Skip to content

Commit 3cfdadf

Browse files
prmerger-automator[bot]prmerger-automator[bot]
authored
Merge pull request #123 from HeidiSteen/heidist-rag
prototype new table layout for vector limits
2 parents e121b60 + 23756b3 commit 3cfdadf

File tree

4 files changed

+33
-62
lines changed

4 files changed

+33
-62
lines changed

‎articles/search/search-limits-quotas-capacity.md

Lines changed: 25 additions & 45 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ author: HeidiSteen
88
ms.author: heidist
99
ms.service: cognitive-search
1010
ms.topic: conceptual
11-
ms.date: 06/13/2024
11+
ms.date: 09/04/2024
1212
ms.custom:
1313
- references_regions
1414
- build-2024
@@ -89,63 +89,43 @@ Use the [GET Service Statistics](/rest/api/searchservice/get-service-statistics)
8989

9090
Vector limits vary by service creation date and tier. To check the age of your search service and learn more about vector indexes, see [Vector index size and staying under limits](vector-search-index-size.md).
9191

92-
### Vector limits on services created after May 17, 2024
92+
### Storage quota (GB)
9393

94-
The highest vector limits are available on search services created after May 17, 2024 in a [supported region](#service-limits).
94+
This table shows the progression of storage quota increases in GB over time. Vector quota is per partition, so the increase in vector quota is bound to the increase in per-partition storage for each tier. Higher capacity partitions came online starting in April 2024.
9595

96-
| Tier | Storage quota (GB) | Vector quota per partition (GB) |
97-
|--------|--------------------|---------------------------------|
98-
| Basic | 15 | 5 |
99-
| S1 | 160 | 35 |
100-
| S2 | 512 | 150 |
101-
| S3 | 1,024 | 300 |
102-
| L1 | 2,048 | 150 |
103-
| L2 | 4,096 | 300 |
96+
| Service creation date |Basic | S1| S2 | S3 | L1 | L2 |
97+
|-----------------------|------|---|----|----|----|----|
98+
|**Before July 1, 2023** <sup>1</sup> | 2 | 25 | 100 | 200 | 1,000 | 2,000 |
99+
| **July 1, 2023 through April 3, 2024** <sup>2</sup>| 2 | 25 | 100 | 200 | 1,000 | 2,000 |
100+
|**April 3, 2024 through May 17, 2024** <sup>3</sup> | 15 | 160 | 350 | 700 | 1,000 | 2,000 |
101+
|**After May 17, 2024** <sup>4</sup> | 15 | 160 | 512 | 1,024 | 2,048 | 4,096 |
104102

105-
### Vector limits on services created between April 3, 2024 and May 17, 2024
103+
<sup>1</sup> Partition sizes during early preview.
106104

107-
The following vector limits are available on search services created after April 3, 2024 in a [supported region](#service-limits).
105+
<sup>2</sup> No change during the later preview period.
108106

109-
| Tier | Storage quota (GB) | Vector quota per partition (GB) |
110-
|--------|--------------------|---------|
111-
| Basic | 15 | 5 |
112-
| S1 | 160 | 35 |
113-
| S2 | 350 | 100 |
114-
| S3 | 700 | 200 |
115-
| L1 | 1,000 | 12 |
116-
| L2 | 2,000 | 36 |
107+
<sup>3</sup> Higher capacity storage for Basic, S1, S2, S3 in the following regions. **Americas**: Brazil South​, Canada Central​, Canada East​​, East US​, East US 2, ​Central US​, North Central US​, South Central US​, West US​, West US 2​, West US 3​, West Central US. **Europe**: France Central​. Italy North​​, North Europe​​, Norway East, Poland Central​​, Switzerland North​, Sweden Central​, UK South​, UK West​. **Middle East**: UAE North. **Africa**: South Africa North. **Asia Pacific**: Australia East​, Australia Southeast​​, Central India, Jio India West​, East Asia, Southeast Asia​, Japan East, Japan West​, Korea Central, Korea South​.
117108

118-
Notice that L1 and L2 limits are unchanged in the April 3 rollout.
109+
<sup>4</sup> Higher capacity storage for more tiers and more regions. **Europe**: Germany North​, Germany West Central, Switzerland West​. **Azure Government**: Texas, Arizona, Virginia. **Africa**: South Africa North​. **Asia Pacific**: China North 3, China East 3.
119110

120-
### Vector limits on services created between July 1, 2023 and April 3, 2024
111+
### Vector quota per partition (GB)
121112

122-
The following limits applied to new services created between July 1 and April 3, 2024, except for the following regions, which have the original limits from before July 1, 2023:
113+
This table shows the progression of vector quota increases in GB over time. The quota is per partition, so if you scale a new Standard (S1) service to 6 partitions, total vector quota is 35 multiplied by 6.
123114

124-
+ Germany West Central
125-
+ West India
126-
+ Qatar Central
115+
| Service creation date |Basic | S1| S2 | S3 | L1 | L2 |
116+
|-----------------------|------|---|----|----|----|----|
117+
|**Before July 1, 2023** <sup>1</sup> | 0.5 | 1 | 6 | 12 | 12 | 36 |
118+
| **July 1, 2023 through April 3, 2024** <sup>2</sup>| 1 | 3 | 12 | 36 | 12 | 36 |
119+
|**April 3, 2024 through May 17, 2024** <sup>3</sup> | 5 | 35 | 100 | 200 | 12 | 36 |
120+
|**After May 17, 2024** <sup>4</sup> | 5 | 35 | 150 | 300 | 150 | 300 |
127121

128-
All other regions have these limits:
122+
<sup>1</sup> Initial vector limits during early preview.
129123

130-
| Tier | Storage quota (GB) | Vector quota per partition (GB) |
131-
|--------|--------------------|---------------|
132-
| Basic | 2 | 1 |
133-
| S1 | 25 | 3 |
134-
| S2 | 100 | 12 |
135-
| S3 | 200 | 36 |
136-
| L1 | 1,000 | 12 |
137-
| L2 | 2,000 | 36 |
124+
<sup>2</sup> Vector limits during the later preview period. Three regions didn't have the higher limits: Germany West Central, West India, Qatar Central.
138125

139-
### Vector limits on services created before July 1, 2023
126+
<sup>3</sup> Higher vector quota based on the larger partitions for supported tiers and regions.
140127

141-
| Tier | Storage quota (GB) | Vector quota per partition (GB) |
142-
|--------|--------------------|--------------|
143-
| Basic | 2 | 0.5 |
144-
| S1 | 25 | 1 |
145-
| S2 | 100 | 6 |
146-
| S3 | 200 | 12 |
147-
| L1 | 1,000 | 12 |
148-
| L2 | 2,000 | 36 |
128+
<sup>4</sup> Higher vector quota for more tiers and regions based on partition size updates.
149129

150130
## Indexer limits
151131

‎articles/search/search-reliability.md

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: mattgotteiner
66
ms.author: magottei
77
ms.service: cognitive-search
88
ms.topic: conceptual
9-
ms.date: 01/02/2024
9+
ms.date: 09/04/2024
1010
ms.custom:
1111
- subject-reliability
1212
- references_regions
@@ -55,10 +55,9 @@ Availability zones are used when you add two or more replicas to your search ser
5555

5656
### Supported regions
5757

58-
Support for availability zones depends on infrastructure and storage. Currently, two zones that were announced in October 2023 have insufficient storage and don't provide an availability zone for Azure AI Search:
58+
Support for availability zones depends on infrastructure and storage. Currently, the following zone has insufficient storage and doesn't provide an availability zone for Azure AI Search:
5959

60-
+ Israel Central
61-
+ Italy North
60+
+ Japan West
6261

6362
Otherwise, availability zones for Azure AI Search are supported in the following regions:
6463

@@ -75,6 +74,8 @@ Otherwise, availability zones for Azure AI Search are supported in the following
7574
| East US 2 | January 30, 2021 or later |
7675
| France Central| October 23, 2020 or later |
7776
| Germany West Central | May 3, 2021, or later |
77+
| Israel Central | April 1, 2024, or later |
78+
| Italy North | April 1, 2024, or later |
7879
| Japan East | January 30, 2021 or later |
7980
| Korea Central | January 20, 2022 or later |
8081
| North Europe | January 28, 2021 or later |

‎articles/search/vector-search-index-size.md

Lines changed: 2 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -30,12 +30,7 @@ For each vector field, Azure AI Search constructs an internal vector index using
3030

3131
+ Vector indexes are also subject to disk quota, in the sense that all indexes are subject disk quota. There's no separate disk quota for vector indexes.
3232

33-
+ Vector quotas are enforced on the search service as a whole, per partition, meaning that if you add partitions, vector quota goes up. Per-partition vector quotas are higher on newer services:
34-
35-
+ [Vector quota for services created after May 17, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-after-may-17-2024)
36-
+ [Vector quota for services between April 3, 2024 and May 17, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-between-april-3-2024-and-may-17-2024)
37-
+ [Vector quota for services created between July 1, 2023 and April 3, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-between-july-1-2023-and-april-3-2024)
38-
+ [Vector quota for services created before July 1, 2023](search-limits-quotas-capacity.md#vector-limits-on-services-created-before-july-1-2023)
33+
+ Vector quotas are enforced on the search service as a whole, per partition, meaning that if you add partitions, vector quota goes up. Per-partition vector quotas are higher on newer services. For more information, see [Vector index size limits](search-limits-quotas-capacity.md#vector-index-size-limits).
3934

4035
## How to check partition size and quantity
4136

@@ -63,12 +58,7 @@ Newer services created after April 3, 2024 offer five to ten times more vector s
6358

6459
:::image type="content" source="media/vector-search-index-size/deployment-details.png" alt-text="Screenshot of the deployment details showing creation date.":::
6560

66-
1. Now that you know the age of your search service, review the vector quota limits based on service creation:
67-
68-
+ [After May 17, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-after-may-17-2024)
69-
+ [Between April 3, 2024 and May 17, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-between-april-3-2024-and-may-17-2024)
70-
+ [Between July 1, 2023 and April 3, 2024](search-limits-quotas-capacity.md#vector-limits-on-services-created-between-july-1-2023-and-april-3-2024)
71-
+ [Before July 1, 2023](search-limits-quotas-capacity.md#vector-limits-on-services-created-before-july-1-2023)
61+
1. Now that you know the age of your search service, review the vector quota limits based on service creation: [Vector index size limits](search-limits-quotas-capacity.md#vector-index-size-limits).
7262

7363
## How to get vector index size
7464

‎articles/search/whats-new.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ ms.custom:
7373
|-----------------------------|------|--------------|
7474
| [Security update addressing information disclosure](https://msrc.microsoft.com/update-guide/vulnerability/CVE-2024-29063) | API | GET responses [no longer return connection strings or keys](search-api-migration.md#breaking-change-for-client-code-that-reads-connection-information). Applies to GET Skillset, GET Index, and GET Indexer. This change helps protect your Azure assets integrated with AI Search from unauthorized access. |
7575
| [More storage on Basic and Standard tiers](search-limits-quotas-capacity.md#service-limits) | Infrastructure | Basic now supports up to three partitions and three replicas. Basic and Standard (S1, S2, S3) tiers have significantly more storage per partition, at the same per-partition billing rate. Extra capacity is subject to [regional availability](search-limits-quotas-capacity.md#service-limits) and applies to new search services created after April 3, 2024. Currently, there's no in-place upgrade, so you must create a new search service to get the extra storage. |
76-
| [More quota for vectors](search-limits-quotas-capacity.md#vector-limits-on-services-created-between-april-3-2024-and-may-17-2024) | Infrastructure | Vector quotas are also higher on new services created after April 3, 2024 in selected regions. |
76+
| [More quota for vectors](search-limits-quotas-capacity.md#vector-index-size-limits) | Infrastructure | Vector quotas are also higher on new services created after April 3, 2024 in selected regions. |
7777
| [Vector quantization, narrow vector data types, and a new `stored` property (preview)](vector-search-how-to-configure-compression-storage.md) | Feature | Collectively, these three features add vector compression and smarter storage options. First, *scalar quantization* reduces vector index size in memory and on disk. Second, [narrow data types](/rest/api/searchservice/supported-data-types) reduce per-field storage by storing smaller values. Third, you can use `stored` to opt-out of storing the extra copy of a vector that's used only for search results. If you don't need vectors in a query response, you can set `stored` to false to save on space. |
7878
| [2024-03-01-preview Search REST API](/rest/api/searchservice/search-service-api-versions#2024-03-01-preview) | API | New preview version of the Search REST APIs for the new data types, vector compression properties, and vector storage options. |
7979
| [2024-03-01-preview Management REST API](/rest/api/searchmanagement/operation-groups?view=rest-searchmanagement-2024-03-01-preview&preserve-view=true) | API | New preview version of the Management REST APIs for control plane operations. |

0 commit comments

Comments
 (0)