ **Created:** [April 25, 2024, 12:29pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210 "2024-04-25T12:29:37Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Chenko](https://avatars.discourse-cdn.com/v4/letter/c/258eb7/32.png) [@Chenko](https://discuss.elastic.co/u/Chenko)\ **Post date:** [April 25, 2024, 12:29pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/1 "2024-04-25T12:29:37Z")
Hi, When using a normal knn query this works: ```auto "knn": [ { "inner_hits": { "_source": false, "fields": [ "passages.text" ] }, "field": "passages.vector.predicted_value", "k": 5, "num_candidates": 100, "query_vector_builder": { "text_embedding": { "model_id": "elastic__multilingual-e5-small-optimized", "model_text": "test text" } } }, { "field": "title.predicted_value", "k": 5, "num_candidates": 100, "query_vector_builder": { "text_embedding": { "model_id": "elastic__multilingual-e5-small-optimized", "model_text": "test text" } } }] ``` Not only does an array not work, when just using 1 of the above knn queries: ```auto { "size": 3, "query": { "pinned": { "ids": ["1", "2"], "organic": { "knn": { "inner_hits": { "_source": false, "fields": [ "passages.text" ] }, "field": "passages.vector.predicted_value", "k": 5, "num_candidates": 100, "query_vector_builder": { "text_embedding": { "model_id": "elastic__multilingual-e5-small-optimized", "model_text": "test query" } } } } } } } ``` Returns the following error: ```auto "caused_by": { "type": "x_content_parse_exception", "reason": "[7:15] [pinned] failed to parse field [organic]", "caused_by": { "type": "illegal_argument_exception", "reason": "[knn] queries cannot be provided directly, use the [knn] body parameter instead" } } ``` So currently I have the following issues; 1. I am not able to do multiple knn queries ( Do knn queries on multiple fields.) 2. I am not able to use knn queries with text, it seems I need to embed the text first. Ps. I could not test with embeddings yet as I have [problem with my inference pipeline](https://discuss.elastic.co/t/inference-api-not-working/358209). Kind regards, Chenko ---
**Author:** ![BenTrent](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/bentrent/32/33915_2.png) [@BenTrent](https://discuss.elastic.co/u/BenTrent)\ **Post date:** [April 25, 2024, 1:03pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/2 "2024-04-25T13:03:08Z")
@Chenko Before 8.12, `knn` couldn't be provided as a query object directly. We only supported a top-level knn object. Here are the docs for 8.12 on using knn in a query: [Knn query | Elasticsearch Guide [8.12] | Elastic](https://www.elastic.co/guide/en/elasticsearch/reference/8.12/query-dsl-knn-query.html) In your case, for pinned query to work with knn, you must be at least on 8.12, and then utilize `nested` for your passage vectors. ---
**Author:** ![Chenko](https://avatars.discourse-cdn.com/v4/letter/c/258eb7/32.png) [@Chenko](https://discuss.elastic.co/u/Chenko)\ **Post date:** [April 25, 2024, 1:23pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/3 "2024-04-25T13:23:59Z")
Hi Ben, Thanks for the swift response! I See, this is indeed the case for me. I am currently using 8.11. As for when I go to 8.12 I would be able to use text instead of first using the inference pipeline? When you say I must utilize `nested` for my passage vectors, do you mean I need to do a nested query instead of a normal one with knn? Could you give an example? ---
**Author:** ![BenTrent](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/bentrent/32/33915_2.png) [@BenTrent](https://discuss.elastic.co/u/BenTrent)\ **Post date:** [April 25, 2024, 1:42pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/4 "2024-04-25T13:42:15Z")
It seems like you are using nested vectors (chunked) right? So, for pinned query and this, it would be something like: ```auto { "size": 5, "query": { "pinned": { "ids": [ "1", "2" ], "organic": { "nested": { "path": "passages", "inner_hits": { "_source": false, "fields": [ "passages.text" ] }, "query": { "knn": { "field": "passages.vector.predicted_value", "query_vector": [...], "num_candidates": 100 } } } } } } } ``` Frustratingly, we didn't add the query vector builder stuff to knn query until later, sorry :(. That isn't until 8.14. ---
**Author:** ![Chenko](https://avatars.discourse-cdn.com/v4/letter/c/258eb7/32.png) [@Chenko](https://discuss.elastic.co/u/Chenko)\ **Post date:** [April 25, 2024, 1:51pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/5 "2024-04-25T13:51:51Z")
Thanks for the example! > [@BenTrent](#): > > It seems like you are using nested vectors (chunked) right? You are correct, I am indeed using nested vectors in the passages field. I am however also using normal vectors for the title. I am now eagerly awaiting 8.14. any idea when it is set to release? ---
**Author:** ![Shell\_Dias](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/shell_dias/32/136785_2.png) [@Shell\_Dias](https://discuss.elastic.co/u/Shell_Dias)\ **Post date:** [July 24, 2024, 5:18am UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/6 "2024-07-24T05:18:23Z")
And the DSL for KNN does not allow passing a text string, only vectors. If you choose to use a trained model that's in the Elasticsearch tool, how can you obtain that vector on a local client? Considering that Model A does not generate the same vector as Model B. ---
**Author:** ![Kathleen\_DeRusso](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/kathleen_derusso/32/132039_2.png) [@Kathleen\_DeRusso](https://discuss.elastic.co/u/Kathleen_DeRusso)\ **Post date:** [July 24, 2024, 12:09pm UTC](https://discuss.elastic.co/t/pinned-query-not-good-with-knn-search/358210/7 "2024-07-24T12:09:24Z")
Hi there @Shell_Dias, I encourage you to start new threads for new topics, so that it doesn't add too much clutter to already resolved topics. With that said, I also encourage you to check out the [query\_vector\_builder](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html#knn-semantic-search) if you're interested in performing kNN search using a text string. You can also upload models using [eland](https://eland.readthedocs.io/en/v8.14.0/) if you're not using a built in Elasticsearch model.