github-mirrors/elasticsearch
1
0
Fork 0
mirror of https://github.com/elastic/elasticsearch.git synced 2025-04-19 04:45:07 -04:00
Code Issues Projects Releases Packages Wiki Activity

Updating text_similarity_reranker documentation (#126175)

Browse source 
* Updating text_similarity_reranker documentation

* Updating docs to include urls

* remove extra THE from the text

---------

Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
This commit is contained in:
Samiul Monir 2025-04-16 17:05:30 -04:00 • committed by GitHub
parent 22adfeb9e1
commit 2e1101cf5e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
docs/reference/elasticsearch/rest-apis/retrievers.md
View file

@ -560,11 +560,11 @@ Refer to [*Semantic re-ranking*](docs-content://solutions/search/ranking/semanti
### Prerequisites [_prerequisites_15]
To use `text_similarity_reranker` you must first set up an inference endpoint for the `rerank` task using the [Create {{infer}} API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put). The endpoint should be set up with a machine learning model that can compute text similarity. Refer to [the Elastic NLP model reference](docs-content://explore-analyze/machine-learning/nlp/ml-nlp-model-ref.md#ml-nlp-model-ref-text-similarity) for a list of third-party text similarity models supported by {{es}}.
To use `text_similarity_reranker`, you can rely on the preconfigured `.rerank-v1-elasticsearch` inference endpoint, which is based on [Elastic Rerank](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-rerank.html) and serves as the default if no `inference_id` is provided. This model is optimized for reranking based on text similarity. If you'd like to use a different model, you can set up a custom inference endpoint for the `rerank` task using the [Create {{infer}} API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put). The endpoint should be configured with a machine learning model capable of computing text similarity. Refer to [the Elastic NLP model reference](docs-content://explore-analyze/machine-learning/nlp/ml-nlp-model-ref.md#ml-nlp-model-ref-text-similarity) for a list of third-party text similarity models supported by {{es}}.
You have the following options:
* Use the the built-in [Elastic Rerank](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put) cross-encoder model via the inference API’s {{es}} service.
* Use the built-in [Elastic Rerank](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put) cross-encoder model via the inference API’s {{es}} service. For an example of creating an endpoint using the Elastic Rerank model, refer to [this guide](https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-elasticsearch.html#inference-example-elastic-reranker).
* Use the [Cohere Rerank inference endpoint](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put) with the `rerank` task type.
* Use the [Google Vertex AI inference endpoint](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put) with the `rerank` task type.
* Upload a model to {{es}} with [Eland](eland://reference/machine-learning.md#ml-nlp-pytorch) using the `text_similarity` NLP task type.
@ -606,9 +606,9 @@ score = ln(score), if score < 0
`inference_id`
: (Required, `string`)
: (Optional, `string`)
Unique identifier of the inference endpoint created using the {{infer}} API.
Unique identifier of the inference endpoint created using the {{infer}} API. If you don’t specify an inference endpoint, the `inference_id` field defaults to `.rerank-v1-elasticsearch`, a preconfigured endpoint for the elasticsearch `.rerank-v1` model.
`inference_text`