# Unknown key for a START\_OBJECT in \[knn\] **URL:** \ **Category:** Elasticsearch\ **Tags:** vector-search\ **Created:** [November 21, 2022, 1:31am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381 "2022-11-21T01:31:01Z")\ **Posts on this page:** 15\ **Page:** 1
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 21, 2022, 1:31am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/1 "2022-11-21T01:31:01Z")
Has anybody actually used the knn sample in the documentation here:[k-nearest neighbor (kNN) search | Elasticsearch Guide [master] | Elastic](https://www.elastic.co/guide/en/elasticsearch/reference/master/knn-search.html) ? Here is their sample: ```auto POST image-index/_search { "query": { "match": { "title": { "query": "mountain lake", "boost": 0.9 } } }, "knn": { "field": "image-vector", "query_vector": [54, 10, -2], "k": 5, "num_candidates": 50, "boost": 0.1 }, "size": 10 } ``` Here is my code based on that: ```auto hybrid_lex_sem = self.es.search(index=indexn, body= { "query": { "match": { "question": { "query": cleanq, "boost": 0.9 }, }, }, "knn": { "field": "question_vector", "query_vector": question_embedding, "k": 5, "num_candidates": 50, "boost": 0.1 }, "size": 10 } ) ``` Here is the parsing exception I get from the above (Python) 'parsing\_exception', 'reason': 'Unknown key for a START\_OBJECT in [knn].' The fields in my query all work fine with a regular dense vector search(non knn). Can somebody direct me where the syntax error is in my version of the documentation's own sample? Thank you very much. ---
**Author:** ![RabBit\_BR](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/rabbit_br/32/82261_2.png) [@RabBit\_BR](https://discuss.elastic.co/u/RabBit_BR)\ **Post date:** [November 21, 2022, 1:38am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/2 "2022-11-21T01:38:51Z")
Hi @Scott_M What is your version ES? ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 21, 2022, 1:39am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/3 "2022-11-21T01:39:15Z")
It is 8.5, I believe latest? ---
**Author:** ![RabBit\_BR](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/rabbit_br/32/82261_2.png) [@RabBit\_BR](https://discuss.elastic.co/u/RabBit_BR)\ **Post date:** [November 21, 2022, 1:47am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/4 "2022-11-21T01:47:58Z")
I tested with successful in version 8.4. I imagined you using version minor. ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 21, 2022, 1:54am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/5 "2022-11-21T01:54:42Z")
Thank you very much. I tried 8.4 version now and got same error. Much appreciated though, that was a good idea! Must be something wrong in my syntax, because it cannot even _parse_ my query: 'parsing\_exception', 'reason': 'Unknown key for a START\_OBJECT in [knn].' ---
**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:** [November 21, 2022, 4:33pm UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/6 "2022-11-21T16:33:07Z")
What is your python client version? The search body looks OK at first glance. Maybe the python client is doing something unexpected, I know in later versions of the client, you specify each part of the search body instead of the whole thing. Maybe something like: ```python hybrid_lex_sem = self.es.search(index=indexn, query= { "match": { "question": { "query": cleanq, "boost": 0.9 }, }, } knn= { "field": "question_vector", "query_vector": question_embedding, "k": 5, "num_candidates": 50, "boost": 0.1 }, size= 10 ) ``` ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 21, 2022, 5:25pm UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/7 "2022-11-21T17:25:02Z")
Thank you for great idea to try. Really appreciate. For some reason even with your excellent suggestion, I still get the same: 'parsing\_exception', 'reason': 'Unknown key for a START\_OBJECT in [knn].', 'line': 1, 'col': 8} I wonder what "unknown key" really means... those dict key names like "field" and "query\_vector" are taken from their own example, in the documentation. ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 21, 2022, 11:53pm UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/8 "2022-11-21T23:53:31Z")
RabBit\_BR, you seem to be the only person in the known universe who's ever actually run this. Even the ES support people don't have an answer. Could I trouble you to show me exactly how you called with that query? Did you use request/curl or straight python or how exactly did you get that to parse?? Thank you so much in advance! ---
**Author:** ![Jiaxiang\_Wang](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jiaxiang_wang/32/114051_2.png) [@Jiaxiang\_Wang](https://discuss.elastic.co/u/Jiaxiang_Wang)\ **Post date:** [November 25, 2022, 4:07am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/9 "2022-11-25T04:07:37Z")
Same Problem meet in dotnet: Client: Elastic.Clients.Elasticsearch 8.0.1 Elasticsearch DB version: 8 ### How I made request in C# Code: ```auto var response = await _client.SearchAsync( s => s .Knn(k => k .QueryVector(embedding_vector) // ICollection .Field(_EmbeddingVectorStr) // string .k(searchTotal) // long .NumCandidates(numCandidate) // long ) .SourceExcludes(_EmbeddingVectorStr) // string .Index(FullImageSearchIndexName) //string ); ``` ### Request Body ```auto { "knn":{ "field":"embedding_vector", "k":10, "num_candidates":20, "query_vector":[ ] } } ``` ### Error Response ```auto {"error":{"root_cause":[{"type":"parsing_exception","reason":"Unknown key for a START_OBJECT in [knn].","line":1,"col":8}],"type":"parsing_exception","reason":"Unknown key for a START_OBJECT in [knn].","line":1,"col":8},"status":400} ``` This issue has confused me for 2 days. Any hints will be appreciated. ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 25, 2022, 5:41am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/10 "2022-11-25T05:41:42Z")
> [@Jiaxiang\_Wang](#): > > Client: Elastic.Clients.Elasticsearch 8.0.1 FIrst thing, I believe you better upgrade your deployment (on dashboard) to 8.5.2 of the core Elasticsearch service ( and separately, make sure your client is the matching latest version, e.g. for me with Python that is 8.5) ---
**Author:** ![Jiaxiang\_Wang](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jiaxiang_wang/32/114051_2.png) [@Jiaxiang\_Wang](https://discuss.elastic.co/u/Jiaxiang_Wang)\ **Post date:** [November 25, 2022, 6:09am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/11 "2022-11-25T06:09:36Z")
Thank you for your reply. I double check that my ES is 8.3.2 and my es dotnet client(Elastic.Clients.Elasticsearch) is the last stable version 8.0.1 The Postman request successfully receive response with provided `Request Body`. Still trying to figure out why it doesn't work. ---
**Author:** ![Scott\_M](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/scott_m/32/99073_2.png) [@Scott\_M](https://discuss.elastic.co/u/Scott_M)\ **Post date:** [November 25, 2022, 6:32am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/12 "2022-11-25T06:32:15Z")
oh ok Just curious why is your query\_vector empty? "query\_vector":[ ] ---
**Author:** ![Jiaxiang\_Wang](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jiaxiang_wang/32/114051_2.png) [@Jiaxiang\_Wang](https://discuss.elastic.co/u/Jiaxiang_Wang)\ **Post date:** [November 25, 2022, 6:46am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/13 "2022-11-25T06:46:28Z")
I remove the float number inside for visibility. (Previously is has a list of 256 float number) ---
**Author:** ![Jiaxiang\_Wang](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jiaxiang_wang/32/114051_2.png) [@Jiaxiang\_Wang](https://discuss.elastic.co/u/Jiaxiang_Wang)\ **Post date:** [November 25, 2022, 7:22am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/14 "2022-11-25T07:22:12Z")
@Scott_M I think the issue in your case is that you are using `search`. What I suggest is to use `knn_search` instead of it. #### Below Python code works for me: ```auto target_float_list = [...]// a list of 256 floating number res = client.knn_search( index=client._active_index, knn={"field": "embedding_vector", "query_vector": target_float_list, "k": 10, "num_candidates": 100}) ``` #### My Request Body ```auto { "knn":{ "field":"embedding_vector", "query_vector":[], "k":10, "num_candidates":100 }, "_source":{ "excludes":[ "embedding_vector" ] } } ``` ---
**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\ **Post date:** [December 23, 2022, 7:23am UTC](https://discuss.elastic.co/t/unknown-key-for-a-start-object-in-knn/319381/15 "2022-12-23T07:23:02Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.