.wrapped(*args, **kwargs)
423 except KeyError:
424 pass
--> 426 return api(*args, **kwargs)
File ~/.conda/envs/unstructured/lib/python3.11/site-packages/elasticsearch/_sync/client/ __init__.py:3836, in Elasticsearch.search(self, index, aggregations, aggs, allow_no_indices, allow_partial_search_results, analyze_wildcard, analyzer, batched_reduce_size, ccs_minimize_roundtrips, collapse, default_operator, df, docvalue_fields, error_trace, expand_wildcards, explain, ext, fields, filter_path, from_, highlight, human, ignore_throttled, ignore_unavailable, indices_boost, knn, lenient, max_concurrent_shard_requests, min_compatible_shard_node, min_score, pit, post_filter, pre_filter_shard_size, preference, pretty, profile, q, query, rank, request_cache, rescore, rest_total_hits_as_int, routing, runtime_mappings, script_fields, scroll, search_after, search_type, seq_no_primary_term, size, slice, sort, source, source_excludes, source_includes, stats, stored_fields, suggest, suggest_field, suggest_mode, suggest_size, suggest_text, terminate_after, timeout, track_scores, track_total_hits, typed_keys, version, body)
3834 if __body is not None:
3835 __headers[\"content-type\"] = \"application/json\"
-> 3836 return self.perform_request( # type: ignore[return-value]
3837 \"POST\", __path, params=__ query, headers= __headers, body=__ body
3838 )
File ~/.conda/envs/unstructured/lib/python3.11/site-packages/elasticsearch/_sync/client/_base.py:320, in BaseClient.perform_request(self, method, path, params, headers, body)
317 except (ValueError, KeyError, TypeError):
318 pass
--> 320 raise HTTP_EXCEPTIONS.get(meta.status, ApiError)(
321 message=message, meta=meta, body=resp_body
322 )
324 # 'X-Elastic-Product: Elasticsearch' should be on every 2XX response.
325 if not self._verified_elasticsearch:
326 # If the header is set we mark the server as verified.
BadRequestError: BadRequestError(400, 'action_request_validation_exception', 'Validation Failed: 1: [rank] cannot be used with [highlighter];')"
}
```
type or paste code here
```auto
```
---
### Author:  [@hadjebi](https://discuss.elastic.co/u/hadjebi)
#### Post date: [March 1, 2024, 2:25pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/6 "2024-03-01T14:25:40Z")
I removed rank and it worked; but 2 issues:
1- I need to do semantic highlighting for knn - as keyword search is not doing well in a lot of cases for my use case.
2- How hybrid search works without rank? Is there any RRF happening?
---
### Author:  [@dadoonet](https://discuss.elastic.co/u/dadoonet)
#### Post date: [March 1, 2024, 2:44pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/7 "2024-03-01T14:44:30Z")
1. I'm not sure on how you could do highlights on text with vectors. There's basically no connection between the source terms and the generated vectors.
2. It's based on the score only.
---
### Author:  [@Mark\_Harwood1](https://discuss.elastic.co/u/Mark_Harwood1)
#### Post date: [March 1, 2024, 3:11pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/8 "2024-03-01T15:11:34Z")
> [@dadoonet](#):
>
> I'm not sure on how you could do highlights on text with vectors. There's basically no connection between the source terms and the generated vectors.
I guess you could use a sampler aggregation on the top N results and use the "significant\_text" aggregation on the text field. That could draw out some of the keywords strongly related to the vector. These keywords could then be used in a follow-up query to get highlighting.
---
### Author:  [@dadoonet](https://discuss.elastic.co/u/dadoonet)
#### Post date: [March 1, 2024, 3:36pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/9 "2024-03-01T15:36:22Z")
Nice hack! ๐
---
### Author:  [@hadjebi](https://discuss.elastic.co/u/hadjebi)
#### Post date: [March 1, 2024, 3:42pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/10 "2024-03-01T15:42:14Z")
> [@Mark\_Harwood1](#):
>
> I guess you could use a sampler aggregation on the top N results and use the "significant\_text" aggregation on the text field. That could draw out some of the keywords strongly related to the vector. These keywords could then be used in a follow-up query to get highlighting.
Thanks @Mark_Harwood1. Intresting idea but didn't work well. As an example, I tried this query:
```auto
query = "Find example case studies for clients like Chevron."
res, keywords = search_es_with_significant_text(query, k=5)
```
While the results set include clients like Chevron and Exxon, the significant\_keywords are like:
```auto
['transitioned', 'dark', 'advertising', 'imagery', 'backend', 'sophisticated', 'showcases']
```
Which are not really what I like to see.
Am I missing something?
---
### Author:  [@Mark\_Harwood1](https://discuss.elastic.co/u/Mark_Harwood1)
#### Post date: [March 1, 2024, 7:34pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/11 "2024-03-01T19:34:31Z")
> Am I missing something?
Some ideas:
Try the [filter\_duplicate\_text](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-significanttext-aggregation.html#filter-duplicate-text-noisy-data) setting which should help avoid being misled by duplicated noise in results.
If you have many shards and the relevant content is spread thinly across many of them it makes it much hard to detect any signal from the data.
If your query is a vector with a filter (e.g. category:caseStudies) then the significance algo may be tuning into the language of case studies in general compared to other categories of doc like category:apiDocs. Use the background\_filter of sig text to set the base line to category:caseStudies so that it has a chance to tune into the Chevron/Exxon-related language rather than the general case study vernacular.
Indexing with shingles can help identify key phrases like [oil field] and [shale drilling]
Different choices of heuristic can produce different results.
However all of the above is futile if you only have a handful of truly relevant docs. There just may not be the cohesion and therefore signal strength in the results required to pull out anything meaningful/useful from the content.
---
### Author:  [@hadjebi](https://discuss.elastic.co/u/hadjebi)
#### Post date: [March 1, 2024, 7:53pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/12 "2024-03-01T19:53:39Z")
Thanks very much @Mark_Harwood1.
Will try them.
Any idea how Google highlighting works?
---
### Author:  [@Mark\_Harwood1](https://discuss.elastic.co/u/Mark_Harwood1)
#### Post date: [March 1, 2024, 9:26pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/13 "2024-03-01T21:26:28Z")
> [@hadjebi](#):
>
> Any idea how Google highlighting works?
Not something I've studied, sorry
---
### Author:  [@system](https://discuss.elastic.co/u/system)
#### Post date: [March 29, 2024, 9:26pm UTC](https://discuss.elastic.co/t/is-it-possible-to-do-highlighting-with-knn-and-or-hybrid-search/354511/14 "2024-03-29T21:26:54Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.