Skip to content
17 changes: 17 additions & 0 deletions docs/reference/elasticsearch/mapping-reference/semantic-text.md
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,23 @@ the embedding generation, indexing, and query to use.
[quantized](/reference/elasticsearch/mapping-reference/dense-vector.md#dense-vector-quantization)
to `bbq_hnsw` automatically.

{applies_to}`stack: preview 9.1` If you use the preconfigured `.elser-2-elastic` endpoint that utilizes the ELSER model as a service (ELSER on EIS), you can
set up `semantic_text` with the following API request:

```console
PUT my-index-000001
{
"mappings": {
"properties": {
"inference_field": {
"type": "semantic_text",
"inference_id": ".elser-2-elastic"
}
}
}
}
```
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we move this example to after the custom inference endpoint mapping setup example? Putting this first may give users the idea that this is the recommended approach.

Also, can we call out that the .elser-2-elastic endpoint is tech preview and should not be used for production?

If any dedicated docs exist for ELSER on EIS, it would be good to link to them here too.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for your feedback, @Mikep86! I've addressed it via 2cd12a5.


If you use the preconfigured `.elser-2-elasticsearch` endpoint, you can set up
`semantic_text` with the following API request:

Expand Down
Loading