From c23c84fb43c524b73964e3010e733c52979e97db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Tue, 23 Sep 2025 14:42:08 +0200 Subject: [PATCH 1/5] [E&A] Makes EIS availability information more granular. --- explore-analyze/elastic-inference/eis.md | 9 +++++++-- explore-analyze/elastic-inference/inference-api.md | 2 +- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/explore-analyze/elastic-inference/eis.md b/explore-analyze/elastic-inference/eis.md index 43aa8fefd4..81f7e23c67 100644 --- a/explore-analyze/elastic-inference/eis.md +++ b/explore-analyze/elastic-inference/eis.md @@ -1,8 +1,11 @@ --- navigation_title: Elastic Inference Service (EIS) applies_to: - stack: ga 9.0 serverless: ga + deployment: + ess: ga + eck: ga + ece: ga --- # Elastic {{infer-cap}} Service [elastic-inference-service-eis] @@ -27,7 +30,9 @@ ELSER requests are managed by Elastic's own EIS infrastructure. ## ELSER via Elastic {{infer-cap}} Service (ELSER on EIS) [elser-on-eis] ```{applies_to} -stack: preview 9.1 +ess: preview 9.1 +eck: preview 9.1 +ece: preview 9.1 serverless: preview ``` diff --git a/explore-analyze/elastic-inference/inference-api.md b/explore-analyze/elastic-inference/inference-api.md index a185fe9d04..e5e13a7fdc 100644 --- a/explore-analyze/elastic-inference/inference-api.md +++ b/explore-analyze/elastic-inference/inference-api.md @@ -30,7 +30,7 @@ The following section lists the default {{infer}} endpoints, identified by their ### Default endpoints for Elastic {{infer-cap}} Service (EIS) -- `.elser-2-elastic`: uses the [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) trained model as an Elastic {{infer-cap}} Service for `sparse_embedding` tasks (recommended for English language text). The `model_id` is `.elser_model_2`. {applies_to}`stack: preview 9.1` {applies_to}`serverless: preview` +- `.elser-2-elastic`: uses the [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) trained model as an Elastic {{infer-cap}} Service for `sparse_embedding` tasks (recommended for English language text). The `model_id` is `.elser_model_2`. {applies_to}`ess: preview 9.1` {applies_to}`eck: preview 9.1` {applies_to}`ece: preview 9.1` {applies_to}`serverless: preview` ### Default endpoints used on ML-nodes From 1b94da628333e06f4e31454f07d0008cf35f0ef3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Tue, 23 Sep 2025 14:51:11 +0200 Subject: [PATCH 2/5] [DOCS] Clean up the mess. --- explore-analyze/elastic-inference/eis.md | 5 ++--- explore-analyze/elastic-inference/inference-api.md | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/explore-analyze/elastic-inference/eis.md b/explore-analyze/elastic-inference/eis.md index 81f7e23c67..69e87d50b6 100644 --- a/explore-analyze/elastic-inference/eis.md +++ b/explore-analyze/elastic-inference/eis.md @@ -1,11 +1,10 @@ --- navigation_title: Elastic Inference Service (EIS) applies_to: + stack: ga serverless: ga deployment: - ess: ga - eck: ga - ece: ga + self: unavailable --- # Elastic {{infer-cap}} Service [elastic-inference-service-eis] diff --git a/explore-analyze/elastic-inference/inference-api.md b/explore-analyze/elastic-inference/inference-api.md index e5e13a7fdc..9720fcf179 100644 --- a/explore-analyze/elastic-inference/inference-api.md +++ b/explore-analyze/elastic-inference/inference-api.md @@ -30,7 +30,7 @@ The following section lists the default {{infer}} endpoints, identified by their ### Default endpoints for Elastic {{infer-cap}} Service (EIS) -- `.elser-2-elastic`: uses the [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) trained model as an Elastic {{infer-cap}} Service for `sparse_embedding` tasks (recommended for English language text). The `model_id` is `.elser_model_2`. {applies_to}`ess: preview 9.1` {applies_to}`eck: preview 9.1` {applies_to}`ece: preview 9.1` {applies_to}`serverless: preview` +- `.elser-2-elastic`: uses the [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) trained model as an Elastic {{infer-cap}} Service for `sparse_embedding` tasks (recommended for English language text). The `model_id` is `.elser_model_2`. {applies_to}`stack: preview 9.1` {applies_to}`self: unavailable` {applies_to}`serverless: preview` ### Default endpoints used on ML-nodes From db7a06ea1e09ec471f8bbaf4d96acb942ea85374 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Tue, 23 Sep 2025 14:54:31 +0200 Subject: [PATCH 3/5] [E&A] More edits. --- explore-analyze/elastic-inference/eis.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/explore-analyze/elastic-inference/eis.md b/explore-analyze/elastic-inference/eis.md index 69e87d50b6..392b4897da 100644 --- a/explore-analyze/elastic-inference/eis.md +++ b/explore-analyze/elastic-inference/eis.md @@ -29,10 +29,10 @@ ELSER requests are managed by Elastic's own EIS infrastructure. ## ELSER via Elastic {{infer-cap}} Service (ELSER on EIS) [elser-on-eis] ```{applies_to} -ess: preview 9.1 -eck: preview 9.1 -ece: preview 9.1 +stack: preview 9.1 serverless: preview +deployment: + self: unavailable ``` ELSER on EIS enables you to use the ELSER model on GPUs, without having to manage your own ML nodes. We expect better performance for throughput and latency than ML nodes, and will continue to benchmark, remove limitations and address concerns as we move towards General Availability. From 9e0e84fe3fa05090cb8bd466be6e6785f3efc949 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Tue, 23 Sep 2025 14:58:43 +0200 Subject: [PATCH 4/5] [E&A] Edits inline applies_to. --- explore-analyze/elastic-inference/eis.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/explore-analyze/elastic-inference/eis.md b/explore-analyze/elastic-inference/eis.md index 392b4897da..1feda7526c 100644 --- a/explore-analyze/elastic-inference/eis.md +++ b/explore-analyze/elastic-inference/eis.md @@ -17,7 +17,7 @@ Instead, you can use {{ml}} models for ingest, search, and chat independently of * Your Elastic deployment or project comes with a default [`Elastic Managed LLM` connector](https://www.elastic.co/docs/reference/kibana/connectors-kibana/elastic-managed-llm). This connector is used in the AI Assistant, Attack Discovery, Automatic Import and Search Playground. -* You can use [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) to perform semantic search as a service (ELSER on EIS). {applies_to}`stack: preview 9.1` {applies_to}`serverless: preview` +* You can use [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) to perform semantic search as a service (ELSER on EIS). {applies_to}`stack: preview 9.1` {applies_to}`self: unavailable` {applies_to}`serverless: preview` ## Region and hosting [eis-regions] From 3edc3f0eeda52a52a93a08944b69744c04b8ed9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Tue, 23 Sep 2025 15:03:23 +0200 Subject: [PATCH 5/5] [E&A] addresses feedback. --- explore-analyze/elastic-inference/eis.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/explore-analyze/elastic-inference/eis.md b/explore-analyze/elastic-inference/eis.md index 1feda7526c..2782d800dc 100644 --- a/explore-analyze/elastic-inference/eis.md +++ b/explore-analyze/elastic-inference/eis.md @@ -17,7 +17,7 @@ Instead, you can use {{ml}} models for ingest, search, and chat independently of * Your Elastic deployment or project comes with a default [`Elastic Managed LLM` connector](https://www.elastic.co/docs/reference/kibana/connectors-kibana/elastic-managed-llm). This connector is used in the AI Assistant, Attack Discovery, Automatic Import and Search Playground. -* You can use [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) to perform semantic search as a service (ELSER on EIS). {applies_to}`stack: preview 9.1` {applies_to}`self: unavailable` {applies_to}`serverless: preview` +* You can use [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) to perform semantic search as a service (ELSER on EIS). {applies_to}`stack: preview 9.1` {applies_to}`serverless: preview` ## Region and hosting [eis-regions] @@ -31,8 +31,6 @@ ELSER requests are managed by Elastic's own EIS infrastructure. ```{applies_to} stack: preview 9.1 serverless: preview -deployment: - self: unavailable ``` ELSER on EIS enables you to use the ELSER model on GPUs, without having to manage your own ML nodes. We expect better performance for throughput and latency than ML nodes, and will continue to benchmark, remove limitations and address concerns as we move towards General Availability.