Skip to content

Commit dae99f4

Browse files
[E&A] Creates a page for guidance on when to use EIS and when to use ML nodes (#3124)
## Overview Related issue: elastic/search-team#11055 and #3008 This PR creates a page under the EIS section about when to use EIS and when to use ML nodes. --------- Co-authored-by: Sean Handley <[email protected]> Co-authored-by: Sean Handley <[email protected]>
1 parent a0c782f commit dae99f4

File tree

2 files changed

+57
-0
lines changed

2 files changed

+57
-0
lines changed
Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
---
2+
navigation_title: ML-nodes vs EIS
3+
applies_to:
4+
stack: ga
5+
serverless: ga
6+
deployment:
7+
self: unavailable
8+
---
9+
10+
# Using ML-nodes or Elastic {{infer-cap}} Service (EIS) [ml-nodes-vs-eis]
11+
12+
## When to use EIS?
13+
14+
The Elastic Inference Service (EIS) requires zero setup or management. It's always-on, has excellent ingest throughput, and uses simple token-based billing.
15+
16+
Use EIS if you're getting started with [semantic search](/solutions/search/semantic-search.md) or [hybrid search](/solutions/search/hybrid-search.md) and want a smooth experience. Under the hood, EIS uses GPUs for ML {{infer}}, which are more efficient and allow a faster, more cost-effective experience for most usecases.
17+
18+
## When to use {{ml}} nodes?
19+
20+
ML nodes are a more configurable solution than EIS where you can set up specific nodes using CPUs to execute [ML {{infer}}](/explore-analyze/elastic-inference/inference-api.md). {{ml-cap}} nodes tend to give more fine-grained control.
21+
22+
Use ML nodes if you want to decide how your models run, you want to run custom models, or you have a self-managed setup.
23+
24+
## How do I switch from using ML nodes to EIS on an existing index?
25+
26+
```{applies_to}
27+
stack: ga 9.3
28+
serverless: ga
29+
```
30+
31+
```console
32+
PUT /my-ml-node-index/_mapping
33+
{
34+
"properties": {
35+
"text": {
36+
"type": "semantic_text",
37+
"inference_id": ".elser-2-elastic"
38+
}
39+
}
40+
}
41+
```
42+
43+
You can also switch an EIS-based index to use ML nodes:
44+
45+
```console
46+
PUT /my-eis-index/_mapping
47+
{
48+
"properties": {
49+
"text": {
50+
"type": "semantic_text",
51+
"inference_id": ".elser-2-elasticsearch"
52+
}
53+
}
54+
}
55+
```

explore-analyze/toc.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -41,6 +41,8 @@ toc:
4141
- file: elastic-inference.md
4242
children:
4343
- file: elastic-inference/eis.md
44+
children:
45+
- hidden: elastic-inference/ml-node-vs-eis.md
4446
- file: elastic-inference/inference-api.md
4547
- file: machine-learning.md
4648
children:

0 commit comments

Comments
 (0)