You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: solutions/search/vector.md
+25Lines changed: 25 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -46,3 +46,28 @@ The sparse vector approach uses the ELSER model to expand content with semantica
46
46
- Large-scale deployments
47
47
48
48
[Learn more about sparse vector search with ELSER](vector/sparse-vector.md).
49
+
50
+
## Choosing your project's profile
51
+
```{applies_to}
52
+
serverless
53
+
```
54
+
55
+
When selecting a profile configuration for your project, it's recommended to consider your vector search use case.
56
+
You can choose between two profiles: the General Purpose profile and the Vector Optimized profile.
57
+
58
+
**The General Purpose (GP) profile is recommended for most search use cases, including:**
59
+
60
+
- full text search
61
+
- sparse vector-based semantic search (such as when using ELSER)
62
+
- dense vectors compressed using BBQ (enabled by default)
63
+
- sparse vectors
64
+
65
+
**The Vector Optimized (VO) profile is recommended when your use case is based on:**
66
+
67
+
- uncompressed dense vectors with high dimensionality
68
+
69
+
::::{tip}
70
+
71
+
Learn how billing works for your project in [Elasticsearch billing dimensions](../../deploy-manage/cloud-organization/billing/elasticsearch-billing-dimensions.md).
0 commit comments